Discriminative reranking of discourse parses using tree kernels

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

11 Citations (Scopus)

Abstract

In this paper, we present a discriminative approach for reranking discourse trees generated by an existing probabilistic discourse parser. The reranker relies on tree kernels (TKs) to capture the global dependencies between discourse units in a tree. In particular, we design new computational structures of discourse trees, which combined with standard TKs, originate novel discourse TKs. The empirical evaluation shows that our reranker can improve the state-of-the-art sentence-level parsing accuracy from 79.77% to 82.15%, a relative error reduction of 11.8%, which in turn pushes the state-of-the-art documentlevel accuracy from 55.8% to 57.3%.

Original languageEnglish
Title of host publicationEMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages2049-2060
Number of pages12
ISBN (Print)9781937284961
Publication statusPublished - 2014
Event2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014 - Doha, Qatar
Duration: 25 Oct 201429 Oct 2014

Other

Other2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014
CountryQatar
CityDoha
Period25/10/1429/10/14

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Vision and Pattern Recognition
  • Information Systems

Cite this

Joty, S., & Moschitti, A. (2014). Discriminative reranking of discourse parses using tree kernels. In EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference (pp. 2049-2060). Association for Computational Linguistics (ACL).

Discriminative reranking of discourse parses using tree kernels. / Joty, Shafiq; Moschitti, Alessandro.

EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2014. p. 2049-2060.

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

Joty, S & Moschitti, A 2014, Discriminative reranking of discourse parses using tree kernels. in EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), pp. 2049-2060, 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, Doha, Qatar, 25/10/14.
Joty S, Moschitti A. Discriminative reranking of discourse parses using tree kernels. In EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2014. p. 2049-2060
Joty, Shafiq ; Moschitti, Alessandro. / Discriminative reranking of discourse parses using tree kernels. EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2014. pp. 2049-2060
@inproceedings{8a61d473983245ce9d85227b5c515b8f,
title = "Discriminative reranking of discourse parses using tree kernels",
abstract = "In this paper, we present a discriminative approach for reranking discourse trees generated by an existing probabilistic discourse parser. The reranker relies on tree kernels (TKs) to capture the global dependencies between discourse units in a tree. In particular, we design new computational structures of discourse trees, which combined with standard TKs, originate novel discourse TKs. The empirical evaluation shows that our reranker can improve the state-of-the-art sentence-level parsing accuracy from 79.77{\%} to 82.15{\%}, a relative error reduction of 11.8{\%}, which in turn pushes the state-of-the-art documentlevel accuracy from 55.8{\%} to 57.3{\%}.",
author = "Shafiq Joty and Alessandro Moschitti",
year = "2014",
language = "English",
isbn = "9781937284961",
pages = "2049--2060",
booktitle = "EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Discriminative reranking of discourse parses using tree kernels

AU - Joty, Shafiq

AU - Moschitti, Alessandro

PY - 2014

Y1 - 2014

N2 - In this paper, we present a discriminative approach for reranking discourse trees generated by an existing probabilistic discourse parser. The reranker relies on tree kernels (TKs) to capture the global dependencies between discourse units in a tree. In particular, we design new computational structures of discourse trees, which combined with standard TKs, originate novel discourse TKs. The empirical evaluation shows that our reranker can improve the state-of-the-art sentence-level parsing accuracy from 79.77% to 82.15%, a relative error reduction of 11.8%, which in turn pushes the state-of-the-art documentlevel accuracy from 55.8% to 57.3%.

AB - In this paper, we present a discriminative approach for reranking discourse trees generated by an existing probabilistic discourse parser. The reranker relies on tree kernels (TKs) to capture the global dependencies between discourse units in a tree. In particular, we design new computational structures of discourse trees, which combined with standard TKs, originate novel discourse TKs. The empirical evaluation shows that our reranker can improve the state-of-the-art sentence-level parsing accuracy from 79.77% to 82.15%, a relative error reduction of 11.8%, which in turn pushes the state-of-the-art documentlevel accuracy from 55.8% to 57.3%.

UR - http://www.scopus.com/inward/record.url?scp=84961317780&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961317780&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781937284961

SP - 2049

EP - 2060

BT - EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

ER -