Do Sentence Embeddings Capture Discourse Properties of Sentences from Scientific Abstracts
empirical methods in natural language processing
摘要
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.
更多查看译文
关键词
scientific abstracts,sentences
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络