2023/09/10 by Yang Janet Liu, Tatsuya Aoyama, Liu, Yang Janet +3 · 1 voice
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling #cs.CL
paper · pdf · doi:10.48550/arxiv.2309.04940
openalex publication_date 2023/09/10 · arxiv published 2023/09/10 · arxiv updated 2023/09/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Despite recent advances in Natural Language Processing (NLP), hierarchical discourse parsing in the framework of Rhetorical Structure Theory remains challenging, and our understanding of the reasons for this are as yet limited. In this paper, we examine and model some of the factors associated with parsing difficulties in previous work: the existence of implicit discourse relations, challenges in identifying long-distance relations, out-of-vocabulary items, and more. In order to assess the relative importance of these variables, we also release two annotated English test-sets with explicit correct and distracting discourse markers associated with gold standard RST relations. Our results show that as in shallow discourse parsing, the explicit/implicit distinction plays a role, but that long-distance dependencies are the main challenge, while lack of lexical overlap is less of a problem, at least for in-domain parsing. Our final model is able to predict where errors will occur with an accuracy of 76.3% for the bottom-up parser and 76.6% for the top-down parser.