Joint Syntacto-Discourse Parsing and the Syntacto-Discourse Treebank
This work addresses the challenge of discourse parsing for NLP researchers by providing a more integrated and efficient approach, though it is incremental as it builds upon existing span-based parsing methods.
The paper tackled the problem of discourse parsing by proposing the first end-to-end parser that jointly handles syntax and discourse, eliminating the need for preprocessing like segmentation or external parsers. It achieved state-of-the-art accuracy in end-to-end discourse parsing and introduced the first syntacto-discourse treebank by integrating existing resources.
Discourse parsing has long been treated as a stand-alone problem independent from constituency or dependency parsing. Most attempts at this problem are pipelined rather than end-to-end, sophisticated, and not self-contained: they assume gold-standard text segmentations (Elementary Discourse Units), and use external parsers for syntactic features. In this paper we propose the first end-to-end discourse parser that jointly parses in both syntax and discourse levels, as well as the first syntacto-discourse treebank by integrating the Penn Treebank with the RST Treebank. Built upon our recent span-based constituency parser, this joint syntacto-discourse parser requires no preprocessing whatsoever (such as segmentation or feature extraction), achieves the state-of-the-art end-to-end discourse parsing accuracy.