Position within the page tree

Institute for Natural Language Processing
Institute
Team
Padó, Sebastian

Sebastian Padó

Prof. Dr.

Chair of Theoretical Computational Linguistics, Managing Director of the IMS
Institute for Natural Language Processing (IMS)
Theoretical Computational Linguistics

Contact

+49 711 685 81400
Email
Website

Pfaffenwaldring 5 b
70569 Stuttgart
Deutschland
Room: 02.020

Office Hours

By appointment (per email).

Subject

I head a research group (mostly) on computational semantics. That is, we are interested in developing software that enables computers to reason about the meaning of words and sentences.

You can find more details on the page of my research group.

Publications

Publications by Sebastian Padó:

2023
1. Troiano, E., Klinger, R., & Padó, S. (2023). On the Relationship between Frames and Emotionality in Text. Northern European Journal of Language Technology, 9(1), Article 1. https://doi.org/10.3384/nejlt.2000-1533.2023.4361
  - BibTeX
  - Link
  BibTeX
  @article{troiano22:_relat_predic_argum_struc_emotion_text, abstract = {Emotions, which are responses to salient events, can be realized in text implicitly, for instance with mere references to facts (e.g., “That was the beginning of a long war”). Interpreting affective meanings thus relies on the readers’ background knowledge, but that is hardly modeled in computational emotion analysis. Much work in the field is focused on the word level and treats individual lexical units as the fundamental emotion cues in written communication. We shift our attention to word relations. We leverage Frame Semantics, a prominent theory for the description of predicate-argument structures, which matches the study of emotions: frames build on a “semantics of understanding” whose assumptions rely precisely on people’s world knowledge. Our overarching question is whether and to what extent the events that are represented by frames possess an emotion meaning. To carry out a large corpus-based correspondence analysis, we automatically annotate texts with emotions as well as with FrameNet frames and roles, and we analyze the correlations between them. Our main finding is that substantial groups of frames have an emotional import. With an extensive qualitative analysis, we show that they capture several properties of emotions that are purported by theories from psychology. These observations boost insights on the two strands of research that we bring together: emotion analysis can profit from the event-based perspective of frame semantics; in return, frame semantics gains a better grip of its position vis-a-vis emotions, an integral part of word meanings.}, author = {Troiano, Enrica and Klinger, Roman and Padó, Sebastian}, journal = {Northern European Journal of Language Technology}, number = 1, title = {On the Relationship between Frames and Emotionality in Text}, url = {https://doi.org/10.3384/nejlt.2000-1533.2023.4361}, volume = 9, year = 2023 }
  Link
  https://doi.org/10.3384/nejlt.2000-1533.2023.4361
2. Nikolaev, D., Baker, C., Petruck, M. R. L., & Padó, S. (2023). Adverbs, surprisingly. Proceedings of STARSEM. https://aclanthology.org/2023.starsem-1.44.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{nikolaev23:_adver, abstract = {This paper begins with the premise that adverbs are neglected in computational linguistics. This view derives from two analyses: a literature review and a novel adverb dataset to probe a state-of-the-art language model, thereby uncovering systematic gaps in accounts for adverb meaning. We suggest that using Frame Semantics for characterizing word meaning, as in FrameNet, provides a promising approach to adverb analysis, given its ability to describe ambiguity, semantic roles, and null instantiation. }, address = {Toronto, Canada}, author = {Nikolaev, Dmitry and Baker, Collin and Petruck, Miriam R. L. and Padó, Sebastian}, booktitle = {Proceedings of STARSEM}, title = {Adverbs, surprisingly}, url = {https://aclanthology.org/2023.starsem-1.44.pdf}, year = 2023 }
  Link
  https://aclanthology.org/2023.starsem-1.44.pdf
3. Nikolaev, D., & Padó, S. (2023). Investigating semantic subspaces of Transformer sentence embeddings through linear structural probing. Proceedings of the BlackboxNLP Workshop. https://aclanthology.org/2023.blackboxnlp-1.11
  - BibTeX
  - Link
  BibTeX
  @inproceedings{nikolaev23:_inves_trans, abstract = { The question of what kinds of linguistic information are encoded in different layers of Transformer-based language models is of considerable interest for the NLP community. Existing work, however, has overwhelmingly focused on word-level representations and encoder-only language models with the masked-token training objective. In this paper, we present experiments with semantic structural probing, a method for studying sentence-level representations via finding a subspace of the embedding space that provides suitable task-specific pairwise distances between data-points. We apply our method to language models from different families (encoder-only, decoder-only, encoder-decoder) and of different sizes in the context of two tasks, semantic textual similarity and natural-language inference. We find that model families differ substantially in their performance and layer dynamics, but that the results are largely model-size invariant.}, address = {Singapore}, author = {Nikolaev, Dmitry and Padó, Sebastian}, booktitle = {Proceedings of the BlackboxNLP workshop}, title = {Investigating semantic subspaces of Transformer sentence embeddings through linear structural probing}, url = {https://aclanthology.org/2023.blackboxnlp-1.11}, year = 2023 }
  Link
  https://aclanthology.org/2023.blackboxnlp-1.11
2022
1. Lehmann, J., & Padó, S. (2022). Clasificación de Tragedias y Comedias en las Comedias Nuevas de Calderón de la Barca. Revista de Humanidades Digitales, 7, 80–103. https://doi.org/10.5944/rhd.vol.7.2022.34588
  - BibTeX
  - Link
  BibTeX
  @article{lehmann23:_clasif_traged_comed_comed_nuevas_calder_barca, abstract = {In this study, we aim at distinguishing comedies and tragedies among 112 dramas written by Calderón de la Barca, using procedures established by distri-butional semantics. Fifteen of these comedias nuevas have already been classified by qualitative re-searchers as either tragedies or comedies, respec-tively; for another 82 dramas the classification was unknown. Four independent document embedding methods are explored, which differ from each other in matrix creation and reduction, and in the calcula-tion of similarity or distance matrices. The best results –measured against the pre-established classification of these dramas–are obtained through the classifi-cation procedure that applied the strongest matrix reduction. In addition, a contrastive vocabulary anal-ysis with word embeddings is carried out, based either on word lists produced by the four tested methods, or on the log-likelihood probability distri-bution for two sub-corpora containing only dramas already determined to be comedies or tragedies. This step permits the identification of 130 terms that are each discriminative either of comedies or of tragedies. The outcome shows that the explored methods identify tragedies with greater accuracy than comedies, indicating that tragedies have more distinctive features. It also becomes apparent that one could more appropriately consider classifications such as tragedy and comedy as poles between which gradual differences can be observed, where-by the ensuing transitional area contains comedias nuevas that have been described in prior research as tragicomedias or comedias mitológicas.}, author = {Lehmann, Jörg and Padó, Sebastian}, doi = {10.5944/rhd.vol.7.2022.34588}, journal = {Revista de Humanidades Digitales}, note = {Spanish version of Lehmann and Padó (ZfDG 2022) modulo reviewer comments}, pages = {80-103}, title = {Clasificación de Tragedias y Comedias en las Comedias Nuevas de Calderón de la Barca}, url = {https://revistas.uned.es/index.php/RHD/article/view/34588/27466}, volume = 7, year = 2022 }
  Link
  https://revistas.uned.es/index.php/RHD/article/view/34588/27466
2. Padó, S., & Hole, D. (2022). Distributional Analysis of Polysemous Function Words. Proceedings of the 13th International Tbilisi Symposium on Language, Logic and Computation 2019, 13206. https://doi.org/10.1007/978-3-030-98479-3_6
  - BibTeX
  - Link
  BibTeX
  @inproceedings{hole19:_distr_analy_funct_words, abstract = {In this paper, we are concerned with the phenomenon of function word polysemy. We adopt the framework of distributional semantics, which characterizes word meaning by observing occurrence contexts in large corpora and which is in principle well situated to model polysemy. Nevertheless, function words were traditionally considered as impossible to analyze distributionally due to their highly flexible usage patterns. We establish that contextualized word embeddings, the most recent generation of distributional methods, offer hope in this regard. Using the German reflexive pronoun 'sich' as an example, we find that contextualized word embeddings capture theoretically motivated word senses for 'sich' to the extent to which these senses are mirrored systematically in linguistic usage.}, author = {Padó, Sebastian and Hole, Daniel}, booktitle = {Proceedings of the 13th International Tbilisi Symposium on Language, Logic and Computation 2019}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Distributional Analysis of Polysemous Function Words}, url = {https://doi.org/10.1007/978-3-030-98479-3_6}, volume = 13206, year = 2022 }
  Link
  https://doi.org/10.1007/978-3-030-98479-3_6
3. Lehmann, J., & Padó, S. (2022). Classification of comedies and tragedies written in Calderón de la Barca’s Comedias Nuevas. Zeitschrift Für Digitale Geisteswissenschaft, 7. https://doi.org/10.17175/2022_012
  - BibTeX
  - Link
  BibTeX
  @article{lehmann22:_class_calder_barca, abstract = {In this study, we aim at distinguishing comedies and tragedies among 112 dramas written by Calderón de la Barca, using procedures established by distributional semantics. 15 each of these comedias nuevas have already been classified by qualitative researchers as either tragedies or comedies, respectively; for another 82 dramas the classification was unknown. Four independent document embedding methods are explored, which differ from each other in matrix creation and reduction, and in the calculation of similarity or distance matrices. The best results – measured against the pre-established classification of these dramas – are obtained through the classification procedure that applied the strongest matrix reduction. In addition, a contrastive vocabulary analysis with word embeddings is carried out, based either on word lists produced by the four tested methods, or on the log-likelihood probability distribution for two sub-corpora containing only dramas already determined to be comedies or tragedies. This step permits the identification of 130 terms that are each discriminative either of comedies or of tragedies. The outcome shows that the explored methods identify tragedies with greater accuracy than comedies, indicating that tragedies show stronger lexical cohesion. It also becomes apparent that one could more appropriately consider classifications such as ›tragedy‹ and ›comedy‹ as poles between which gradual differences can be observed, whereby the ensuing transitional area contains comedias nuevas that have been described in prior research as tragicomedias or comedias mitológicas.}, author = {Lehmann, Jörg and Padó, Sebastian}, journal = {Zeitschrift für Digitale Geisteswissenschaft}, note = {English version of Lehmann and Padó (RHD 2022) modulo reviewer comments}, title = {Classification of comedies and tragedies written in {Calderón de la Barca's Comedias Nuevas}}, url = {https://doi.org/10.17175/2022_012}, volume = 7, year = 2022 }
  Link
  https://doi.org/10.17175/2022_012
4. Papay, S., Klinger, R., & Padó, S. (2022). Constraining Linear-chain CRFs to Regular Languages. Proceedings of ICLR. https://openreview.net/forum?id=jbrgwbv8nD
  - BibTeX
  - Link
  BibTeX
  @inproceedings{papay2021constraining, abstract = {A major challenge in structured prediction is to represent the interdependencies within output structures. When outputs are structured as sequences, linear-chain conditional random fields (CRFs) are a widely used model class which can learn local dependencies in the output. However, the CRF's Markov assumption makes it impossible for CRFs to represent distributions with nonlocal dependencies, and standard CRFs are unable to respect nonlocal constraints of the data (such as global arity constraints on output labels). We present a generalization of CRFs that can enforce a broad class of constraints, including nonlocal ones, by specifying the space of possible output structures as a regular language L. The resulting regular-constrained CRF (RegCCRF) has the same formal properties as a standard CRF, but assigns zero probability to all label sequences not in L. Notably, RegCCRFs can incorporate their constraints during training, while related models only enforce constraints during decoding. We prove that constrained training is never worse than constrained decoding, and show empirically that it can be substantially better in practice. Additionally, we demonstrate a practical benefit on downstream tasks by incorporating a RegCCRF into a deep neural model for semantic role labeling, exceeding state-of-the-art results on a standard dataset.}, author = {Papay, Sean and Klinger, Roman and Padó, Sebastian}, booktitle = {Proceedings of ICLR}, note = {Long video presentation at <a href="https://www.youtube.com/watch?v=iVH5-cHWaiE">https://www.youtube.com/watch?v=iVH5-cHWaiE</a>}, title = {Constraining Linear-chain CRFs to Regular Languages}, url = {https://openreview.net/forum?id=jbrgwbv8nD}, year = 2022 }
  Link
  https://openreview.net/forum?id=jbrgwbv8nD
5. Sikos, J., Roth, M., & Padó, S. (2022). Improving Multilingual Frame Identification by Estimating Frame Transferability. Linguistic Issues in Language Technology, 19. https://doi.org/10.33011/lilt.v19i.939
  - BibTeX
  - Link
  BibTeX
  @article{sikos:_improv_multil_frame_ident_estim_frame_trans, abstract = {A recent research direction in computational linguistics involves efforts to make the field, which used to focus primarily on English, more multilingual and inclusive. However, resource creation often remains a bottleneck for many languages, in particular at the semantic level. In this article, we consider the case of frame-semantic annotation. We investigate how to perform frame selection for annotation in a target language by taking advantage of existing annotations in different, supplementary languages, with the goal of reducing the required annotation effort in the target language. We measure success by training and testing frame identification models for the target language. We base our selection methods on measuring frame transferability in the supplementary language, where we estimate which frames will transfer poorly, and therefore should receive more annotation, in the target language. We apply our approach to English, German, and French – three languages which have annotations that are similar in size as well as frames with overlapping lexicographic definitions. We find that transferability is indeed a useful indicator and supports a setup where a limited amount of target language data is sufficient to train frame identification systems.}, author = {Sikos, Jen and Roth, Michael and Padó, Sebastian}, journal = {Linguistic Issues in Language Technology}, title = {Improving Multilingual Frame Identification by Estimating Frame Transferability}, url = {https://doi.org/10.33011/lilt.v19i.939}, volume = 19, year = 2022 }
  Link
  https://doi.org/10.33011/lilt.v19i.939
2021
1. Iordachioaia, G., Lapesa, G., Meyer, S., & Padó, S. (2021). Difference of first attestation dates as evidence for directionality in zero derivation. Proceedings of the DGfS Workshop on the Semantics of Derivational Morphology.
  - BibTeX
  BibTeX
  @inproceedings{iordachioaia21:_differ, address = {Freiburg im Breisgau, Germany}, author = {Iord\u{a}chioaia, Gianina and Lapesa, Gabriella and Meyer, Sabrina and Padó, Sebastian}, booktitle = {Proceedings of the {DGfS} workshop on the semantics of derivational morphology}, title = {Difference of first attestation dates as evidence for directionality in zero derivation}, year = 2021 }
2. Westera, M., Gupta, A., Boleda, G., & Padó, S. (2021). Distributional models of category concepts based on names of category members. Cognitive Science, 45(9), Article 9. https://doi.org/10.1111/cogs.13029
  - BibTeX
  - Link
  BibTeX
  @article{westera:_word, abstract = { Cognitive scientists have long used distributional semantic representations of categories. The predominant approach uses distributional representations of category-denoting nouns, like "city" for the category city. We propose a novel scheme that represents categories as prototypes over representations of \textit{names} of its members, such as "Barcelona", "Mumbai", and "Wuhan" for the category city. This name-based representation empirically outperforms the noun-based representation on two experiments (modelling human judgments of category relatedness and predicting category membership) with particular improvements for ambiguous nouns. We discuss the model complexity of both classes of models and argue that the name-based model has superior explanatory potential with regard to concept acquisition.}, author = {Westera, Matthijs and Gupta, Abhijeet and Boleda, Gemma and Padó, Sebastian}, journal = {Cognitive Science}, number = 9, pages = {e13029}, title = {Distributional models of category concepts based on names of category members}, url = {https://doi.org/10.1111/cogs.13029}, volume = 45, year = 2021 }
  Link
  https://doi.org/10.1111/cogs.13029
3. Varvara, R., Lapesa, G., & Padó, S. (2021). Grounding Semantic Transparency In Context: A Distributional Semantic Study on German Event Nominalizations. Morphology, 31, 409–446. https://doi.org/10.1007/s11525-021-09382-w
  - BibTeX
  - Link
  BibTeX
  @article{varvara:_groun_seman_trans_in_contex, abstract = { We present the results of a large-scale corpus-based comparison of two German event nominalization patterns: deverbal nouns in -ung (e.g., die Evaluierung, 'the evaluation') and nominal infinitives (e.g., das Evaluieren, 'the evaluating'). Among the many available event nominalization patterns for German, we selected these two because they are both highly productive and challenging from the semantic point of view. Both patterns are known to keep a tight relation with the event denoted by the base verb, but with different nuances. Our study targets a better understanding of the differences in their semantic import. The key notion of our comparison is that of semantic transparency, and we propose a usage-based characterization of the relationship between derived nominals and their bases. Using methods from distributional semantics, we bring to bear two concrete measures of transparency which highlight different nuances: the first one, cosine, detects nominalizations which are semantically similar to their bases; the second one, distributional inclusion, detects nominalizations which are used in a subset of the contexts of the base verb. We find that the inclusion measure helps in characterizing the difference between the two types of nominalizations, in relation with the traditionally considered variable of relative frequency (Hay, 2001). We further benefit from our distributional analysis to frame our comparison in the broader coordinates of the inflection vs. derivation cline.}, author = {Varvara, Rossella and Lapesa, Gabriella and Padó, Sebastian}, journal = {Morphology}, pages = {409-446}, title = {Grounding Semantic Transparency In Context: A Distributional Semantic Study on {G}erman Event Nominalizations}, url = {https://doi.org/10.1007/s11525-021-09382-w}, volume = 31, year = 2021 }
  Link
  https://doi.org/10.1007/s11525-021-09382-w
2019
1. Padó, S. (2019). Entities as a window into distributional semantics. RANLP 2019. https://nlpado.de/~sebastian/pub/papers/RANLP19-slides.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{pado2019entities, address = {Varna, Bulgaria}, author = {Padó, Sebastian}, booktitle = {RANLP 2019}, note = {Slides for invited talk.}, title = {Entities as a window into distributional semantics}, url = {https://nlpado.de/~sebastian/pub/papers/RANLP19-slides.pdf}, year = 2019 }
  Link
  https://nlpado.de/~sebastian/pub/papers/RANLP19-slides.pdf
2. Frassinelli, D., Vigliocco, G., & Padó, S. (2019). Distributional Semantics reveals cross-cultural differences in food concepts. Proceedings of AmLaP.
  - BibTeX
  BibTeX
  @inproceedings{frassinelli19:_distr_seman, address = {Moscow, Russia}, author = {Frassinelli, Diego and Vigliocco, Gabriella and Padó, Sebastian}, booktitle = {Proceedings of {AmLaP}}, title = {Distributional Semantics reveals cross-cultural differences in food concepts}, year = 2019 }
3. Sikos, J., & Padó, S. (2019). Frame Identification as Categorization: Exemplars vs Protoypes in Embeddingland. Proceedings of IWCS, 295--306. https://aclweb.org/anthology/papers/W/W19/W19-0425/
  - BibTeX
  - Link
  BibTeX
  @inproceedings{sikos19:_frame_ident_categ, abstract = {Categorization is a central capability of human cognition, and a number of theories have been developed to account for properties of categorization. Even though many tasks in semantics also involve categorization of some kind, theories of categorization do not play a major role in contemporary research in computational linguistics. This paper follows the idea that embedding-based models of semantics lend themselves well to being formulated in terms of classical categorization theories. The benefit is a space of model families that enables (a) the formulation of hypotheses about the impact of major design decisions, and (b) a transparent assessment of these decisions. We instantiate this idea on the task of frame-semantic frame identification. We define four models that cross two design variables: (a) the choice of prototype vs. exemplar categorization, corresponding to different degrees of generalization applied to the input, and (b) the presence vs. absence of a fine-tuning step, corresponding to generic vs. task-adaptive categorization. We find that for frame identification, generalization and task-adaptive categorization both yield substantial benefits. Our prototype-based, fine-tuned model, which combines the best choices over these variables, establishes a new state-of-the-art in frame identification.}, address = {Gothenburg, Sweden}, author = {Sikos, Jennifer and Padó, Sebastian}, booktitle = {Proceedings of IWCS}, pages = {295--306}, title = {Frame Identification as Categorization: Exemplars vs Protoypes in Embeddingland}, url = {https://aclweb.org/anthology/papers/W/W19/W19-0425/}, year = 2019 }
  Link
  https://aclweb.org/anthology/papers/W/W19/W19-0425/
2018
1. Lapesa, G., Kawaletz, L., Plag, I., Andreou, M., Kisselew, M., & Padó, S. (2018). Disambiguation of newly derived nominalizations in context: A Distributional Semantics approach. Word Structure, 11(3), Article 3. https://www.euppublishing.com/doi/abs/10.3366/word.2018.0131
  - BibTeX
  - Link
  BibTeX
  @article{lapesa17:_disam, author = {Lapesa, Gabriella and Kawaletz, Lea and Plag, Ingo and Andreou, Marios and Kisselew, Max and Padó, Sebastian}, journal = {Word Structure}, number = 3, pages = {315--350}, title = {Disambiguation of newly derived nominalizations in context: {A Distributional Semantics approach}}, url = {https://www.euppublishing.com/doi/abs/10.3366/word.2018.0131}, volume = 11, year = 2018 }
  Link
  https://www.euppublishing.com/doi/abs/10.3366/word.2018.0131
2. Buljan, M., Padó, S., & Snajder, J. (2018). Lexical Substitution for Evaluating Compositional Distributional Models. Proceedings of NAACL, 206–211. http://aclweb.org/anthology/N18-2033.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{buljan18:_lexic_subst_evaluat_compos_distr_model, abstract = {Compositional Distributional Semantic Models (CDSMs) model the meaning of phrases and sentences in vector space. They have been predominantly evaluated on limited, artificial tasks such as semantic sentence similarity on hand-constructed datasets. This paper argues for lexical substitution as a means to evaluate CDSMs. Lexical substitution is a more natural task, enables us to evaluate meaning composition at the level of individual words, and provides a common ground to compare CDSMs with dedicated lexical substitution models. We create a lexical substitution dataset for CDSM evaluation from an English-language corpus with manual “all-words” lexical substitution annotation. Our experiments indicate that the Practical Lexical Function CDSM outperforms simple component-wise CDSMs and performs on par with the context2vec lexical substitution model using the same context.}, address = {New Orleans, LA}, author = {Buljan, Maja and Padó, Sebastian and \v{S}najder, Jan}, booktitle = {Proceedings of NAACL}, pages = {206-211}, title = {Lexical Substitution for Evaluating Compositional Distributional Models}, url = {http://aclweb.org/anthology/N18-2033.pdf}, year = 2018 }
  Link
  http://aclweb.org/anthology/N18-2033.pdf
2017
1. Pross, T., Rossdeutscher, A., Lapesa, G., & Padó, S. (2017). Integrating lexical-conceptual and distributional semantics: a case report. Proceedings of the Amsterdam Colloquium, 75--84. http://semanticsarchive.net/Archive/jZiM2FhZ/AC2017-Proceedings.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{pross17:_integ, abstract = {By means of a case study on German verbs prefixed with the preposition über (‘over’) we compare alternation-based lexical-conceptual and usage-based distributional approaches to verb meaning. Our investigation supports the view that when distributional vectors are rendered human-interpretable by approximation of their representation with its nearest neighbour words in the semantic vector space, they reflect conceptual commonalities be- tween verbs similar to those targeted in lexical-conceptual semantics. Moreover, our case study shows that distributional representations reveal conceptual features of verb meaning that are di cult if not impossible to detect and represent in theoretical frameworks of lexical semantics and thus that a general theory of word meaning requires a combination and complementation of lexical and distributional methods.}, address = {Amsterdam, The Netherlands}, author = {Pross, Tillmann and Rossdeutscher, Antje and Lapesa, Gabriella and Padó, Sebastian}, booktitle = {Proceedings of the Amsterdam Colloquium}, pages = {75--84}, title = {Integrating lexical-conceptual and distributional semantics: a case report}, url = {http://semanticsarchive.net/Archive/jZiM2FhZ/AC2017-Proceedings.pdf}, year = 2017 }
  Link
  http://semanticsarchive.net/Archive/jZiM2FhZ/AC2017-Proceedings.pdf
2. Melymuka, M., Lapesa, G., Kisselew, M., & Padó, S. (2017). Modeling Derivational Morphology in Ukrainian. Proceedings of IWCS. http://aclweb.org/anthology/W/W17/W17-6928.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{melymuka17:_model_deriv_morph_in_ukrain, abstract = {We report on a study applying compositional distributional semantic models (CDSMs) to a set of Ukrainian derivational patterns. Ukrainian is an interesting language as it is morphologically rich, and low-resource. Our study aims at resolving inconsistent results from previous studies which employed CDSMs for derivation; we provide evidence for a cross-lingual advantage of CBOW over NMF representations, as well as a simple additive over a lexical function model. In addition, we present two case studies in which we test the capabilities of CDSMs to deal with pattern-level ambiguity and apply the same CDSMs to inflectional patterns.}, address = {Montpellier, France}, author = {Melymuka, Mariia and Lapesa, Gabriella and Kisselew, Max and Padó, Sebastian}, booktitle = {Proceedings of IWCS}, title = {Modeling Derivational Morphology in {U}krainian}, url = {http://aclweb.org/anthology/W/W17/W17-6928.pdf}, year = 2017 }
  Link
  http://aclweb.org/anthology/W/W17/W17-6928.pdf
3. Lapesa, G., Padó, S., Pross, T., & Rossdeutscher, A. (2017). Are doggies cuter than dogs? Emotional valence and concreteness in German derivational morphology. Proceedings of IWCS. http://aclweb.org/anthology/W/W17/W17-6922.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{lapesa17:_are_doggies_reall_nicer_than_dogs, abstract = {The semantic behavior of derivational processes has been investigated with compositional distribu- tional models relating the meaning of base, affix, and derivative (e.g., anti+capitalist → anticapitalist). While broadly successful, these approaches model how the distributional behavior generally is affected by derivation. Meanwhile, their predictions can not be interpreted at the level of linguistic regularities. In this paper, we adopt an alternative approach and focus on the impact of derivation on finer-grained semantic properties of the base. We focus on (the psycholinguistically prominent) emotional valence, i.e., the speakers’ positive/negative evaluation of the word referent. We present two case studies on German derivational patterns, combining distributional and regression analysis. We are able to establish the broad presence of valence effects in German derivation as well as strong interactions with concreteness.}, address = {Montpellier, France}, author = {Lapesa, Gabriella and Padó, Sebastian and Pross, Tillmann and Rossdeutscher, Antje}, booktitle = {Proceedings of IWCS}, title = {Are doggies cuter than dogs? Emotional valence and concreteness in German derivational morphology}, url = {http://aclweb.org/anthology/W/W17/W17-6922.pdf}, year = 2017 }
  Link
  http://aclweb.org/anthology/W/W17/W17-6922.pdf
4. Medić, Z., Šnajder, J., & Padó, S. (2017). Does Free Word Order Hurt? Assessing the Practical Lexical Function Model for Croatian. Proceedings of STARSEM. http://aclweb.org/anthology/S/S17/S17-1014.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{medic17:_does_free_word_order_hurt, abstract = {The Practical Lexical Function (PLF) model is a model of computational distri- butional semantics that attempts to strike a balance between expressivity and learn- ability in predicting phrase meaning and shows competitive results. We investigate how well the PLF carries over to free word order languages, given that it builds on ob- servations of predicate-argument combina- tions that are harder to recover in free word order languages. We evaluate variants of the PLF for Croatian, using a new lexical substitution dataset. We find that the PLF works about as well for Croatian as for En- glish, but demonstrate that its strength lies in modeling verbs, and that the free word order affects the less robust PLF variant.}, address = {Vancouver, BC}, author = {Medić, Zoran and Šnajder, Jan and Padó, Sebastian}, booktitle = {Proceedings of STARSEM}, title = {Does Free Word Order Hurt? {A}ssessing the Practical Lexical Function Model for {C}roatian}, url = {http://aclweb.org/anthology/S/S17/S17-1014.pdf}, year = 2017 }
  Link
  http://aclweb.org/anthology/S/S17/S17-1014.pdf
5. Boleda, G., Gupta, A., & Padó, S. (2017). Instances and concepts in distributional space. Proceedings of EACL, 79--85. http://www.aclweb.org/anthology/E17-2013.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{boleda17:_instan_concep_distr_space, abstract = {Instances (``Mozart'') are ontologically distinct from concepts or classes (``composer''). Natural language encompasses both, but instances have received comparatively little attention in distributional semantics. Our results show that instances and concepts differ in their distributional properties. We also establish that instantiation detection (``Mozart -- composer'') is generally easier than hypernymy detection (``chemist -- scientist''), and that results on the influence of input representation do not transfer from hyponymy to instantiation.}, address = {Valencia, Spain}, author = {Boleda, Gemma and Gupta, Abhijeet and Pad\'{o}, Sebastian}, booktitle = {Proceedings of EACL}, month = {04}, pages = {79--85}, title = {Instances and concepts in distributional space}, url = {http://www.aclweb.org/anthology/E17-2013.pdf}, year = 2017 }
  Link
  http://www.aclweb.org/anthology/E17-2013.pdf
6. Gupta, A., Boleda, G., & Padó, S. (2017). Distributed Prediction of Relations for Entities: The Easy, The Difficult, and The Impossible. Proceedings of STARSEM. http://aclweb.org/anthology/S/S17/S17-1012.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{pado2017distributed, abstract = {Word embeddings are supposed to provide easy access to semantic relations such as “male of” (man–woman). While this claim has been investigated for concepts, little is known about the distributional behavior of relations of (Named) Entities. We de- scribe two word embedding-based models that predict values for relational attributes of entities, and analyse them. The task is challenging, with major performance dif- ferences between relations. Contrary to many NLP tasks, high difficulty for a re- lation does not result from low frequency, but from (a) one-to-many mappings; and (b) lack of context patterns expressing the relation that are easy to pick up by word embeddings.}, address = {Vancouver, BC}, author = {Gupta, Abhijeet and Boleda, Gemma and Padó, Sebastian}, booktitle = {Proceedings of STARSEM}, title = {Distributed Prediction of Relations for Entities: The Easy, The Difficult, and The Impossible}, url = {http://aclweb.org/anthology/S/S17/S17-1012.pdf}, year = 2017 }
  Link
  http://aclweb.org/anthology/S/S17/S17-1012.pdf
2016
1. Kisselew, M., Rimell, L., Palmer, A., & Padó, S. (2016). Predicting the Direction of Derivation in English conversion. Proceedings of the ACL SIGMORPHON Workshop, 93--98. http://aclweb.org/anthology/W/W16/W16-2015.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{kisselew16:_predic_direc_deriv_englis_conver, abstract = {Conversion is a word formation operation that changes the grammatical category of a word in the absence of overt morphology. Conversion is extremely productive in English (e.g., tunnel, talk). This paper investigates whether distributional information can be used to predict the diachronic direction of conversion for homophonous noun–verb pairs. We aim to predict, for example, that tunnel was used as a noun prior to its use as a verb. We test two hypotheses: (1) that derived forms are less frequent than their bases, and (2) that derived forms are more semantically specific than their bases, as approximated by information theoretic measures. We find that hypothesis (1) holds for N-to-V conversion, while hypothesis (2) holds for V-to-N conversion. We achieve the best overall account of the historical data by taking both frequency and semantic specificity into account. These results provide a new perspective on linguistic theories regarding the semantic specificity of derivational morphemes, and on the morphosyntactic status of conversion.}, address = {Berlin, Germany}, author = {Kisselew, Max and Rimell, Laura and Palmer, Alexis and Padó, Sebastian}, booktitle = {Proceedings of the ACL SIGMORPHON workshop}, pages = {93--98}, title = {Predicting the Direction of Derivation in {E}nglish conversion}, url = {http://aclweb.org/anthology/W/W16/W16-2015.pdf}, year = 2016 }
  Link
  http://aclweb.org/anthology/W/W16/W16-2015.pdf
2. Padó, S., Herbelot, A., Kisselew, M., & Snajder, J. (2016). Predictability of Distributional Semantics in Derivational Word Formation. Proceedings of COLING, 1285--1296. http://www.aclweb.org/anthology/C/C16/C16-1122.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{pado16:_predic_distr_seman_deriv_word_format, abstract = {Compositional distributional semantic models (CDSMs) have successfully been applied to the task of predicting the meaning of a range of linguistic constructions. Their performance on semi-compositional word formation process of (morphological) derivation, however, has been extremely variable, with no large-scale empirical investigation to date. This paper fills that gap, performing an analysis of CDSM predictions on a large dataset (over 30,000 German derivationally related word pairs). We use linear regression models to analyze CDSM performance and obtain insights into the linguistic factors that influence how predictable the distributional context of a derived word is going to be. We identify various such factors, notably part of speech, argument structure, and semantic regularity.}, address = {Osaka, Japan}, author = {Padó, Sebastian and Herbelot, Aurélie and Kisselew, Max and \v{S}najder, Jan}, booktitle = {Proceedings of COLING}, pages = {1285--1296}, title = {Predictability of Distributional Semantics in Derivational Word Formation}, url = {http://www.aclweb.org/anthology/C/C16/C16-1122.pdf}, year = 2016 }
  Link
  http://www.aclweb.org/anthology/C/C16/C16-1122.pdf
3. Padó, S., & Dagan, I. (2016). Textual Entailment. In R. Mitkov (Ed.), Oxford Handbook of Computational Linguistics (2nd ed.). Oxford University Press. http://dx.doi.org/10.1093/oxfordhb/9780199573691.013.024
  - BibTeX
  - Link
  BibTeX
  @incollection{pado10:_textual_entail, abstract = {Textual entailment is a binary relation between two natural-language texts (called ‘text’ and ‘hypothesis’), where readers of the ‘text’ would agree the ‘hypothesis’ is most likely true (Peter is snoring → A man sleeps). Its recognition requires an account of linguistic variability ( an event may be realized in different ways, e.g. Peter buys the car ↔ The car is purchased by Peter) and of relationships between events (e.g. Peter buys the car → Peter owns the car). Unlike logics-based inference, textual entailment also covers cases of probable but still defeasible entailment (A hurricane hit Peter’s town → Peter’s town was damaged). Since human common-sense reasoning often involves such defeasible inferences, textual entailment is of considerable interest for real-world language processing tasks, as a generic, application-independent framework for semantic inference. This chapter discusses the history of textual entailment, approaches to recognizing it, and its integration in various NLP tasks.}, author = {Pad\'o, Sebastian and Dagan, Ido}, booktitle = {Oxford Handbook of Computational Linguistics}, edition = {2nd}, editor = {Mitkov, Ruslav}, publisher = {Oxford University Press}, title = {Textual Entailment}, url = {http://dx.doi.org/10.1093/oxfordhb/9780199573691.013.024}, year = 2016 }
  Link
  http://dx.doi.org/10.1093/oxfordhb/9780199573691.013.024
4. Pross, T., Rossdeutscher, A., Padó, S., Lapesa, G., & Kisselew, M. (2016). “Over reference”: A comparative study on German prefix verbs. ESSLLI SemRefPlus Workshop: Referential Semantics One Step Further: Incorporating Insights from Conceptual and Distributional Approaches to Meaning.
  - BibTeX
  BibTeX
  @inproceedings{pross16:_over, address = {Bolzano, Italy}, author = {Pross, Tillmann and Rossdeutscher, Antje and Padó, Sebastian and Lapesa, Gabriella and Kisselew, Max}, booktitle = {ESSLLI SemRefPlus Workshop: Referential semantics one step further: Incorporating insights from conceptual and distributional approaches to meaning}, title = {'Over reference': A comparative study on {G}erman prefix verbs}, year = 2016 }
5. Varvara, R., Lapesa, G., & Padó, S. (2016). Quantifying regularity in morphological processes: An ongoing study on nominalization in German. ESSLLI DISSALT Workshop: Distributional Semantics and Semantic Theory.
  - BibTeX
  BibTeX
  @inproceedings{varvara16:_quant, address = {Bolzano, Italy}, author = {Varvara, Rossella and Lapesa, Gabriella and Padó, Sebastian}, booktitle = {ESSLLI DISSALT Workshop: Distributional Semantics and Semantic Theory}, title = {Quantifying regularity in morphological processes: An ongoing study on nominalization in {G}erman}, year = 2016 }
6. Lapesa, G., Kisselew, M., Padó, S., Pross, T., & Rossdeutscher, A. (2016). Characterizing the pragmatic component of distributional vectors in terms of polarity: Experiments on German über verbs. ESSLLI DISSALT Workshop: Distributional Semantics and Semantic Theory.
  - BibTeX
  BibTeX
  @inproceedings{lapesa16:_charac, address = {Bolzano, Italy}, author = {Lapesa, Gabriella and Kisselew, Max and Padó, Sebastian and Pross, Tillmann and Rossdeutscher, Antje}, booktitle = {ESSLLI DISSALT Workshop: Distributional Semantics and Semantic Theory}, title = {Characterizing the pragmatic component of distributional vectors in terms of polarity: Experiments on {G}erman \textit{über} verbs}, year = 2016 }
7. Padó, S., Snajder, J., Utt, J., & Zeller, B. (2016). Smoothing Syntax-Based Semantic Spaces: Let The Winner Take It All. Proceedings of KONVENS, 186--191. http://www.linguistics.rub.de/konvens16/pub/23_konvensproc.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{pado16:_smoot_syntax_based_seman_spaces, abstract = {Syntax-based semantic spaces are more flexible and can potentially better model semantic relatedness than bag-of-words spaces. Their application is however limited by sparsity and restricted coverage. We address these problems by smoothing syntax-based with word-based spaces and investigate when to choose which prediction. We obtain the best results by picking the maximal predicted similarity for each word pair, taking advantage of the tendency of unreliable models to underestimate similarity. We show that smoothing can substantially improve coverage while maintaining prediction quality on two German benchmark tasks.}, address = {Bochum, Germany}, author = {Padó, Sebastian and \v{S}najder, Jan and Utt, Jason and Zeller, Britta}, booktitle = {Proceedings of KONVENS}, pages = {186--191}, title = {Smoothing Syntax-Based Semantic Spaces: Let The Winner Take It All}, url = {http://www.linguistics.rub.de/konvens16/pub/23_konvensproc.pdf}, year = 2016 }
  Link
  http://www.linguistics.rub.de/konvens16/pub/23_konvensproc.pdf
8. Köper, M., Schulte im Walde, S., Kisselew, M., & Padó, S. (2016). Improving Zero-Shot-Learning for German Particle Verbs by using Training-Space Restrictions and Local Scaling. Proceedings of STARSEM. http://www.aclweb.org/anthology/S16-2010.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{koeper16:_improv_zero_shot_learn_german, abstract = {Recent models in distributional semantics consider derivational patterns (e.g., use → use+ful) as the result of a compositional process, where base term and affix are combined. We exploit such models for German particle verbs (PVs), and focus on the task of learning a mapping function between base verbs and particle verbs. Our models apply particle-verb motivated training-space restrictions relying on nearest neighbors, as well as recent advances from zero- shot-learning. The models improve the mapping between base terms and derived terms for a new PV derivation dataset, and also across existing derivation datasets for German and English.}, address = {Berlin, Germany}, author = {Köper, Maximilian and {Schulte im Walde}, Sabine and Kisselew, Max and Padó, Sebastian}, booktitle = {Proceedings of STARSEM}, title = {Improving Zero-Shot-Learning for German Particle Verbs by using Training-Space Restrictions and Local Scaling}, url = {http://www.aclweb.org/anthology/S16-2010.pdf}, year = 2016 }
  Link
  http://www.aclweb.org/anthology/S16-2010.pdf
2015
1. Zeller, B. D. (2015). Induction, Semantic Validation and Evaluation of a Derivational Morphology Lexicon for German.
  - BibTeX
  BibTeX
  @phdthesis{zeller2015induction, author = {Zeller, Britta Dorothee}, title = {Induction, Semantic Validation and Evaluation of a Derivational Morphology Lexicon for German}, year = 2015 }
2. Padó, S., Palmer, A., Kisselew, M., & Snajder, J. (2015). Measuring Semantic Content To Assess Asymmetry in Derivation. Proceedings of the IWCS Workshop on Advances in Distributional Semantics. https://www.nlpado.de/~sebastian/pub/papers/iwcs15_pado.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{pado15:_measur_seman_conten_to_asses_asymm_deriv, address = {London, UK}, author = {Pad\'o, Sebastian and Palmer, Alexis and Kisselew, Max and \v{S}najder, Jan}, booktitle = {Proceedings of the IWCS Workshop on Advances in Distributional Semantics}, title = {Measuring Semantic Content To Assess Asymmetry in Derivation}, url = {https://www.nlpado.de/~sebastian/pub/papers/iwcs15_pado.pdf}, year = 2015 }
  Link
  https://www.nlpado.de/~sebastian/pub/papers/iwcs15_pado.pdf
3. Kisselew, M., Padó, S., Palmer, A., & Snajder, J. (2015). Obtaining a Better Understanding of Distributional Models of German Derivational Morphology. Proceedings of IWCS, 58--63. http://www.aclweb.org/anthology/W15-0108.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{kisselew15:_obtain_better_under_distr_model, abstract = {Derivationally related words (read / read+er) usually have closely related meanings. It is an interesting challenge for distributional semantics to account for this relationship by predicting the meaning (represented as a vector) of a derived term (read+er) from the meaning of its base term (read). Previous work has framed this task as an instance of compositional meaning construction, but its properties are not yet well understood. Our goal is to better understand the factors influencing performance on this task via quantitative and qualitative analysis of two existing composition models on a set of German derivation patterns (e.g., -in, durch-). We begin by introducing a rank-based evaluation metric that provides a more relevant assessment of the models’ practical value and reveals the task to be challenging due to specific properties of German (compounding, capitalization). We also find that performance varies greatly between patterns and even among base-derived term pairs of the same pattern. A regression analysis shows that semantic coherence of the base and derived terms within a pattern, as well as coherence of the semantic shifts from base to derived terms, all significantly impact prediction quality. Finally, we investigate false positives, finding that different models capture complementary aspects of the semantic shifts.}, address = {London, UK}, author = {Kisselew, Max and Pad\'o, Sebastian and Palmer, Alexis and \v{S}najder, Jan}, booktitle = {Proceedings of IWCS}, pages = {58--63}, title = {Obtaining a Better Understanding of Distributional Models of German Derivational Morphology}, url = {http://www.aclweb.org/anthology/W15-0108.pdf}, year = 2015 }
  Link
  http://www.aclweb.org/anthology/W15-0108.pdf
4. Feizabadi, P. S., & Padó, S. (2015). Combining Seemingly Incompatible Corpora for Implicit Semantic Role Labeling. Proceedings of STARSEM, 40--50. http://www.aclweb.org/anthology/S/S15/S15-1005.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{feizabadi15:_combin_seemin_incom_corpor_implic, abstract = {Implicit semantic role labeling, the task of retrieving locally unrealized arguments from wider discourse context, is a knowledge-intensive task. At the same time, the annotated corpora that exist are all small and scattered across different annotation frameworks, genres, and classes of predicates. Previous work has treated these corpora as incompatible with one another, and has concentrated on optimizing the exploitation of single corpora. In this paper, we show that corpus combination is effective after all when the differences between corpora are bridged with domain adaptation methods. When we combine the SemEval-2010 Task 10 and Gerber and Chai noun corpora, we obtain substantially improved performance on both corpora, for all roles and parts of speech. We also present new insights into the properties of the implicit semantic role labeling task.}, address = {Denver, CO}, author = {Feizabadi, Parvin Sadat and Pad\'o, Sebastian}, booktitle = {Proceedings of STARSEM}, pages = {40--50}, title = {Combining Seemingly Incompatible Corpora for Implicit Semantic Role Labeling}, url = {http://www.aclweb.org/anthology/S/S15/S15-1005.pdf}, year = 2015 }
  Link
  http://www.aclweb.org/anthology/S/S15/S15-1005.pdf
5. Gupta, A., Utt, J., & Padó, S. (2015). Dissecting the Practical Lexical Function Model for Compositional Distributional Semantics. Proceedings of STARSEM, 153--158. http://www.aclweb.org/anthology/S15-1017.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{gupta15:_dissec_pract_lexic_funct_model, abstract = {The Practical Lexical Function model (PLF) is a recently proposed compositional distributional semantic model which provides an elegant account of composition, striking a balance between expressiveness and robustness and performing at the state-of-the-art. In this paper, we identify an inconsistency in PLF between the objective function at training and the prediction at testing which leads to an over- counting of the predicate’s contribution to the meaning of the phrase. We investigate two possible solutions of which one (the exclusion of simple lexical vector at test time) improves performance significantly on two out of the three composition datasets.}, address = {Denver, CO}, author = {Gupta, Abhijeet and Utt, Jason and Pad\'o, Sebastian}, booktitle = {Proceedings of STARSEM}, pages = {153--158}, title = {Dissecting the Practical Lexical Function Model for Compositional Distributional Semantics}, url = {http://www.aclweb.org/anthology/S15-1017.pdf}, year = 2015 }
  Link
  http://www.aclweb.org/anthology/S15-1017.pdf
6. Zarcone, A., Padó, S., & Lenci, A. (2015). Same Same but Different: Type and Typicality in a Distributional Model of Complement Coercion. Proceedings of NetWords, 91--94. http://ceur-ws.org/Vol-1347/paper19.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{zarcone15:_same_same_differ, abstract = {We aim to model the results from a self-paced reading experiment, which tested the effect of semantic type clash and typicality on the processing of German complement coercion. We present two distributional semantic models to test if they can model the effect of both type and typicality in the psycholinguistic study. We show that one of the models, without explicitly representing type information, can account both for the effect of type and typicality in complement coercion.}, address = {Pisa, Italy}, author = {Zarcone, Alessandra and Pad\'o, Sebastian and Lenci, Alessandro}, booktitle = {Proceedings of NetWords}, pages = {91--94}, title = {Same Same but Different: Type and Typicality in a Distributional Model of Complement Coercion}, url = {http://ceur-ws.org/Vol-1347/paper19.pdf}, year = 2015 }
  Link
  http://ceur-ws.org/Vol-1347/paper19.pdf
2014
1. Feizabadi, P. S., & Padó, S. (2014). Crowdsourcing Annotation of Non-Local Semantic Roles. Proceedings of EACL, 226–230. http://aclweb.org/anthology/E/E14/E14-4044.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{feizabadi14, abstract = {This paper reports on a study of crowdsourcing the annotation of non-local (or implicit) frame-semantic roles, i.e., roles that are realized in the previous discourse context. We describe two annotation setups (marking and gap filling) and find that gap filling works considerably better, attaining an acceptable quality relatively cheaply. The produced data is available for research purposes.}, address = {Gothenburg, Sweden}, author = {Feizabadi, Parvin Sadat and Padó, Sebastian}, booktitle = {Proceedings of EACL}, ee = {http://aclweb.org/anthology/E/E14/E14-4044.pdf}, pages = {226-230}, title = {Crowdsourcing Annotation of Non-Local Semantic Roles.}, url = {http://aclweb.org/anthology/E/E14/E14-4044.pdf}, year = 2014 }
  Link
  http://aclweb.org/anthology/E/E14/E14-4044.pdf
2. Zeller, B., Padó, S., & Snajder, J. (2014). Towards Semantic Validation of a Derivational Lexicon. Proceedings of COLING, 1728--1739. http://www.aclweb.org/anthology/C14-1163.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{zeller14:_towar_seman_valid_deriv_lexic, abstract = {Derivationally related lemmas like (friend – friendly – friendship) are derived from a common stem. Frequently, their meanings are also systematically related. However, there are also many examples of derivationally related lemma pairs whose meanings differ substantially, e.g., (object – objective). Most broad-coverage derivational lexicons do not reflect this distinction, mixing up semantically related and unrelated word pairs. In this paper, we investigate strategies to recover the above distinction by recognizing semantically related lemma pairs, a process we call semantic validation. We make two main contributions: First, we perform a detailed data analysis on the basis of a large German derivational lexicon. It reveals two promising sources of information (distributional semantics and structural information about derivational rules), but also systematic problems with these sources. Second, we develop a classification model for the task that reflects the noisy nature of the data. It achieves an improvement of 13.6\% in precision and 5.8\% in F1-score over a strong majority class baseline. Our experiments confirm that both information sources contribute to semantic validation, and that they are complementary enough that the best results are obtained from a combined model.}, address = {Dublin, Ireland}, author = {Zeller, Britta and Pad\'o, Sebastian and \v{S}najder, Jan}, booktitle = {Proceedings of COLING}, pages = {1728--1739}, title = {Towards Semantic Validation of a Derivational Lexicon}, url = {http://www.aclweb.org/anthology/C14-1163.pdf}, year = 2014 }
  Link
  http://www.aclweb.org/anthology/C14-1163.pdf
3. Magnini, B., Dagan, I., Neumann, G., & Padó, S. (2014). Entailment Graphs for Text Analytics in the Excitement Project. Proceedings of Text, Speech and Dialogue, 11--18. https://doi.org/10.1007/978-3-319-10816-2_2
  - BibTeX
  - Link
  BibTeX
  @inproceedings{tsd2014, abstract = {In the last years, a relevant research line in Natural Language Processing has focused on detecting semantic relations among portions of text, including entailment, similarity, temporal relations, and, with a less degree, causality. The attention on such semantic relations has raised the demand to move towards more informative meaning representations, which express properties of concepts and relations among them. This demand triggered research on "statement entailment graphs", where nodes are natural language statements (propositions), comprising of predicates with their arguments and modifiers, while edges represent entailment relations between nodes. We report initial research that defines the properties of entailment graphs and their potential applications. Particularly, we show how entailment graphs are profitably used in the context of the European project EXCITEMENT, where they are applied for the analysis of customer interactions across multiple channels, including speech, email, chat and social media, and multiple languages (English, German, Italian).}, address = {Brno, Czech Republic}, author = {Magnini, Bernardo and Dagan, Ido and Neumann, G\"unter and Pad\'o, Sebastian}, booktitle = {Proceedings of Text, Speech and Dialogue}, doi = {10.1007/978-3-319-10816-2_2}, pages = {11--18}, title = {Entailment Graphs for Text Analytics in the {Excitement} Project}, url = {http://dx.doi.org/10.1007/978-3-319-10816-2\_2}, year = 2014 }
  Link
  http://dx.doi.org/10.1007/978-3-319-10816-2\_2
2013
1. Padó, S., Snajder, J., & Zeller, B. D. (2013). Derivational Smoothing for Syntactic Distributional Semantics. Proceedings of ACL, 731--735. http://www.aclweb.org/anthology/P13-2128.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{pado:2013, abstract = {Syntax-based vector spaces are used widely in lexical semantics and are more versatile than word-based spaces (Baroni and Lenci, 2010). However, they are also sparse, with resulting reliability and coverage problems. We address this problem by derivational smoothing, which uses knowledge about derivationally related words (oldish -- old) to improve semantic similarity estimates. We develop a set of derivational smoothing methods and evaluate them on two lexical semantics tasks in German. Even for models built from very large corpora, simple derivational smoothing can improve coverage considerably.}, address = {Sofia, Bulgaria}, author = {Padó, Sebastian and \v{S}najder, Jan and Zeller, Britta D.}, booktitle = {Proceedings of ACL}, pages = {731--735}, title = {Derivational Smoothing for Syntactic Distributional Semantics}, url = {http://www.aclweb.org/anthology/P13-2128.pdf}, year = 2013 }
  Link
  http://www.aclweb.org/anthology/P13-2128.pdf
2. Zarcone, A., Lenci, A., Padó, S., & Utt, J. (2013). Fitting, not clashing! A distributional semantic model of logical metonymy. Proceedings of IWCS, 404--410. http://www.aclweb.org/anthology/W13-0216.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{zarcone13:_fittin, abstract = {Logical metonymy interpretation (e.g. begin the book → writing) has received wide attention in linguistics. Experimental results have shown higher processing costs for metonymic conditions compared with non-metonymic ones (read the book). According to a widely held interpretation, it is the type clash between the event-selecting verb and the entity-denoting object (begin the book) that triggers coercion mechanisms and leads to additional processing effort. We propose an alternative explanation and argue that the extra processing effort is an effect of thematic fit. This is a more economical hypothesis that does not need to postulate a separate type clash mechanism: entity- denoting objects simply have a low fit as objects of event-selecting verbs. We test linguistic datasets from psycholinguistic experiments and find that a structured distributional model of thematic fit, which does not encode any explicit argument type information, is able to replicate all significant experimental findings. This result provides evidence for a graded account of coercion phenomena in which thematic fit accounts for both the trigger of the coercion and the retrieval of the covert event.}, address = {Potsdam, Germany}, author = {Zarcone, Alessandra and Lenci, Alessandro and Pad{\'o}, Sebastian and Utt, Jason}, booktitle = {Proceedings of IWCS}, pages = {404--410}, title = {Fitting, not clashing! {A} distributional semantic model of logical metonymy}, url = {http://www.aclweb.org/anthology/W13-0216.pdf}, year = 2013 }
  Link
  http://www.aclweb.org/anthology/W13-0216.pdf
3. Utt, J., Lenci, A., Pado, S., & Zarcone, A. (2013). The Curious Case of Metonymic Verbs: A Distributional Characterization. Proceedings of the IWCS Workshop “‘Towards A Formal Distributional Semantics.’” http://www.aclweb.org/anthology/W/W13/W13-0604.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{utt13:_curious_case_meton_verbs, abstract = {Logical metonymy combines an event-selecting verb with an entity-denoting noun (e.g., The writer began the novel), triggering a covert event interpretation (e.g., reading, writing). Experimental investigations of logical metonymy must assume a binary distinction between metonymic (i.e. event- selecting) verbs and non-metonymic verbs to establish a control condition. However, this binary distinction (whether a verb is metonymic or not) is mostly made on intuitive grounds, which introduces a potential confounding factor. We describe a corpus-based approach which characterizes verbs in terms of their behavior at the syntax-semantics interface. The model assesses the extent to which transitive verbs prefer event-denoting objects over entity-denoting objects. We then test this “eventhood” measure on psycholinguistic datasets, showing that it can distinguish not only metonymic from non-metonymic verbs, but that it can also capture more fine-grained distinctions among different classes of metonymic verbs, putting such distinctions into a new graded perspective.}, address = {Potsdam, Germany}, author = {Utt, Jason and Lenci, Alessandro and Pado, Sebastian and Zarcone, Alessandra}, booktitle = {Proceedings of the IWCS workshop ''Towards A Formal Distributional Semantics''}, title = {The Curious Case of Metonymic Verbs: A Distributional Characterization}, url = {http://www.aclweb.org/anthology/W/W13/W13-0604.pdf}, year = 2013 }
  Link
  http://www.aclweb.org/anthology/W/W13/W13-0604.pdf
4. Snajder, J., Padó, S., & Zeljko Agić. (2013). Building and Evaluating a Distributional Memory for Croatian. Proceedings of ACL, 784--789. http://www.aclweb.org/anthology/P13-2137.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{snajder:2013, abstract = {We report on the first structured distributional semantic model for Croatian, DM.HR. It is constructed after the model of the English Distributional Memory (Baroni and Lenci, 2010), from a dependency-parsed Croatian web corpus, and covers about 2M lemmas. We give details on the linguistic processing and the design principles. An evaluation shows state-of-the- art performance on a semantic similarity task with particularly good performance on nouns. The resource is freely available.}, address = {Sofia, Bulgaria}, author = {\v{S}najder, Jan and Padó, Sebastian and {\v Z}eljko Agi{\'c}}, booktitle = {Proceedings of ACL}, pages = {784--789}, title = {Building and Evaluating a Distributional Memory for {C}roatian}, url = {http://www.aclweb.org/anthology/P13-2137.pdf}, year = 2013 }
  Link
  http://www.aclweb.org/anthology/P13-2137.pdf
2012
1. Zarcone, A., Utt, J., & Pado, S. (2012). Modeling covert event retrieval in logical metonymy: probabilistic and distributional accounts. Proceedings of the NAACL Workshop on Cognitive Modeling in Computational Linguistics, 70--79. http://aclweb.org/anthology/W/W12/W12-1707.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{zarcone12:_model, abstract = {Logical metonymies (The student finished the beer) represent a challenge to compositionality since they involve semantic content not overtly realized in the sentence (covert events -> drinking the beer). We present a contrastive study of two classes of computational models for logical metonymy in German, namely a probabilistic model and a distributional, similarity-based model. We build both models from the SDEWAC corpus and evaluate them against a dataset from a self-paced reading and a probe recognition study for their sensitivity to thematic fit effects via their accuracy in predicting the correct covert event in a metonymical context. The similarity-based models allow for better coverage while maintaining the accuracy of the probabilistic models.}, address = {Montreal, QC}, author = {Zarcone, Alessandra and Utt, Jason and Pado, Sebastain}, booktitle = {Proceedings of the NAACL Workshop on Cognitive Modeling in Computational Linguistics}, pages = {70--79}, title = {Modeling covert event retrieval in logical metonymy: probabilistic and distributional accounts}, url = {http://aclweb.org/anthology/W/W12/W12-1707.pdf}, year = 2012 }
  Link
  http://aclweb.org/anthology/W/W12/W12-1707.pdf
2. Padó, S., & Utt, J. (2012). A Distributional Memory for German. Proceedings of the KONVENS Workshop on Recent Developments and Applications of Lexical-Semantic Resources. http://www.oegai.at/konvens2012/proceedings/67_pado12w/67_pado12w.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{utt12:_distr_memor_german, abstract = {This paper describes the creation of a Distri- butional Memory (Baroni and Lenci 2010) resource for German. Distributional Mem- ory is a generalized distributional resource for lexical semantics that does not have to commit to a particular vector space at the time of creation. We induce a resource from a German corpus, following the original de- sign decisions as closely as possible, and discuss the steps necessary for a new lan- guage. We evaluate the German DM model on a synonym selection task, finding that it can compete with existing models.}, address = {Vienna, Austria}, author = {Padó, Sebastian and Utt, Jason}, booktitle = {Proceedings of the KONVENS workshop on recent developments and applications of lexical-semantic resources}, title = {A Distributional Memory for {G}erman}, url = {http://www.oegai.at/konvens2012/proceedings/67_pado12w/67_pado12w.pdf}, year = 2012 }
  Link
  http://www.oegai.at/konvens2012/proceedings/67_pado12w/67_pado12w.pdf
3. Boleda, G., Padó, S., & Utt, J. (2012). Regular polysemy: A distributional model. Proceedings of *SEM, 151--160. http://www.aclweb.org/anthology/S12-1023.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{boleda12:regular, abstract = {Many types of polysemy are not word specific, but are instances of general sense alternations such as Animal-Food. Despite their pervasiveness, regular alternations have been mostly ignored in empirical computational semantics. This paper presents (a) a general framework which grounds sense alternations in corpus data, generalizes them above individual words, and allows the prediction of alternations for new words; and (b) a concrete unsupervised implementation of the framework, the Centroid Attribute Model. We evaluate this model against a set of 2,400 ambiguous words and demonstrate that it outperforms two baselines.}, address = {Montr\'{e}al, Canada}, author = {Boleda, Gemma and Pad{\'o}, Sebastian and Utt, Jason}, booktitle = {Proceedings of {*}SEM}, pages = {151--160}, title = {Regular polysemy: A distributional model}, url = {http://www.aclweb.org/anthology/S12-1023.pdf}, year = 2012 }
  Link
  http://www.aclweb.org/anthology/S12-1023.pdf
4. Frank, A., & Padó, S. (2012). Semantics in Computational Lexicons. In C. Maienborn, K. von Heusinger, & P. Portner (Eds.), Semantics: An International Handbook of Natural Language Meaning (Vol. 3, pp. 2887--2917). De Gruyter. http://dx.doi.org/10.1515/9783110253382.2887
  - BibTeX
  - Link
  BibTeX
  @incollection{frank09:_seman_comput_lexic, abstract = {This chapter gives an overview of work on the representation of semantic information in lexicon resources for computational natural language processing (NLP). It starts with a broad overview of the history and state of the art of different types of semantic lexicons in Computational Linguistics, and discusses their main use cases. Section 2 is devoted to questions of how to construct semantic lexicons for Computational Linguistics. We discuss diverse modelling principles for semantic lexicons and methods for their construction, ranging from largely manual resource creation to automated methods for learning lexicons from text, semi-structured or unstructured. Section 3 addresses issues related to the cross-lingual and multi-lingual creation of broad-coverage semantic lexicon resources. Section 4 discusses interoperability, i.e., the combination of lexical (and other) resources describing different meaning aspects. Section 5 concludes with an outlook on future research directions.}, author = {Frank, Anette and Pad\'o, Sebastian}, booktitle = {Semantics: An International Handbook of Natural Language Meaning}, editor = {Maienborn, Claudia and von Heusinger, Klaus and Portner, Paul}, pages = {2887--2917}, publisher = {De Gruyter}, title = {Semantics in Computational Lexicons}, url = {http://dx.doi.org/10.1515/9783110253382.2887}, volume = 3, year = 2012 }
  Link
  http://dx.doi.org/10.1515/9783110253382.2887
5. Augenstein, I., Padó, S., & Rudolph, S. (2012). LODifier: Generating Linked Data from Unstructured Text. Proceedings of ESWC, 210--224. http://dx.doi.org/10.1007/978-3-642-30284-8\_21
  - BibTeX
  - Link
  BibTeX
  @inproceedings{augenstein12:_lodif, abstract = {The automated extraction of information from text and its transformation into a formal description is an important goal in both Semantic Web research and computational linguistics. The extracted information can be used for a variety of tasks such as ontology generation, question answering and information retrieval. LODifier is an approach that combines deep semantic analysis with named entity recognition, word sense disambiguation and controlled Semantic Web vocabularies in order to extract named entities and relations between them from text and to convert them into an RDF representation which is linked to DBpedia and WordNet. We present the architecture of our tool and discuss design decisions made. An evaluation of the tool on a story link detection task gives clear evidence of its practical potential.}, address = {Heraklion, Greece}, author = {Augenstein, Isabelle and Pad{\'o}, Sebastian and Rudolph, Sebastian}, booktitle = {Proceedings of ESWC}, pages = {210--224}, title = {{LODifier}: Generating Linked Data from Unstructured Text}, url = {http://dx.doi.org/10.1007/978-3-642-30284-8\_21}, year = 2012 }
  Link
  http://dx.doi.org/10.1007/978-3-642-30284-8\_21
2011
1. Kim, S., Kozareva, Z., Nakov, P., Séaghdha, D. Ó., Padó, S., & Szpakowicz, S. (Eds.). (2011). Proceedings of the ACL Workshop on Relational Models of Semantics.
  - BibTeX
  BibTeX
  @proceedings{kim11:_proceed_of_acl_works_relat, address = {Portland, OR}, editor = {Kim, S. and Kozareva, Z. and Nakov, P. and S\'eaghdha, D. \'O and Pad\'o, S. and Szpakowicz, S.}, title = {Proceedings of the ACL Workshop on Relational Models of Semantics}, year = 2011 }
2. Peirsman, Y., & Padó, S. (2011). Semantic relations in bilingual vector spaces. ACM Transactions in Speech and Language Processing, 8(2), Article 2. http://dx.doi.org/10.1145/2050100.2050102
  - BibTeX
  - Link
  BibTeX
  @article{peirsman:_seman_relat_in_bilin_vector_spaces, author = {Peirsman, Yves and Pad\'o, Sebastian}, journal = {ACM Transactions in Speech and Language Processing}, note = {Preprint at https://nlpado.de/~sebastian/pub/papers/tslp11_peirsman.pdf}, number = 2, pages = {3:1--3:21}, title = {Semantic relations in bilingual vector spaces}, url = {http://dx.doi.org/10.1145/2050100.2050102}, volume = 8, year = 2011 }
  Link
  http://dx.doi.org/10.1145/2050100.2050102
3. Padó, S., & Peirsman, Y. (Eds.). (2011). Proceedings of the EMNLP Workshop on Geometrical Models of Natural Language Semantics.
  - BibTeX
  BibTeX
  @proceedings{pado11:_proceed_of_emnlp_works_geomet, address = {Edinburgh, UK}, editor = {Pad\'o, S. and Peirsman, Y.}, title = {Proceedings of the EMNLP Workshop on Geometrical Models of Natural Language Semantics}, year = 2011 }
2010
1. Hendrickx, I., Kim, S. N., Kozareva, Z., Nakov, P., Séaghdha, D. Ó., Padó, S., Pennacchiotti, M., Romano, L., & Szpakowicz, S. (2010). Multi-Way Classification of Semantic Relations Between Pairs of Nominals. Proceedings of the 5th SIGLEX Workshop on Semantic Evaluation, 33--38. http://www.aclweb.org/anthology/S10-1006.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{hendrickx10:_multi_way_class_of_seman, abstract = {We describe the SemEval-2 task 8 (multi-way classification of semantic relations between pairs of nominals). The task was designed to compare different approaches to the problem and to provide a standard testbed for future research. This paper defines the task, describes the training and test data and the process of their creation, lists the participating systems (10 teams, 28 runs), and discusses their results.}, address = {Uppsala, Sweden}, author = {Hendrickx, Iris and Kim, Su Nam and Kozareva, Zornitsa and Nakov, Preslav and Séaghdha, Diarmuid Ó and Padó, Sebastian and Pennacchiotti, Marco and Romano, Lorenza and Szpakowicz, Stan}, booktitle = {Proceedings of the 5th SIGLEX Workshop on Semantic Evaluation}, pages = {33--38}, title = {Multi-Way Classification of Semantic Relations Between Pairs of Nominals}, url = {http://www.aclweb.org/anthology/S10-1006.pdf}, year = 2010 }
  Link
  http://www.aclweb.org/anthology/S10-1006.pdf
2. Faruqui, M., & Padó, S. (2010). Training and Evaluating a German Named Entity Recognizer with Semantic Generalization. Proceedings of KONVENS 2010. http://www.nlpado.de/~sebastian/pub/papers/konvens10_faruqui.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{faruqui10:_training, abstract = {We present a freely available optimized Named Entity Recognizer (NER) for German. It alleviates the small size of available NER training corpora for German with distributional generalization features trained on large unlabelled corpora. We vary the size and source of the generalization corpus and find improvements of 6\% F1-score (in-domain) and 9\% (out-of-domain) over simple supervised training.}, address = {Saarbr\"ucken, Germany}, author = {Faruqui, Manaal and Pad{\'o}, Sebastian}, booktitle = {Proceedings of KONVENS 2010}, title = {Training and Evaluating a {G}erman Named Entity Recognizer with Semantic Generalization}, url = {http://www.nlpado.de/~sebastian/pub/papers/konvens10_faruqui.pdf}, year = 2010 }
  Link
  http://www.nlpado.de/~sebastian/pub/papers/konvens10_faruqui.pdf
2009
1. Padó, S., Galley, M., Manning, C. D., & Jurafsky, D. (2009). Robust Machine Translation Evaluation with Entailment Features. Proceedings of ACL 2009, 297--305. http://www.aclweb.org/anthology/P/P09/P09-1034.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{pado09:_robus_machin_trans_evaluat_with_entail_featur, abstract = {Existing evaluation metrics for machine translation lack crucial robustness: their correlations with human quality judgments vary considerably across languages and genres. We believe that the main reason is their inability to properly capture meaning: A good translation candidate means the same thing as the reference translation, regardless of formulation. We propose a metric that evaluates MT output based on a rich set of features motivated by textual entailment, such as lexical-semantic (in-)compatibility and argument structure overlap. We compare this metric against a combination metric of four state-of-the-art scores (BLEU, NIST, TER, and METEOR) in two different settings. The combination metric outperforms the individual scores, but is bested by the entailment-based metric. Combining the entailment and traditional features yields further improvements.}, address = {Singapore}, author = {Pad{\'o}, Sebastian and Galley, Michel and Manning, Christopher D. and Jurafsky, Daniel}, booktitle = {Proceedings of ACL 2009}, pages = {297--305}, title = {Robust Machine Translation Evaluation with Entailment Features}, url = {http://www.aclweb.org/anthology/P/P09/P09-1034.pdf}, year = 2009 }
  Link
  http://www.aclweb.org/anthology/P/P09/P09-1034.pdf
2. Padó, S., & Lapata, M. (2009). Cross-lingual Annotation Projection of Role-semantic Information. Artificial Intelligence Research, 36, 307--340. http://dx.doi.org/10.1613/jair.2863
  - BibTeX
  - Link
  BibTeX
  @article{pado:_cross_projec_role_infor, author = {Padó, Sebastian and Lapata, Mirella}, journal = {Artificial Intelligence Research}, pages = {307--340}, title = {Cross-lingual Annotation Projection of Role-semantic Information}, url = {http://dx.doi.org/10.1613/jair.2863}, volume = 36, year = 2009 }
  Link
  http://dx.doi.org/10.1613/jair.2863
3. Padó, S., Galley, M., Manning, C. D., & Jurafsky, D. (2009). Textual Entailment Features for Machine Translation Evaluation. Proceedings of the EACL Workshop on Machine Translation, 37--41. http://www.aclweb.org/anthology/W09-0404.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{pado09:_textual_entail_featur_for_machin_trans_evaluat, abstract = {We present two regression models for the prediction of pairwise preference judgments among MT hypotheses. Both models are based on feature sets that are motivated by textual entailment and incorporate lexical similarity as well as local syntactic features and specific semantic phenomena. One model predicts absolute scores; the other one direct pairwise judgments. We find that both models are competitive with regression models built over the scores of established MT evaluation metrics. Further data analysis clarifies the complementary behavior of the two feature sets.}, address = {Athens, Greece}, author = {Pad\'o, Sebastian and Galley, Michel and Manning, Christopher D. and Jurafsky, Daniel}, booktitle = {Proceedings of the EACL Workshop on Machine Translation}, pages = {37--41}, title = {Textual Entailment Features for Machine Translation Evaluation}, url = {http://www.aclweb.org/anthology/W09-0404.pdf}, year = 2009 }
  Link
  http://www.aclweb.org/anthology/W09-0404.pdf
4. Erk, K., & Padó, S. (2009). Paraphrase assessment in structured vector space: Exploring parameters and datasets. Proceedings of the EACL Workshop on Geometrical Methods for Natural Language Semantics, 57--65. http://www.aclweb.org/anthology/W09-0208.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{erk09:_parap_asses_in_struc_vector_space, abstract = {The appropriateness of paraphrases for words depends often on context: ``grab'' can replace ``catch'' in ``catch a ball'', but not in ``catch a cold''. Structured Vector Space (SVS) is a model that computes word meaning in context in order to assess the appropriateness of such paraphrases. This paper investigates ``best-practice'' parameter settings for SVS, and it presents a method to obtain large datasets for paraphrase assessment from corpora with WSD annotation.}, address = {Athens, Greece}, author = {Erk, Katrin and Pad\'o, Sebastian}, booktitle = {Proceedings of the EACL Workshop on Geometrical Methods for Natural Language Semantics}, pages = {57--65}, title = {Paraphrase assessment in structured vector space: Exploring parameters and datasets}, url = {http://www.aclweb.org/anthology/W09-0208.pdf}, year = 2009 }
  Link
  http://www.aclweb.org/anthology/W09-0208.pdf
5. Padó, S., Cer, D., Galley, M., Manning, C. D., & Jurafsky, D. (2009). Measuring Machine Translation Quality as Semantic Equivalence: A Metric based on Entailment Features. Machine Translation, 23(2--3), Article 2--3. http://dx.doi.org/10.1007/s10590-009-9060-y
  - BibTeX
  - Link
  BibTeX
  @article{pado:_seman_mt_based_entail_featur, author = {Pad\'o, Sebastian and Cer, Daniel and Galley, Michel and Manning, Christopher D. and Jurafsky, Daniel}, journal = {Machine Translation}, note = {Preprint at https://nlpado.de/~sebastian/pub/papers/mt09_pado.pdf}, number = {2--3}, pages = {181--193}, title = {Measuring Machine Translation Quality as Semantic Equivalence: A Metric based on Entailment Features}, url = {http://dx.doi.org/10.1007/s10590-009-9060-y}, volume = 23, year = 2009 }
  Link
  http://dx.doi.org/10.1007/s10590-009-9060-y
6. Burchardt, A., Erk, K., Frank, A., Kowalski, A., Padó, S., & Pinkal, M. (2009). Using FrameNet for the Semantic Analysis of German: Annotation, Representation, and Automation. In H. C. Boas (Ed.), Multilingual FrameNets in Computational Lexicography -- Methods and Applications (pp. 209–244). De Gruyter. http://dx.doi.org/10.1515/9783110212976.3.209
  - BibTeX
  - Link
  BibTeX
  @incollection{Burchardtetal:forth, author = {Burchardt, Aljoscha and Erk, Katrin and Frank, Anette and Kowalski, Andrea and Pad\'o, Sebastian and Pinkal, Manfred}, booktitle = {Multilingual FrameNets in Computational Lexicography -- Methods and Applications}, editor = {Boas, Hans C.}, pages = {209-244}, publisher = {De Gruyter}, title = {Using {FrameNet} for the Semantic Analysis of {G}erman: Annotation, Representation, and Automation}, url = {http://dx.doi.org/10.1515/9783110212976.3.209}, year = 2009 }
  Link
  http://dx.doi.org/10.1515/9783110212976.3.209
7. Hendrickx, I., Kim, S. N., Kozareva, Z., Nakov, P., Séaghdha, D. Ó., Padó, S., Pennacchiotti, M., Romano, L., & Szpakowicz, S. (2009). SemEval-2010 Task 8: Multi-Way Classification of Semantic Relations Between Pairs of Nominals. Proceedings of the NAACL Workshop on Semantic Evaluations: Recent Achievements and Future Directions, 94--99. http://www.aclweb.org/anthology/W09-2415.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{iris09:_semev_task, abstract = {We present a brief overview of the main challenges in the extraction of semantic relations from English text, and discuss the shortcomings of previous data sets and shared tasks. This leads us to introduce a new task, which will be part of SemEval-2010: multi-way classification of mutually exclusive semantic relations between pairs of common nominals. The task is designed to compare different approaches to the problem and to provide a standard testbed for future research, which can benefit many applications in Natural Language Processing.}, address = {Boulder, CO}, author = {Hendrickx, Iris and Kim, Su Nam and Kozareva, Zornitsa and Nakov, Preslav and Séaghdha, Diarmuid Ó and Padó, Sebastian and Pennacchiotti, Marco and Romano, Lorenza and Szpakowicz, Stan}, booktitle = {Proceedings of the NAACL Workshop on Semantic Evaluations: Recent Achievements and Future Directions}, pages = {94--99}, title = {SemEval-2010 Task 8: Multi-Way Classification of Semantic Relations Between Pairs of Nominals}, url = {http://www.aclweb.org/anthology/W09-2415.pdf}, year = 2009 }
  Link
  http://www.aclweb.org/anthology/W09-2415.pdf
8. Hajic, J., Ciaramita, M., Johansson, R., Kawahara, D., Martì, M. A., Màrquez, L., Meyers, A., Nivre, J., Padó, S., Stepánek, J., Stranák, P., Surdeanu, M., Xue, N., & Zhang, Y. (2009). The CoNLL-2009 Shared Task: Syntactic and Semantic Dependencies in Multiple Languages. Proceedings of CoNLL-2009, 1--18. http://www.aclweb.org/anthology/W/W09/W09-1201.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{hajic09:_conll_shared_task, abstract = {For the 11th straight year, the Conference on Computational Natural Language Learning has been accompanied by a shared task whose purpose is to promote natural language processing applications and evaluate them in a standard setting. In 2009, the shared task was dedicated to the joint parsing of syntactic and semantic dependencies in multiple languages. This shared task combines the shared tasks of the previous five years under a unique dependency-based formalism similar to the 2008 task. In this paper, we define the shared task, describe how the data sets were created and show their quantitative properties, report the results and summarize the approaches of the participating systems.}, address = {Boulder, CO}, author = {Haji\v{c}, Jan and Ciaramita, Massimiliano and Johansson, Richard and Kawahara, Daisuke and Mart\`i, Maria A. and M\`arquez, Llu\'is and Meyers, Adam and Nivre, Joakim and Pad\'o, Sebastian and \v{S}tep\'anek, Jan and Stra\v{n}\'ak, Pavel and Surdeanu, Mihai and Xue, Niawen and Zhang, Yi}, booktitle = {Proceedings of CoNLL-2009}, pages = {1--18}, title = {The {CoNLL-2009} Shared Task: Syntactic and Semantic Dependencies in Multiple Languages}, url = {http://www.aclweb.org/anthology/W/W09/W09-1201.pdf}, year = 2009 }
  Link
  http://www.aclweb.org/anthology/W/W09/W09-1201.pdf
2008
1. Padó, S., Pennacchiotti, M., & Sporleder, C. (2008). Semantic role assignment for event nominalisations by leveraging verbal data. Proceedings of COLING 2008, 665--672. http://www.aclweb.org/anthology/C/C08/C08-1084.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{pado08:_nom, abstract = {This paper presents a novel approach to the task of semantic role labelling for event nominalisations, which make up a considerable fraction of predicates in running text, but are underrepresented in terms of training data and difficult to model. We propose to address this situation by data expansion. We construct a model for nominal role labelling solely from verbal training data. The best quality results from salvaging grammatical features where applicable, and generalising over lexical heads otherwise.}, address = {Manchester, UK}, author = {Pad{\'o}, Sebastian and Pennacchiotti, Marco and Sporleder, Caroline}, booktitle = {Proceedings of COLING 2008}, pages = {665--672}, title = {Semantic role assignment for event nominalisations by leveraging verbal data}, url = {http://www.aclweb.org/anthology/C/C08/C08-1084.pdf}, year = 2008 }
  Link
  http://www.aclweb.org/anthology/C/C08/C08-1084.pdf
2. Culo, O., Erk, K., Padó, S., & im Walde, S. S. (2008). Comparing and Combining Semantic Verb Classifications. Language Resources and Evaluation, 42(3), Article 3. http://dx.doi.org/10.1007/s10579-008-9070-z
  - BibTeX
  - Link
  BibTeX
  @article{culo:_compar_combin_seman_verb_class, author = {\v{C}ulo, Oliver and Erk, Katrin and Padó, Sebastian and im Walde, Sabine Schulte}, journal = {Language Resources and Evaluation}, note = {Preprint at https://nlpado.de/~sebastian/pub/papers/lre08_culo.pdf}, number = 3, pages = {161--199}, title = {Comparing and Combining Semantic Verb Classifications}, url = {http://dx.doi.org/10.1007/s10579-008-9070-z}, volume = 42, year = 2008 }
  Link
  http://dx.doi.org/10.1007/s10579-008-9070-z
2007
1. Padó, S. (2007). Cross-lingual Parallelism and Translational Equivalence: The Case of FrameNet Frames. Proceedings of the NODALIDA Workshop on Building Frame Semantics Resources for Scandinavian and Baltic Languages. https://www.nlpado.de/~sebastian/pub/papers/nodalida07_pado.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{pado07:_cross_paral_trans_equiv, abstract = {Annotation projection is a strategy for the cross-lingual transfer of annotations which can be used to bootstrap linguistic resources for low-density languages, such as role-semantic databases similar to FrameNet. In this paper, we investigate the main assumption underlying annotation projection, cross-lingual parallelism, which states that annotation is parallel across languages. Concentrating on the level of frames, we provide a qualitative and quantitative characterisation of the relationship between translation and cross-lingual parallelism on the basis of a trilingual English–French– German corpus. We link frame (non)-parallelism to different kinds of translational shifts and show that a simple heuristic can detect the majority of such shifts.}, address = {Tartu, Estonia}, author = {Padó, Sebastian}, booktitle = {Proceedings of the NODALIDA Workshop on Building Frame Semantics Resources for Scandinavian and Baltic Languages}, title = {Cross-lingual Parallelism and Translational Equivalence: {T}he Case of {FrameNet} Frames}, url = {https://www.nlpado.de/~sebastian/pub/papers/nodalida07_pado.pdf}, year = 2007 }
  Link
  https://www.nlpado.de/~sebastian/pub/papers/nodalida07_pado.pdf
2. Spohr, D., Burchardt, A., Padó, S., Frank, A., & Heid, U. (2007). Inducing a Computational Lexicon from a Corpus with Syntactic and Semantic Annotation. Proceedings of IWCS-7. https://www.nlpado.de/~sebastian/pub/papers/iwcs07_spohr.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{spohr07:_induc_comput_lexic_corpus_syntac_seman_annot, abstract = {To date, linguistically annotated corpora are mainly exploited for feature-based training of automatic labelling systems. In this paper, we present a general approach for the Description Logics-based modelling of multi-layered annotated corpora which offers (i) flexible and enhanced querying functionality that goes beyond current XML-based query languages, (ii) a basis for consistency checking, and (iii) a general method for defining abstractions over corpus annotations. We apply this method to the syntactically and semantically annotated SALSA/TIGER corpus . By defining abstractions over the corpus data, we generalise from a large set of individual corpus annotations to a corresponding lexicon model. We discuss issues arising from modelling multi-layered corpus annotations in Description Logics and illustrate the benefits of our approach at concrete examples.}, address = {Tilburg, The Netherlands}, author = {Spohr, Dennis and Burchardt, Aljoscha and Padó, Sebastian and Frank, Anette and Heid, Ulrich}, booktitle = {Proceedings of IWCS-7}, title = {Inducing a Computational Lexicon from a Corpus with Syntactic and Semantic Annotation}, url = {https://www.nlpado.de/~sebastian/pub/papers/iwcs07_spohr.pdf}, year = 2007 }
  Link
  https://www.nlpado.de/~sebastian/pub/papers/iwcs07_spohr.pdf
3. Padó, S., & Lapata, M. (2007). Dependency-based Construction of Semantic Spaces. Computational Linguistics, 33(2), Article 2. http://dx.doi.org/10.1162/coli.2007.33.2.161
  - BibTeX
  - Link
  BibTeX
  @article{pado07:_depen_const_seman_spaces, author = {Pad\'o, Sebastian and Lapata, Mirella}, journal = {Computational Linguistics}, number = 2, pages = {161--199}, title = {Dependency-based Construction of Semantic Spaces}, url = {http://dx.doi.org/10.1162/coli.2007.33.2.161}, volume = 33, year = 2007 }
  Link
  http://dx.doi.org/10.1162/coli.2007.33.2.161
2006
1. Erk, K., & Padó, S. (2006). Shalmaneser - a flexible toolbox for semantic role assignment. Proceedings of LREC 2006. http://www.lrec-conf.org/proceedings/lrec2006/pdf/537_pdf.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{erk:_shalm, abstract = {This paper presents Shalmaneser, a software package for shallow semantic parsing, the automatic assignment of semantic classes and roles to free text. Shalmaneser is a toolchain of independent modules communicating through a common XML format. System output can be inspected graphically. Shalmaneser can be used either as a "black box" to obtain semantic parses for new datasets (classifiers for English and German frame-semantic analysis are included), or as a research platform that can be extended to new parsers, languages, or classification paradigms.}, address = {Genoa, Italy}, author = {Erk, Katrin and Padó, Sebastian}, booktitle = {Proceedings of {LREC} 2006}, title = {Shalmaneser - a flexible toolbox for semantic role assignment}, url = {http://www.lrec-conf.org/proceedings/lrec2006/pdf/537_pdf.pdf}, year = 2006 }
  Link
  http://www.lrec-conf.org/proceedings/lrec2006/pdf/537_pdf.pdf
2. Burchardt, A., Erk, K., Frank, A., Kowalski, A., Padó, S., & Pinkal, M. (2006). Challenges in lexical semantics: Non-compositionality in SALSA corpus annotation. Deutsche Gesellschaft Für Sprachwissenschaft.
  - BibTeX
  BibTeX
  @inproceedings{burchardt06:_chall, address = {Bielefeld, Germany}, author = {Burchardt, Aljoscha and Erk, Katrin and Frank, Anette and Kowalski, Andrea and Pad\'o, Sebastian and Pinkal, Manfred}, booktitle = {Deutsche Gesellschaft für Sprachwissenschaft}, title = {Challenges in lexical semantics: Non-compositionality in {SALSA} corpus annotation}, year = 2006 }
3. Burchardt, A., Erk, K., Frank, A., Kowalski, A., Padó, S., & Pinkal, M. (2006). SALTO -- A Versatile Multi-Level Annotation Tool. Proceedings of LREC 2006. http://www.lrec-conf.org/proceedings/lrec2006/pdf/341_pdf.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{burchardt:_salto, abstract = {In this paper, we describe the SALTO tool. It was originally developed for the annotation of semantic roles in the frame semantics paradigm, but can be used for graphical annotation of treebanks with general relational information in a simple drag-and-drop fashion. The tool additionally supports corpus management and quality control.}, address = {Genoa, Italy}, author = {Burchardt, Aljoscha and Erk, Katrin and Frank, Anette and Kowalski, Andrea\ and Padó, Sebastian and Pinkal, Manfred}, booktitle = {Proceedings of {LREC} 2006}, title = {{SALTO} -- A Versatile Multi-Level Annotation Tool}, url = {http://www.lrec-conf.org/proceedings/lrec2006/pdf/341_pdf.pdf}, year = 2006 }
  Link
  http://www.lrec-conf.org/proceedings/lrec2006/pdf/341_pdf.pdf
4. Burchardt, A., Erk, K., Frank, A., Kowalski, A., Padó, S., & Pinkal, M. (2006). Consistency and Coverage: Challenges for exhaustive semantic annotation. Deutsche Gesellschaft Für Sprachwissenschaft.
  - BibTeX
  BibTeX
  @inproceedings{burchardt06:_consis_cover, address = {Bielefeld, Germany}, author = {Burchardt, Aljoscha and Erk, Katrin and Frank, Anette and Kowalski, Andrea and Pad\'o, Sebastian and Pinkal, Manfred}, booktitle = {Deutsche Gesellschaft für Sprachwissenschaft}, title = {Consistency and Coverage: Challenges for exhaustive semantic annotation}, year = 2006 }
5. Burchardt, A., Erk, K., Frank, A., Kowalski, A., Padó, S., & Pinkal, M. (2006). The SALSA corpus: a German corpus resource for lexical semantics. Proceedings of LREC 2006. http://www.lrec-conf.org/proceedings/lrec2006/pdf/339_pdf.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{burchardt:_salsa, abstract = {This paper describes the SALSA corpus, a large German corpus manually annotated with role-semantic information, based on the syntactically annotated TIGER newspaper corpus (Brants et al., 2002). The rst release, comprising about 20,000 annotated predicate instances (about half the TIGER corpus), is scheduled for mid-2006. In this paper we discuss the frame-semantic annotation framework and its cross-lingual applicability, problems arising from exhaustive annotation, strategies for quality control, and possible applications.}, address = {Genoa, Italy}, author = {Burchardt, Aljoscha and Erk, Katrin and Frank, Anette and Kowalski, Andrea\ and Padó, Sebastian and Pinkal, Manfred}, booktitle = {Proceedings of {LREC} 2006}, title = {The {SALSA} corpus: a {G}erman corpus resource for lexical semantics}, url = {http://www.lrec-conf.org/proceedings/lrec2006/pdf/339_pdf.pdf}, year = 2006 }
  Link
  http://www.lrec-conf.org/proceedings/lrec2006/pdf/339_pdf.pdf
6. Padó, S., & Lapata, M. (2006). Optimal Constituent Alignment with Edge Covers for Semantic Projection. Proceedings of COLING/ACL 2006, 1161--1168. http://www.aclweb.org/anthology/P/P06/P06-1146.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{pado06:_optim_const_align_edge_cover_seman_projec, abstract = {Given a parallel corpus, semantic projection attempts to transfer semantic role annotations from one language to another, typically by exploiting word alignments. In this paper, we present an improved method for obtaining constituent alignments between parallel sentences to guide the role projection task. Our extensions are twofold: (a) we model constituent alignment as minimum weight edge covers in a bipartite graph, which allows us to find a globally optimal solution efficiently; (b) we propose tree pruning as a promising strategy for reducing alignment noise. Experimental results on an English-German parallel corpus demonstrate improvements over state-of-the-art models.}, address = {Sydney, Australia}, author = {Padó, Sebastian and Lapata, Mirella}, booktitle = {Proceedings of COLING/ACL 2006}, pages = {1161--1168}, title = {Optimal Constituent Alignment with Edge Covers for Semantic Projection}, url = {http://www.aclweb.org/anthology/P/P06/P06-1146.pdf}, year = 2006 }
  Link
  http://www.aclweb.org/anthology/P/P06/P06-1146.pdf
2005
1. Erk, K., & Padó, S. (2005). Analysing models of semantic role assignment using confusability. Proceedings of HLT/EMNLP 2005. http://www.aclweb.org/anthology/H/H05/H05-1084.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{erk05:_analy, abstract = {We analyze models for semantic role assignment by defining a meta-model that abstracts over features and learning paradigms. This meta-model is based on the concept of role confusability, is defined in information-theoretic terms, and predicts that roles realized by less specific grammatical functions are more difficult to assign. We find that confusability is strongly correlated with the performance of classifiers based on syntactic features, but not for classifiers including semantic features. This indicates that syntactic features approximate a description of grammatical functions, and that semantic features provide an independent second view on the data.}, address = {Vancouver, Canada}, author = {Erk, Katrin and Padó, Sebastian}, booktitle = {Proceedings of HLT/EMNLP 2005}, title = {Analysing models of semantic role assignment using confusability}, url = {http://www.aclweb.org/anthology/H/H05/H05-1084.pdf}, year = 2005 }
  Link
  http://www.aclweb.org/anthology/H/H05/H05-1084.pdf
2. Padó, S., & Erk, K. (2005). To cause or not to cause: Cross-lingual semantic matching for paraphrase modelling. Proceedings of the Cross-Language Knowledge Induction Workshop.
  - BibTeX
  BibTeX
  @inproceedings{pado05:_cause, address = {Cluj-Napoca, Romania}, author = {Padó, Sebastian and Erk, Katrin}, booktitle = {Proceedings of the Cross-Language Knowledge Induction Workshop}, title = {To cause or not to cause: Cross-lingual semantic matching for paraphrase modelling}, year = 2005 }
3. Padó, S., & Lapata, M. (2005). Cross-lingual Bootstrapping for Semantic Lexicons: The case of FrameNet. Proceedings of AAAI 2005. http://www.nlpado.de/~sebastian/pub/papers/aaai05_pado.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{pado05:_cross_boots_seman_lexic, abstract = {This paper considers the problem of unsupervised semantic lexicon acquisition. We introduce a fully automatic approach which exploits parallel corpora, relies on shallow text properties, and is relatively inexpensive. Given the English FrameNet lexicon, our method exploits word alignments to generate frame candidate lists for new languages, which are subsequently pruned automatically using a small set of linguistically motivated filters. Evaluation shows that our approach can produce high-precision multilingual FrameNet lexicons without recourse to bilingual dictionaries or deep syntactic and semantic analysis.}, address = {Pittsburgh, PA}, author = {Padó, Sebastian and Lapata, Mirella}, booktitle = {Proceedings of AAAI 2005}, title = {Cross-lingual Bootstrapping for Semantic Lexicons: The case of {FrameNet}}, url = {http://www.nlpado.de/~sebastian/pub/papers/aaai05_pado.pdf}, year = 2005 }
  Link
  http://www.nlpado.de/~sebastian/pub/papers/aaai05_pado.pdf
4. Padó, S., & Lapata, M. (2005). Cross-lingual projection of role-semantic information. Proceedings of HTL/EMNLP 2005, 859--866. http://www.aclweb.org/anthology/H/H05/H05-1108.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{pado05:_cross, abstract = {This paper considers the problem of automatically inducing role-semantic annotations in the FrameNet paradigm for new languages. We introduce a general framework for semantic projection which exploits parallel texts, is relatively inexpensive and can potentially reduce the amount of effort involved in creating semantic resources. We propose projection models that exploit lexical and syntactic information. Experimental results on an English- German parallel corpus demonstrate the advantages of this approach.}, address = {Vancouver, Canada}, author = {Padó, Sebastian and Lapata, Mirella}, booktitle = {Proceedings of HTL/EMNLP 2005}, pages = {859--866}, title = {Cross-lingual projection of role-semantic information}, url = {http://www.aclweb.org/anthology/H/H05/H05-1108.pdf}, year = 2005 }
  Link
  http://www.aclweb.org/anthology/H/H05/H05-1108.pdf
2004
1. Ellsworth, M., Erk, K., Kingsbury, P., & Padó, S. (2004). PropBank, SALSA and FrameNet: How Design Determines Product. Proceedings of the Workshop on Building Lexical Resources From Semantically Annotated Corpora, LREC-2004. https://www.nlpado.de/~sebastian/pub/papers/lrec04_ellsworth.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{ellsworth04:_propb_salsa_framen, abstract = {We compare three projects that annotate semantic roles: PropBank, FrameNet, and SALSA. The first part of our analysis is a comparison of the different word sense distinction criteria underlying the annotation. Then, we study the effects of these criteria at the level of actual phenomena that require annotation. In particular, we discuss metaphor, support constructions, words with multiple meaning aspects, phrases realizing more than one semantic role, and nonlocal semantic roles.}, address = {Lisbon, Portugal}, author = {Ellsworth, Michael and Erk, Katrin and Kingsbury, Paul and Padó, Sebastian}, booktitle = {Proceedings of the Workshop on Building Lexical Resources From Semantically Annotated Corpora, LREC-2004}, title = {{P}rop{B}ank, {SALSA} and {F}rame{N}et: How Design Determines Product}, url = {https://www.nlpado.de/~sebastian/pub/papers/lrec04_ellsworth.pdf}, year = 2004 }
  Link
  https://www.nlpado.de/~sebastian/pub/papers/lrec04_ellsworth.pdf
2. Baldewein, U., Erk, K., Padó, S., & Prescher, D. (2004). Semantic Role Labelling With Similarity-Based Generalisation Using EM-based Clustering. Proceedings of SENSEVAL 3. http://www.aclweb.org/anthology/W/W04/W04-0817.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{baldewein04:_seman_role_label_with_simil, abstract = {We describe a system for semantic role assignment built as part of the Senseval III task, based on an off-the-shelf parser and Maxent and Memory-Based learners. We focus on generalisation using several similarity measures to increase the amount of training data available and on the use of EM-based clustering to improve role assignment. Our final score yields Precision=73.6\%, Recall=59.4\% (F=65.7).}, address = {Barcelona, Spain}, author = {Baldewein, Ulrike and Erk, Katrin and Padó, Sebastian and Prescher, Detlef}, booktitle = {Proceedings of SENSEVAL 3}, title = {Semantic Role Labelling With Similarity-Based Generalisation Using {EM}-based Clustering}, url = {http://www.aclweb.org/anthology/W/W04/W04-0817.pdf}, year = 2004 }
  Link
  http://www.aclweb.org/anthology/W/W04/W04-0817.pdf
3. Erk, K., & Padó, S. (2004). A powerful and versatile XML Format for representing role-semantic annotation. Proceedings of LREC 2004. http://www.lrec-conf.org/proceedings/lrec2004/pdf/202.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{erk04:_xml_format, abstract = {We present two XML formats for the description and encoding of semantic role information in corpora. The TIGER/SALSA XML format provides a modular representation for semantic roles and syntactic structure. The Text-SALSA XML format is a lightweight version of TIGER/SALSA XML designed for manual annotation with an XML editor rather than a special tool. Both formats can deal with underspecification, roles crossing the sentence boundary, compound splitting, and whole-sentence tags for meta-level comments.}, address = {Lisbon, Portugal}, author = {Erk, Katrin and Padó, Sebastian}, booktitle = {Proceedings of LREC 2004}, title = {A powerful and versatile {XML} Format for representing role-semantic annotation}, url = {http://www.lrec-conf.org/proceedings/lrec2004/pdf/202.pdf}, year = 2004 }
  Link
  http://www.lrec-conf.org/proceedings/lrec2004/pdf/202.pdf
4. Padó, S., & Boleda Torrent, G. (2004). The Influence of Argument Structure on Semantic Role Assignment. Proceedings of EMNLP 2004, 103--110. http://www.aclweb.org/anthology/W/W04/W04-3214.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{pado04:_influence, abstract = {We present a data and error analysis for semantic role labelling. In a first experiment, we build a generic statistical model for semantic role assignment in the FrameNet paradigm and show that there is a high variance in performance across frames. The main hypothesis of our paper is that this variance is to a large extent a result of differences in the underlying argument structure of the predicates in different frames. In a second experiment, we show that frame uniformity, which measures argument structure variation, correlates well with the performance figures, effectively explaining the variance.}, address = {Barcelona, Spain}, author = {Padó, Sebastian and {Boleda Torrent}, Gemma}, booktitle = {Proceedings of EMNLP 2004}, pages = {103--110}, title = {The Influence of Argument Structure on Semantic Role Assignment}, url = {http://www.aclweb.org/anthology/W/W04/W04-3214.pdf}, year = 2004 }
  Link
  http://www.aclweb.org/anthology/W/W04/W04-3214.pdf
5. Baldewein, U., Erk, K., Padó, S., & Prescher, D. (2004). Semantic Role Labelling for Chunk Sequences. Proceedings of the CoNLL 2004 Shared Task. http://www.aclweb.org/anthology/W/W04/W04-2413.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{baldewein04:_seman_role_label_chunk_sequen, abstract = {We describe a statistical approach to semantic role labelling that employs only shallow infor- mation. We use a Maximum Entropy learner, augmented by EM-based clustering to model the fit between a verb and its argument can- didate. The instances to be classified are se- quences of chunks that occur frequently as ar- guments in the training corpus. Our best model obtains an F score of 51.70 on the test set.}, address = {Boston, MA}, author = {Baldewein, Ulrike and Erk, Katrin and Padó, Sebastian and Prescher, Detlef}, booktitle = {Proceedings of the CoNLL 2004 shared task}, title = {Semantic Role Labelling for Chunk Sequences}, url = {http://www.aclweb.org/anthology/W/W04/W04-2413.pdf}, year = 2004 }
  Link
  http://www.aclweb.org/anthology/W/W04/W04-2413.pdf
2003
1. Erk, K., Kowalski, A., Padó, S., & Pinkal, M. (2003). Building a Resource for Lexical Semantics. Proceedings of the Workshop on Frame Semantics, XVII. International Congress of Linguists.
  - BibTeX
  BibTeX
  @inproceedings{erk03:_build_resour, address = {Prague, Czech Republic}, author = {Erk, Katrin and Kowalski, Andrea and Padó, Sebastian and Pinkal, Manfred}, booktitle = {Proceedings of the Workshop on Frame Semantics, XVII. International Congress of Linguists}, title = {Building a Resource for Lexical Semantics}, year = 2003 }
2. Erk, K., Kowalski, A., & Padó, S. (2003). The SALSA Annotation Tool. Proceedings of the Workshop on Prospects and Advances in the Syntax/Semantics Interface.
  - BibTeX
  BibTeX
  @inproceedings{erk03:_salsa_annot_tool, address = {Nancy, France}, author = {Erk, Katrin and Kowalski, Andrea and Padó, Sebastian}, booktitle = {Proceedings of the Workshop on Prospects and Advances in the Syntax/Semantics Interface}, title = {The {SALSA} Annotation Tool}, year = 2003 }
3. Erk, K., Kowalski, A., Padó, S., & Pinkal, M. (2003). Towards a Resource for Lexical Semantics: A Large German Corpus with Extensive Semantic Annotation. Proceedings of ACL 2003. http://www.aclweb.org/anthology/P/P03/P03-1068.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{erk03:_towar_resour, abstract = {We describe the ongoing construction of a large, semantically annotated corpus resource as reliable basis for the largescale acquisition of word-semantic information, e.g. the construction of domainindependent lexica. The backbone of the annotation are semantic roles in the frame semantics paradigm. We report experiences and evaluate the annotated data from the first project stage. On this basis, we discuss the problems of vagueness and ambiguity in semantic annotation.}, address = {Sapporo, Japan}, author = {Erk, Katrin and Kowalski, Andrea and Padó, Sebastian and Pinkal, Manfred}, booktitle = {Proceedings of ACL 2003}, title = {Towards a Resource for Lexical Semantics: A Large {G}erman Corpus with Extensive Semantic Annotation}, url = {http://www.aclweb.org/anthology/P/P03/P03-1068.pdf}, year = 2003 }
  Link
  http://www.aclweb.org/anthology/P/P03/P03-1068.pdf
4. Padó, S., & Boleda Torrent, G. (2003). Towards a better understanding of frame element assignment errors. Proceedings of the Workshop on Prospects and Advances in the Syntax/Semantics Interface.
  - BibTeX
  BibTeX
  @inproceedings{pado03:_towar, address = {Nancy, France}, author = {Padó, Sebastian and {Boleda Torrent}, Gemma}, booktitle = {Proceedings of the Workshop on Prospects and Advances in the Syntax/Semantics Interface}, title = {Towards a better understanding of frame element assignment errors}, year = 2003 }
5. Padó, S., & Lapata, M. (2003). Constructing Semantic Space Models from Parsed Corpora. Proceedings of ACL 2003, 128--135. http://www.aclweb.org/anthology/P/P03/P03-1017.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{pado03:_const_seman, abstract = {Traditional vector-based models use word co-occurrence counts from large corpora to represent lexical meaning. In this paper we present a novel approach for constructing semantic spaces that takes syntactic relations into account. We introduce a formalisation for this class of models and evaluate their adequacy on two modelling tasks: semantic priming and automatic discrimination of lexical relations.}, address = {Sapporo, Japan}, author = {Padó, Sebastian and Lapata, Mirella}, booktitle = {Proceedings of ACL 2003}, pages = {128--135}, title = {Constructing Semantic Space Models from Parsed Corpora}, url = {http://www.aclweb.org/anthology/P/P03/P03-1017.pdf}, year = 2003 }
  Link
  http://www.aclweb.org/anthology/P/P03/P03-1017.pdf

Teaching

SS 2018

Lecture "Empirische Methoden der Maschinellen Sprachverarbeitung" (with Antje Schweitzer)
Seminar "Ethics and NLP" (with Thang Vu)

Vita

since 2013:: Professor of Theoretical Computational Linguistics, IMS, Stuttgart University
2010-2013:: Professor of Computational Linguistics, ICL, Heidelberg University
2009-2010:: Juniorprofessor (Assistant Professor) of Computational Linguistics, IMS, Stuttgart University
2007-2009:: Postdoctoral Scholar, Department of Linguistics, Stanford University
2007:: PhD (Dr. phil.) in Computational Linguistics, Saarland University
2002:: MSc in Cognitive Science and Natural Language, University of Edinburgh

Supervision

I offer various BSc and MSc thesis topics. Please come to my office hour or check the IMS theses page on ILIAS.

If you write to me to inquire about internships or external thesis supervision, please add the word 'hospes' to the subject of your email. Otherwise I will not read it.

Team page

Sebastian Padó

Contact

Office Hours

Subject

Publications

2023

BibTeX

Link

BibTeX

Link

BibTeX

Link

2022

BibTeX

Link

BibTeX

Link

BibTeX

Link

BibTeX

Link

BibTeX

Link

2021

BibTeX

BibTeX

Link

BibTeX

Link

2019

BibTeX

Link

BibTeX

BibTeX

Link

2018

BibTeX

Link

BibTeX

Link

2017

BibTeX

Link

BibTeX

Link

BibTeX

Link

BibTeX

Link

BibTeX

Link

BibTeX

Link

2016

BibTeX

Link

BibTeX

Link

BibTeX

Link

BibTeX

BibTeX

BibTeX

BibTeX

Link

BibTeX

Link

2015

BibTeX

BibTeX

Link

BibTeX

Link

BibTeX

Link

BibTeX

Link

BibTeX

Link

2014