Syntactic and semantic structure for opinion expression detection

Richard Johansson, Alessandro Moschitti

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

44 Citations (Scopus)

Abstract

We demonstrate that relational features derived from dependency-syntactic and semantic role structures are useful for the task of detecting opinionated expressions in natural-language text, significantly improving over conventional models based on sequence labeling with local features. These features allow us to model the way opinionated expressions interact in a sentence over arbitrary distances. While the relational features make the prediction task more computationally expensive, we show that it can be tackled effectively by using a reranker. We evaluate a number of machine learning approaches for the reranker, and the best model results in a 10-point absolute improvement in soft recall on the MPQA corpus, while decreasing precision only slightly.

Original languageEnglish
Title of host publicationCoNLL 2010 - Fourteenth Conference on Computational Natural Language Learning, Proceedings of the Conference
Pages67-76
Number of pages10
Publication statusPublished - 1 Dec 2010
Externally publishedYes
Event14th Conference on Computational Natural Language Learning, CoNLL 2010 - Uppsala, Sweden
Duration: 15 Jul 201016 Jul 2010

Other

Other14th Conference on Computational Natural Language Learning, CoNLL 2010
CountrySweden
CityUppsala
Period15/7/1016/7/10

Fingerprint

Syntactics
Semantics
semantics
Labeling
Learning systems
language
learning

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Linguistics and Language

Cite this

Johansson, R., & Moschitti, A. (2010). Syntactic and semantic structure for opinion expression detection. In CoNLL 2010 - Fourteenth Conference on Computational Natural Language Learning, Proceedings of the Conference (pp. 67-76)

Syntactic and semantic structure for opinion expression detection. / Johansson, Richard; Moschitti, Alessandro.

CoNLL 2010 - Fourteenth Conference on Computational Natural Language Learning, Proceedings of the Conference. 2010. p. 67-76.

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

Johansson, R & Moschitti, A 2010, Syntactic and semantic structure for opinion expression detection. in CoNLL 2010 - Fourteenth Conference on Computational Natural Language Learning, Proceedings of the Conference. pp. 67-76, 14th Conference on Computational Natural Language Learning, CoNLL 2010, Uppsala, Sweden, 15/7/10.
Johansson R, Moschitti A. Syntactic and semantic structure for opinion expression detection. In CoNLL 2010 - Fourteenth Conference on Computational Natural Language Learning, Proceedings of the Conference. 2010. p. 67-76
Johansson, Richard ; Moschitti, Alessandro. / Syntactic and semantic structure for opinion expression detection. CoNLL 2010 - Fourteenth Conference on Computational Natural Language Learning, Proceedings of the Conference. 2010. pp. 67-76
@inproceedings{3a900eddb3a24ca59ed029f8d209ea5e,
title = "Syntactic and semantic structure for opinion expression detection",
abstract = "We demonstrate that relational features derived from dependency-syntactic and semantic role structures are useful for the task of detecting opinionated expressions in natural-language text, significantly improving over conventional models based on sequence labeling with local features. These features allow us to model the way opinionated expressions interact in a sentence over arbitrary distances. While the relational features make the prediction task more computationally expensive, we show that it can be tackled effectively by using a reranker. We evaluate a number of machine learning approaches for the reranker, and the best model results in a 10-point absolute improvement in soft recall on the MPQA corpus, while decreasing precision only slightly.",
author = "Richard Johansson and Alessandro Moschitti",
year = "2010",
month = "12",
day = "1",
language = "English",
isbn = "9781932432831",
pages = "67--76",
booktitle = "CoNLL 2010 - Fourteenth Conference on Computational Natural Language Learning, Proceedings of the Conference",

}

TY - GEN

T1 - Syntactic and semantic structure for opinion expression detection

AU - Johansson, Richard

AU - Moschitti, Alessandro

PY - 2010/12/1

Y1 - 2010/12/1

N2 - We demonstrate that relational features derived from dependency-syntactic and semantic role structures are useful for the task of detecting opinionated expressions in natural-language text, significantly improving over conventional models based on sequence labeling with local features. These features allow us to model the way opinionated expressions interact in a sentence over arbitrary distances. While the relational features make the prediction task more computationally expensive, we show that it can be tackled effectively by using a reranker. We evaluate a number of machine learning approaches for the reranker, and the best model results in a 10-point absolute improvement in soft recall on the MPQA corpus, while decreasing precision only slightly.

AB - We demonstrate that relational features derived from dependency-syntactic and semantic role structures are useful for the task of detecting opinionated expressions in natural-language text, significantly improving over conventional models based on sequence labeling with local features. These features allow us to model the way opinionated expressions interact in a sentence over arbitrary distances. While the relational features make the prediction task more computationally expensive, we show that it can be tackled effectively by using a reranker. We evaluate a number of machine learning approaches for the reranker, and the best model results in a 10-point absolute improvement in soft recall on the MPQA corpus, while decreasing precision only slightly.

UR - http://www.scopus.com/inward/record.url?scp=84862285540&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862285540&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84862285540

SN - 9781932432831

SP - 67

EP - 76

BT - CoNLL 2010 - Fourteenth Conference on Computational Natural Language Learning, Proceedings of the Conference

ER -