A novel discriminative framework for sentence-level discourse analysis

Shafiq Joty, Giuseppe Carenini, Raymond T. Ng

Research output: Chapter in Book/Report/Conference proceedingConference contribution

36 Citations (Scopus)

Abstract

We propose a complete probabilistic discriminative framework for performing sentence-level discourse analysis. Our framework comprises a discourse segmenter, based on a binary classifier, and a discourse parser, which applies an optimal CKY-like parsing algorithm to probabilities inferred from a Dynamic Conditional Random Field. We show on two corpora that our approach outperforms the state-of-the-art, often by a wide margin.

Original languageEnglish
Title of host publicationEMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference
Pages904-915
Number of pages12
Publication statusPublished - 1 Dec 2012
Event2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2012 - Jeju Island, Korea, Republic of
Duration: 12 Jul 201214 Jul 2012

Publication series

NameEMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference

Other

Other2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2012
CountryKorea, Republic of
CityJeju Island
Period12/7/1214/7/12

    Fingerprint

ASJC Scopus subject areas

  • Software

Cite this

Joty, S., Carenini, G., & Ng, R. T. (2012). A novel discriminative framework for sentence-level discourse analysis. In EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference (pp. 904-915). (EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference).