Do sentence embeddings capture discourse properties of sentences from Scientific Abstracts ?

no code implementations • EMNLP (CODI) 2020 • Laurine Huber, Chaker Memmadi, Mathilde Dargnat, Yannick Toussaint

We introduce four tasks designed to determine which sentence encoders best capture discourse properties of sentences from scientific abstracts, namely coherence and cohesion between clauses of a sentence, and discourse relations within sentences.

Sentence Sentence Embeddings

\'Etude comparative de corr\'elats prosodiques de marqueurs discursifs fran\ccais et anglais selon leur fonction pragmatique (Comparative study on prosodic correlates of discourse markers in French and English according to their pragmatic function)

no code implementations • JEPTALNRECITAL 2020 • Lou Lee, Denis Jouvet, Katarina Bartkova, Yvon Keromnes, Mathilde Dargnat

L{'}analyse a {\'e}t{\'e} effectu{\'e}e sur plusieurs centaines d{'}occurrences de marqueurs discursifs extraits de corpus oraux fran{\c{c}}ais et anglais.

Aligning Discourse and Argumentation Structures using Subtrees and Redescription Mining

no code implementations • WS 2019 • Laurine Huber, Yannick Toussaint, Charlotte Roze, Mathilde Dargnat, Chlo{\'e} Braud

In this paper, we investigate similarities between discourse and argumentation structures by aligning subtrees in a corpus containing both annotations.