A PDTB-styled end-to-end discourse parser
- 6 November 2012
- journal article
- research article
- Published by Cambridge University Press (CUP) in Natural Language Engineering
- Vol. 20 (2) , 151-184
Abstract
Since the release of the large discourse-level annotation of the Penn Discourse Treebank (PDTB), research work has been carried out on certain subtasks of this annotation, such as disambiguating discourse connectives and classifying Explicit or Implicit relations. We see a need to construct a full parser on top of these subtasks and propose a way to evaluate the parser. In this work, we have designed and developed an end-to-end discourse parser-to-parse free texts in the PDTB style in a fully data-driven approach. The parser consists of multiple components joined in a sequential pipeline architecture, which includes a connective classifier, argument labeler, explicit classifier, non-explicit classifier, and attribution span labeler. Our trained parser first identifies all discourse and non-discourse relations, locates and labels their arguments, and then classifies the sense of the relation between each pair of arguments. For the identified relations, the parser also determines the attribution spans, if any, associated with them. We introduce novel approaches to locate and label arguments, and to identify attribution spans. We also significantly improve on the current state-of-the-art connective classifier. We propose and present a comprehensive evaluation from both component-wise and error-cascading perspectives, in which we illustrate how each component performs in isolation, as well as how the pipeline performs with errors propagated forward. The parser gives an overall system F1 score of 46.80 percent for partial matching utilizing gold standard parses, and 38.18 percent with full automation.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Discourse structure and language technologyNatural Language Engineering, 2011
- Modeling Local Coherence: An Entity-Based ApproachComputational Linguistics, 2008
- D‐LTAG: extending lexicalized TAG to discourseCognitive Science, 2004
- The classification of coherence relations and their linguistic markers: An exploration of two languagesJournal of Pragmatics, 1998
- WordNetCommunications of the ACM, 1995
- Temporal interpretation, discourse relations and commonsense entailmentLinguistics and Philosophy, 1993
- A formal model of the structure of discourseJournal of Pragmatics, 1988
- An augmented context free grammar for discourse1988
- Rhetorical Structure Theory: Toward a functional theory of text organizationText & Talk, 1988
- A syntactic approach to discourse semantics1984