Abstract

Discourse parsing is a challenging task and plays a critical role in discourse analysis. In this paper, we focus on labeling full argument spans of discourse connectives in the Penn Discourse Treebank (PDTB). Previous studies cast this task as a linear tagging or subtree extraction problem. In this paper, we propose a novel constituent-based approach to argument labeling, which integrates the advantages of both linear tagging and subtree extraction. In particular, the proposed approach unifies intra- and intersentence cases by treating the immediately preceding sentence as a special constituent. Besides, a joint inference mechanism is introduced to incorporate global information across arguments into our constituent-based approach via integer linear programming. Evaluation on PDTB shows significant performance improvements of our constituent-based approach over the best state-of-the-art system. It also shows the effectiveness of our joint inference mechanism in modeling global information across arguments.

Highlights

  • Discourse parsing determines the internal structure of a text and identifies the discourse relations between its text units

  • We first evaluate the effectiveness of our constituent-based approach by comparing our system with the state-of-the-art systems, ignoring the joint inference mechanism

  • As a representative linear tagging approach, Ghosh et al (2011; 2012; 2012) only reported the exact match results for Arg1 and Arg2 using the evaluation script for chunking evaluation8 under GS+noEP setting with Section 02–22 of the Penn Discourse Treebank (PDTB) corpus for training, Section 23–24 for testing, and Section 00–01 for development

Read more

Summary

Introduction

Discourse parsing determines the internal structure of a text and identifies the discourse relations between its text units It has attracted increasing attention in recent years due to its importance in text understanding, especially since the release of the Penn Discourse Treebank (PDTB) corpus (Prasad et al, 2008), which adds a layer of discourse annotations on top of the Penn Treebank (PTB) corpus (Marcus et al, 1993). For argument labeling, Lin et al (2014) only achieved the performance of 53.85% in Fmeasure using gold-standard parse trees and connectives, much lower than the inter-annotation agreement of 90.20% (Miltsakaki et al, 2004)

Methods
Results
Conclusion
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.