Chaker Memmadi


Do sentence embeddings capture discourse properties of sentences from Scientific Abstracts ?
Laurine Huber | Chaker Memmadi | Mathilde Dargnat | Yannick Toussaint
Proceedings of the First Workshop on Computational Approaches to Discourse

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. We show that even if contextual encoders such as BERT or SciBERT encodes the coherence in discourse units, they do not help to predict three discourse relations commonly used in scientific abstracts. We discuss what these results underline, namely that these discourse relations are based on particular phrasing that allow non-contextual encoders to perform well.