Department Foundations of Computational Linguistics

Department Foundations of Computational Linguistics, Head Prof. Dr. Jonas Kuhn

Welcome to the Chair Foundations of Computational Linguistics at IMS Stuttgart. The group has been led by Prof. Jonas Kuhn since January 2010.

Our group works on computational models for processing natural language using both rule-based and statistical techniques.

Team

Research interests of group members

Statistical models for dependency parsing focusing on morphologically rich languages. Our research puts special emphasis on the interaction between morphology and syntax. Our group obtained the best results on the two recent shared tasks on parsing morphologically rich languages (SPMRL 2013 and SPMRL 2014). We are also involved in the adaptation of Universal Dependencies to German.

Selected publications:

Algorithmic and theoretical challenges information structure and coreference. We develop novel algorithms for solving these tasks automatically as well devise annotation schemes and carry out annotation efforts. Of particular interest is the interaction between information structure and prosody, both on the modelling and computational side.

Selected publications:

Algorithmic and architectural aspects of data-driven generation. In particular, the interaction between referring expression generation and surface realization for end-to-end generation systems and morphologically rich languages (e.g. German). More recently, weakly supervised learning of representations for data-to-text generation and semantic parsing.

Selected publications:

Continuing a long tradition of work on corpora and language-technological tools at IMS, our group is involved in projects that focus on infrastructural aspects and the sustainability of language resources. This involves the creation of ready-to-use tool chains and web services, easy access to data by means of visualisations and query tools, the creation of meta data and the documentation of workflows for all kinds of language resources, and the support of collaborative annotation and curation efforts. The group also runs Stuttgart's CLARIN-D center.

Selected publications:

We collaborate with various disciplines in the humanities, developing a joint methodological framework for analyzing large text corpora against specific content-analytical questions. One of our goals is to make the aggregated results of such analyses transparent to scholars from the humanities, which requires adaptable models and interactive tools and user interfaces. We have been contributing to several DH-related projects: CLARIN-D, e-Identity, ePoetics, and we are involved in a new Stuttgart center for reflected text analytics (CRETA) in the Digital Humanities.

Selected publications:

  • Andre Blessing, Andrea Glaser, and Jonas Kuhn. Biographical Data Exploration as a Test-bed for a Multi-view, Multi-method Approach in the Digital Humanities. Proceedings of the first Conference on Biographical Data in a Digital World, 2015.
  • Andre Blessing, Fritz Kliche, Ulrich Heid, Cathleen Kantner, and Jonas Kuhn. Computerlinguistische Werkzeuge zur Erschließung und Exploration großer Textsammlungen aus der Perspektive fachspezifischer Theorie. Grenzen und Möglichkeiten der Digital Humanities Sonderband 1, 2015.
  • Jonas Kuhn and Nils Reiter. A Plea for a Method-driven Agenda in the Digital Humanities. Global Digital Humanities Conference, Sydney, Australia. 2015.
  • Markus John, Steffen Koch, Florian Heimerl, Andreas Müller, Thomas Ertl, and Jonas Kuhn. Interactive Visual Analysis Of German Poetics. Global Digital Humanities Conference, 2015.
  • Nils Reiter. Towards Annotating Narrative Segments. Proceedings of the 9th SIGHUM Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities (LaTeCH), 2015.
  • Schulz, S. & Keller, M. (2016). Code-Switching Ubique Est - Language Identification and Part-of-Speech Tagging for Historical Mixed Text. LaTeCH@ACL, August, Berlin: The Association for Computer Linguistics.

Continuing a long tradition at the IMS, one focus in our group is on Discourse Representation Theory, the syntax-semantics interface, and the role of lexical information in word formation and sentence/discourse semantics.

Selected publications:

Projects

Current Projects

Digital Humanities:

Infrastructure:

Past Projects

Digital Humanities:

  • e-Identity
    A collaboration between Political Science and Natural Language Processing
    PI: Prof. Dr. Cathleen Kantner, Co-PI at IMS: Prof. Dr. Jonas Kuhn
    further collaborators: University of Hildesheim and University of Potsdam
  • ePoetics
    A collaboration between Literary Studies, Computer Science and Natural Language Processing
    PI: Prof. Dr. Sandra Richter, Prof. Dr. Thomas Ertl, Prof. Dr. Jonas Kuhn, Prof. Dr. Andrea Rapp
  • DebateExplorer
    PI: Jonas Kuhn

SFB 732 Incremental Specification in Context

Associated Groups

Department Foundations of Computational Linguistics

This image shows Jonas Kuhn

Jonas Kuhn

Prof. Dr.

Chair of Foundations of Computational Linguistics

Sybille Laderer

 

Secretary Foundations of Computational Linguistics/Computational Linguistics

To the top of the page