What Causes the Failure of Explicit to Implicit Discourse Relation Recognition?

arXiv:2404.00999v1 Announce Type: new
Abstract: We consider an unanswered question in the discourse processing community: why do relation classifiers trained on explicit examples (with connectives removed) perform poorly in real implicit scenarios? Prior work claimed this is due to linguistic dissimilarity between explicit and implicit examples but provided no empirical evidence. In this study, we show that one cause for such failure is a label shift after connectives are eliminated. Specifically, we find that the discourse relations expressed by some …

abstract arxiv classifiers community cs.cl discourse examples failure prior processing question recognition type work