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) 331 977-2692 | 📧 | 🔗

Stede

Prof. Dr. Manfred Stede

Universität PotsdamCampus GolmDepartment LinguistikKarl-Liebknecht-Strasse 24-25, Haus 14, Raum 2.3114476 Potsdam

(+49) 331 977-2691 | 📧 | 🔗 | 🔗

Publications

Author(s)TitleYearPublished inDOILinksType

News

Sixth Summer School on Statistical Methods for Linguistics and Psychology

One goal of the summer school is to provide comprehensive training in the theory and application of statistics, with a…

Workshop: Basics of Artificial Neural Networks / Deep Learning

The SFB1287 at the University Potsdam invites interested researchers of linguistics to a free this workshop.This 2-day workshop offers an…