Two practical rhetorical structure theory parsers

Mihai Surdeanu, Thomas Hicks, Marco A. Valenzuela-Escárcega

Research output: Contribution to conferencePaperpeer-review

60 Scopus citations

Abstract

We describe the design, development, and API for two discourse parsers for Rhetorical Structure Theory. The two parsers use the same underlying framework, but one uses features that rely on dependency syntax, produced by a fast shift-reduce parser, whereas the other uses a richer feature space, including both constituent- and dependency-syntax and coreference information, produced by the Stanford CoreNLP toolkit. Both parsers obtain state-of-the-art performance, and use a very simple API consisting of, minimally, two lines of Scala code. We accompany this code with a visualization library that runs the two parsers in parallel, and displays the two generated discourse trees side by side, which provides an intuitive way of comparing the two parsers.

Original languageEnglish (US)
Pages1-5
Number of pages5
StatePublished - 2015
Event14th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2015 - Denver, United States
Duration: May 31 2015Jun 5 2015

Conference

Conference14th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2015
Country/TerritoryUnited States
CityDenver
Period5/31/156/5/15

ASJC Scopus subject areas

  • Language and Linguistics
  • Computer Science Applications
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Two practical rhetorical structure theory parsers'. Together they form a unique fingerprint.

Cite this