This image shows Michael Roth

Michael Roth

Dr.

Emmy Noether group leader
Institute for Natural Language Processing (IMS)
Independent Junior Research Group MIST

Contact

Pfaffenwaldring 5b
70569 Stuttgart
Deutschland
Room: 01.020

Office Hours

By appointment.


News

  • March 2023: I will teach a workshop on Transformer Models for DH in Cologne.
  • December 2022: I gave an invited talk for GSCL. For more GSCL events, see here.
  • September 2022:
    • I gave the opening keynote at KONVENS. More details here.
    • We got one paper accepted (and one rejected) at AACL-IJCNLP 2022.
  • July 2022:
  • May 2022: Jennifer Sikos, Sebastian Padó and I got a LiLT journal article accepted.
  • April 2022: We got one paper accepted at LREC and one accepted at SemEval.

About me

As a computational linguist, I combine methods from computer science, linguistics, and the digital humanities. My research is driven by a deep fascination for natural languages and their efficiency. One focus for me is on variety, which occurs because language is used differently depending on context, and we as humans can apparently adapt to it without any effort. For computational models, a further challenge is posed by phenomena of implicit language, that is information and relations that seem intuitively obvious but are not explicitly realized and therefore difficult to capture automatically. Finally, misunderstandings can also occur between competent speakers, the linguistic causes of which also need to be taken into account by computational models.

Since March 2019, I am leading a DFG Emmy Noether research group at the IMS, which focuses in particular on potential causes of misunderstandings in instructional texts. We are investigating the extent to which such causes can be reconstructed from revision histories, which linguistic phenomena play a role in these processes, and how computational linguistic methods can be used to detect and correct corresponding text passages automatically. Our research has led to several conference papers and student theses as well as two best paper awards: Alok Debnath (now at Trinity College Dublin) received the Best Student Paper award at EACL 2021, and our shared task on clarifications received the Best Task Paper award at SemEval 2022.

Prior to my current position in Stuttgart, I worked as part of the SFB 1102 in Saarbrücken on interdisciplinary issues related to the modeling of script knowledge and its utility in language comprehension (work with Manfred Pinkal), carried out a DFG Research Fellowship in Edinburgh and Illinois on modeling contextual meaning (hosted by Mirella Lapata and Dan Roth), contributed to a EC FP7 cooperation project on software engineering (work with Ewan Klein), and received a PhD from the University of Heidelberg for a thesis on implicit language phenomena (advised by Anette Frank and Michael Strube).

 

  1. 2022

    1. Vanderlyn, L., Anthonio, T., Ortega, D., Roth, M., & Vu, N. T. (2022). Toward Implicit Reference in Dialog: A Survey of Methods and Data. Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing.
    2. Roth, M., Anthonio, T., & Sauer, A. (2022). SemEval-2022 Task 7: Identifying Plausible Clarifications of Implicit and Underspecified Phrases in Instructional Texts. Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), 1039--1049. https://aclanthology.org/2022.semeval-1.146
    3. 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
    4. Anthonio, T., Sauer, A., & Roth, M. (2022). Clarifying Implicit and Underspecified Phrases in Instructional Text. Proceedings of the Language Resources and Evaluation Conference, 3319--3330. https://aclanthology.org/2022.lrec-1.354
  2. 2021

    1. Anthonio, T., & Roth, M. (2021). Resolving Implicit References in Instructional Texts. Proceedings of the 2nd Workshop on Computational Approaches to Discourse, 58--71. https://aclanthology.org/2021.codi-main.6
    2. Roth, M., & Anthonio, T. (2021). UnImplicit Shared Task Report: Detecting Clarification Requirements in Instructional Text. Proceedings of the 1st Workshop on Understanding Implicit and Underspecified Language, 28--32. https://aclanthology.org/2021.unimplicit-1.4
    3. Debnath, A., & Roth, M. (2021). A Computational Analysis of Vagueness in Revisions of Instructional Texts. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop, 30--35. https://www.aclweb.org/anthology/2021.eacl-srw.5
  3. 2020

    1. Anikina, T., Koller, A., & Roth, M. (2020). Predicting Coreference in Abstract Meaning Representations. Proceedings of the Third Workshop on Computational Models of Reference, Anaphora and Coreference, 33--38. https://www.aclweb.org/anthology/2020.crac-1.4
    2. Anthonio, T., & Roth, M. (2020). What Can We Learn from Noun Substitutions in Revision Histories? Proceedings of the 28th International Conference on Computational Linguistics, 1359--1370. https://www.aclweb.org/anthology/2020.coling-main.117
    3. Bhat, I., Anthonio, T., & Roth, M. (2020). Towards Modeling Revision Requirements in wikiHow Instructions. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 8407--8414. https://www.aclweb.org/anthology/2020.emnlp-main.675
    4. Anthonio, T., Bhat, I., & Roth, M. (2020). wikiHowToImprove: A Resource and Analyses on Edits in Instructional Texts. Proceedings of the 12th Language Resources and Evaluation Conference, 5721--5729. https://www.aclweb.org/anthology/2020.lrec-1.702
  4. 2019

    1. Wanzare, L. D. A., Roth, M., & Pinkal, M. (2019). Detecting Everyday Scenarios in Narrative Texts. Proceedings of the Second Workshop on Storytelling, 90--106. https://doi.org/10.18653/v1/W19-3410
    2. Ostermann, S., Roth, M., & Pinkal, M. (2019). MCScript2.0: A Machine Comprehension Corpus Focused on Script Events and Participants. Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019), 103--117. https://doi.org/10.18653/v1/S19-1012
    3. Ostermann, S., Zhang, S., Roth, M., & Clark, P. (2019). Commonsense Inference in Natural Language Processing (COIN) - Shared Task Report. Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing, 66--74. https://doi.org/10.18653/v1/D19-6007
    4. Roth, M., & Upadhyay, S. (2019). Combining Discourse Markers and Cross-lingual Embeddings for Synonym--Antonym Classification. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 3899--3905. https://doi.org/10.18653/v1/N19-1390
  5. 2018

    1. Khashabi, D., Chaturvedi, S., Roth, M., Upadhyay, S., & Roth, D. (2018). Looking Beyond the Surface: A Challenge Set for Reading Comprehension over Multiple Sentences. Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), 252--262. http://aclweb.org/anthology/N/N18/N18-1023.pdf
    2. Ostermann, S., Roth, M., Modi, A., Thater, S., & Pinkal, M. (2018). SemEval-2018 Task 11: Machine Comprehension Using Commonsense Knowledge. Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018), 747--757. http://aclweb.org/anthology/S/S18/S18-1119.pdf
    3. Kamper, H., & Roth, M. (2018). Visually Grounded Cross-lingual Keyword Spotting in Speech. The 6th International Workshop on Spoken Language Technologies for Under-Resourced Languages (SLTU 2018). https://www.isca-speech.org/archive/SLTU_2018/pdfs/Herman.pdf
    4. Ostermann, S., Modi, A., Roth, M., Thater, S., & Pinkal, M. (2018). MCScript: A Novel Dataset for Assessing Machine Comprehension Using Script Knowledge. Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), 3567--3574. http://www.lrec-conf.org/proceedings/lrec2018/pdf/225.pdf
  6. 2017

    1. Diamantopoulos, T. G., Roth, M., Symeonidis, A. L., & Klein, E. (2017). Software requirements as an application domain for natural language processing. Language Resources and Evaluation, 51(2), 495–524. http://dblp.uni-trier.de/db/journals/lre/lre51.html#DiamantopoulosR17
    2. Mostafazadeh, N., Roth, M., Louis, A., Chambers, N., & Allen, J. (2017). LSDSem 2017 Shared Task: The Story Cloze Test. Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics, 46--51. http://aclweb.org/anthology/W17-0906.pdf
    3. Roth, M. (2017). Role Semantics for Better Models of Implicit Discourse Relations. Proceedings of the 12th International Conference on Computational Semantics (IWCS). http://www.aclweb.org/anthology/W/W17/W17-6934.pdf
    4. Ostermann, S., Roth, M., Thater, S., & Pinkal, M. (2017). Aligning Script Events with Narrative Texts. Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM), 128--134. http://www.aclweb.org/anthology/S17-1016.pdf
  7. 2016

    1. Roth, M. (2016). Improving Frame Semantic Parsing via Dependency Path Embeddings. Book of Abstracts of the 9th International Conference on Construction Grammar, 165--167. http://www.ufjf.br/iccg9/files/2015/02/ICCG9_Book_of_Abstracts_v1.pdf#page=167
    2. Roth, M., & Lapata, M. (2016). Neural Semantic Role Labeling with Dependency Path Embeddings. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 1192--1202. http://www.aclweb.org/anthology/P16-1113
  8. 2015

    1. Roth, M., & Frank, A. (2015). Inducing Implicit Arguments from Comparable Texts: A Framework and its Applications. Computational Linguistics, 41(4), 625--664. http://www.mitpressjournals.org/doi/full/10.1162/COLI_a_00236
    2. Roth, M., & Lapata, M. (2015). Context-aware Frame-Semantic Role Labeling. Transactions of the Association for Computational Linguistics (TACL), 3, 449--460. https://tacl2013.cs.columbia.edu/ojs/index.php/tacl/article/view/652
    3. Roth, M., & Klein, E. (2015). Parsing Software Requirements with an Ontology-based Semantic Role Labeler. Proceedings of the IWCS Workshop Language and Ontologies, 14--21. http://www.aclweb.org/anthology/W/W15/W15-0403.pdf
  9. 2014

    1. Roth, M. (2014). Inducing Implicit Arguments via Cross-document Alignment: A Framework and its Applications [Heidelberg University, Germany]. http://www.ub.uni-heidelberg.de/archiv/17050
    2. Roth, M., & Woodsend, K. (2014). Composition of Word Representations Improves Semantic Role Labelling. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 407--413. http://www.aclweb.org/anthology/D14-1045.pdf
    3. Roth, M., & Schulte im Walde, S. (2014). Combining Word Patterns and Discourse Markers for Paradigmatic Relation Classification. Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL), Volume 2, 524--530. http://aclweb.org/anthology//P/P14/P14-2086.pdf
    4. Roth, M., Diamantopoulos, T., Klein, E., & Symeonidis, A. (2014). Software Requirements: A New Domain For Semantic Parsers. Proceedings of the ACL 2014 Workshop on Semantic Parsing (SP14), 50--54. http://www.aclweb.org/anthology/W14-2410.pdf
  10. 2013

    1. Moor, T., Roth, M., & Frank, A. (2013). Predicate-specific Annotations for Implicit Role Binding: Corpus Annotation, Data Analysis  and  Evaluation Experiments. Proceedings of the 10th International Conference on Computational Semantics (IWCS), 369--375. http://www.aclweb.org/anthology/W13-0211.pdf
    2. Roth, M., & Frank, A. (2013). Automatically Identifying Implicit Arguments to Improve Argument Linking and Coherence Modeling. Proceedings of the Second Joint Conference on Lexical and Computational Semantics (*SEM), 306--316. http://www.aclweb.org/anthology/S13-1043.pdf
  11. 2012

    1. Roth, M., & Frank, A. (2012). Aligning Predicate Argument Structures in Monolingual Comparable Texts: A new corpus for a new task. Proceedings of the First Joint Conference on Lexical and Computational Semantics (*SEM), 218--227. http://aclweb.org/anthology//S/S12/S12-1030.pdf
    2. Roth, M., & Frank, A. (2012). Aligning Predicates across Monolingual Comparable Texts using Graph-based Clustering. Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP), 171--182. http://www.aclweb.org/anthology/D12-1016.pdf
  12. 2011

    1. Schuldes, S., Boland, K., Roth, M., Strube, M., Kroemker, S., & Frank, A. (2011). Modeling Spatial Knowledge for Generating Verbal and Visual Route Directions. Proceedings of the 15th Annual KES Conference, Part IV, 366--377.
  13. 2010

    1. Roth, M., & Frank, A. (2010). Computing EM-based Alignments of Routes and Route Directions as a Basis for Natural Language Generation. Proceedings of the 23rd International Conference on Computational Linguistics (COLING), 958--966. http://www.aclweb.org/anthology/C10-1108.pdf
  14. 2009

    1. Roth, M., & Frank, A. (2009). A NLG-based Application for Walking Directions. Companion Volume to the Proceedings of the 47th Annual Meeting of the Association for Computational Linguistics and the 4th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing (ACL-IJCNLP), 37--40. http://aclweb.org/anthology/P/P09/P09-4010.pdf
    2. Schuldes, S., Roth, M., Frank, A., & Strube, M. (2009). Creating an Annotated Corpus for Generating Walking Directions. Proceedings of the ACL-IJCNLP’09 Workshop on Language Generation and Summarisation (UCNLG+Sum), 72--76. http://aclweb.org/anthology/W/W09/W09-2814.pdf
  15. 2008

    1. Roth, M. (2008). Representing FrameNet in Semantic Spaces.
    2. Schulte im Walde, S., Melinger, A., Roth, M., & Weber, A. (2008). An Empirical Characterisation of Response Types in German Association Norms. In Research on Language and Computation (No. 2; Vol. 6, Issue 2, pp. 205–238).
    3. Mukherjee, S., Fradkin, D., & Roth, M. (2008). Classifying Spend Transactions with Off-the-Shelf Learning Components. Proceedings of IEEE International Conference on Tools in Artificial Intelligence (ICTAI), 53--60.
    4. Pennacchiotti, M., Cao, D. D., Basili, R., Croce, D., & Roth, M. (2008). Automatic induction of FrameNet lexical units. Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing (EMNLP), 457--465. http://www.aclweb.org/anthology/D/D08/D08-1048.pdf
    5. Roth, M., & Schulte im Walde, S. (2008). Corpus Co-Occurrence and Dictionary and Wikipedia Entries as Resources for Semantic Relatedness Information. Proceedings of the 6th International Conference on Language Resources and Evaluation (LREC), 1852--1859. http://www.lrec-conf.org/proceedings/lrec2008/pdf/473_paper.pdf

At the University of Stuttgart, I regularly teach courses and seminars related to my research.

  • Lectures
    • Parsing (Summer 2022)
    • Mathematical Foundations of Machine Learning (Winter 2021, Summer 2020, Winter 2020)
  • Seminars
    • Language Technology for Diversity & Inclusion (Summer 2023, Winter 2021)
    • Context Sensitivity in Language Understanding (Summer 2021, Summer 2020)
    • Hot and Odd Topics in Semantics (Summer 2019)

During my PhD studies, I also taught foundation courses and seminars at Heidelberg University.

  • Winter 2011: Introduction to Resources in Computational Linguistics (Lectures + Exercises)
  • Winter 2010: Playfully to New Resources (Seminar)
  • Winter 2009: Natural Language Generation (Seminar)
  • Winter 2008: Corpus Acquisition and Text Classsification ("Software Project")
  • December 2021: selected top-15% candidate for the Hector RCD Award.
  • September 2021:
    • The website of our SemEval shared task on clarifications is now here
    • Talita Anthonio and I got a paper accepted at the CODI workshop.
  • August 2021:
    • The proceedings of our UnImplicit workshop are now available here.
    • We also got one paper rejected at EMNLP.
  • May 2021: Our shared task proposal has been accepted at SemEval 2022
  • April 2021:
    • Our contribution to the EACL-SRW won the Best Paper award! Paper here
    • I am an area chair for Semantics at CoNLL 2021.
  • March 2021: I am an area chair at EMNLP 2021. Please consider submitting!
  • February 2021: We are in the process of organizing a shared task (link).
  • January 2021: Alok Debnath and I got a paper accepted at the EACL-SRW!  
  • November 2020: Our workshop proposal got accepted for ACL (link).
  • October 2020: Tatiana Anikina, Alexander Koller and I got a workshop paper accepted!
  • September 2020: We received a couple of notifications regarding submitted papers:
    • Our submissions to COLING (link) and EMNLP (link) got accepted!
    • I also got one paper rejected at EMNLP and at CoNLL.
  • July 2020: I am an area chair at EACL 2021. Please consider submitting!
  • June 2020: Former student Simon Ostermann's PhD thesis is now availabe here.
  • Spring 2020: I am an area chair at CoNLL, AACL-IJCNLP and EMNLP 2020.
  • April 2020: Our paper submission to ACL 2020 got rejected.
  • March 2020: I am part of the Steering Committee for SemEval 2021.
  • February 2020: Our paper on edits in wikiHow has been accepted at LREC!
  • February 2020: I am a standing reviewer for Computational Linguistics.
To the top of the page