Work

Joint Syntacto-Discourse Parsing and the Syntacto-Discourse Treebank

Year: 2017

Type: conference-paper

Abstract: 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 goldstandard 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 syntactodiscourse parser requires no preprocessing whatsoever (such as segmentation or feature extraction), achieves the state-of-theart end-to-end discourse parsing accuracy.

Source: Conference on Empirical Methods in Natural Language Processing (EMNLP)

DOI: 10.18653/v1/d17-1225

Authors: Kai Zhao, Liang Huang

Institutions: Google (United States), Oregon State University

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: National Science Foundation, Defense Advanced Research Projects Agency

Awards: G1037014486, G3959814348, EAGER: Collaborative Research: Scaling Up Discriminative Learning for Natural Language Understanding and Translation