Collaborative Research Centre 1287 - Limits of Variability in Language: Cognitive, Computational, and Grammatical Aspects

B06

Predicting the limits of variability in discourse using neural models

PI(s): Prof. Dr. David Schlangen & Prof. Dr. Manfred Stede

We investigate the notion of utterance acceptability in context, and through it, the underlying competence notion coherence, understanding it quite directly as a limit on variability in discourse follow-ups. We will assemble a test suite of relevant cases (in English), and collect acceptability judgements. Building on this, we will study which aspects of this notion, if any, neural language models capture. Finally, we will use the results of these studies to investigate whether we can improve the models by providing inductive biases that introduce discourse structural knowledge. A particular focus in these studies is on coherence in dialogue.

Members

Beyer

Anne Beyer

Universität PotsdamCampus GolmDepartment LinguistikKarl-Liebknecht-Strasse 24-25, Haus 14, Raum 2.2814476 Potsdam
Schlangen

Prof. Dr. David Schlangen

Universität PotsdamCampus GolmDepartment PsychologieKarl-Liebknecht-Strasse 24-25, Haus 14, Raum 2.1914476 Potsdam
(+49) 331 977-2692E-MailLink
Stede

Prof. Dr. Manfred Stede

Universität PotsdamCampus GolmDepartment LinguistikKarl-Liebknecht-Strasse 24-25, Haus 14, Raum 2.3114476 Potsdam
(+49) 331 977-2691E-MailLink | Link

Publications

Author(s)TitleYearPublished inDOILinksTypeProject
Loáiciga, S., Beyer, A., & Schlangen, D.New or Old? Exploring How Pre-Trained Language Models Represent Discourse Entities.2022Proceedings of the 29th International Conference on Computational Linguistics (pp. 875-886). Gyeongju, Republic of Korea.Paper CodePeer-ReviewedB06