A novel discriminative framework for sentence-level discourse analysis

Shafiq Rayhan Joty, Giuseppe Carenini, Raymond T. Ng

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

33 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
Externally publishedYes
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

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

Classifiers

ASJC Scopus subject areas

  • Software

Cite this

Rayhan 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)

A novel discriminative framework for sentence-level discourse analysis. / Rayhan Joty, Shafiq; Carenini, Giuseppe; Ng, Raymond T.

EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference. 2012. p. 904-915.

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

Rayhan Joty, S, Carenini, G & Ng, RT 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, 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2012, Jeju Island, Korea, Republic of, 12/7/12.
Rayhan Joty S, Carenini G, Ng RT. 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. 2012. p. 904-915
Rayhan Joty, Shafiq ; Carenini, Giuseppe ; Ng, Raymond T. / A novel discriminative framework for sentence-level discourse analysis. EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference. 2012. pp. 904-915
@inproceedings{65a2049de9ad4736948100e49b99a513,
title = "A novel discriminative framework for sentence-level discourse analysis",
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.",
author = "{Rayhan Joty}, Shafiq and Giuseppe Carenini and Ng, {Raymond T.}",
year = "2012",
month = "12",
day = "1",
language = "English",
isbn = "9781937284435",
pages = "904--915",
booktitle = "EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference",

}

TY - GEN

T1 - A novel discriminative framework for sentence-level discourse analysis

AU - Rayhan Joty, Shafiq

AU - Carenini, Giuseppe

AU - Ng, Raymond T.

PY - 2012/12/1

Y1 - 2012/12/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84876791740&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84876791740&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781937284435

SP - 904

EP - 915

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

ER -