What's Hard in English RST Parsing? Predictive Models for Error Analysis
This work addresses parsing difficulties in NLP for researchers, but it is incremental as it builds on prior error analysis with new annotated datasets.
The paper tackled the challenge of understanding why English RST parsing remains difficult, identifying long-distance dependencies as the main issue and achieving error prediction accuracies of 76.3% and 76.6% for two parsers.
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.