Re ranking Models in Fine-grained Opinion Analysis

Richard Johansson, Alessandro Moschitti

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

17 Citations (Scopus)

Abstract

We describe the implementation of re ranking models for fine-grained opinion analysis - marking up opinion expressions and extracting opinion holders. The re ranking approach makes it possible to model complex relations between multiple opinions in a sentence, allowing us to represent how opinions interact through the syntactic and semantic structure. We carried out evaluations on the MPQA corpus, and the experiments showed significant improvements over a conventional system that only uses local information: for both tasks, our system saw recall boosts of over 10 points.

Original languageEnglish
Title of host publicationColing 2010 - 23rd International Conference on Computational Linguistics, Proceedings of the Conference
Pages519-527
Number of pages9
Volume2
Publication statusPublished - 1 Dec 2010
Externally publishedYes
Event23rd International Conference on Computational Linguistics, Coling 2010 - Beijing, China
Duration: 23 Aug 201027 Aug 2010

Other

Other23rd International Conference on Computational Linguistics, Coling 2010
CountryChina
CityBeijing
Period23/8/1027/8/10

Fingerprint

ranking
Syntactics
Semantics
Experiments
semantics
Ranking
experiment
evaluation
Evaluation
Conventional
Semantic Structure
Experiment
Syntactic Structure

ASJC Scopus subject areas

  • Language and Linguistics
  • Computational Theory and Mathematics
  • Linguistics and Language

Cite this

Johansson, R., & Moschitti, A. (2010). Re ranking Models in Fine-grained Opinion Analysis. In Coling 2010 - 23rd International Conference on Computational Linguistics, Proceedings of the Conference (Vol. 2, pp. 519-527)

Re ranking Models in Fine-grained Opinion Analysis. / Johansson, Richard; Moschitti, Alessandro.

Coling 2010 - 23rd International Conference on Computational Linguistics, Proceedings of the Conference. Vol. 2 2010. p. 519-527.

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

Johansson, R & Moschitti, A 2010, Re ranking Models in Fine-grained Opinion Analysis. in Coling 2010 - 23rd International Conference on Computational Linguistics, Proceedings of the Conference. vol. 2, pp. 519-527, 23rd International Conference on Computational Linguistics, Coling 2010, Beijing, China, 23/8/10.
Johansson R, Moschitti A. Re ranking Models in Fine-grained Opinion Analysis. In Coling 2010 - 23rd International Conference on Computational Linguistics, Proceedings of the Conference. Vol. 2. 2010. p. 519-527
Johansson, Richard ; Moschitti, Alessandro. / Re ranking Models in Fine-grained Opinion Analysis. Coling 2010 - 23rd International Conference on Computational Linguistics, Proceedings of the Conference. Vol. 2 2010. pp. 519-527
@inproceedings{e225b5d208da4c4e99d4b2976a044284,
title = "Re ranking Models in Fine-grained Opinion Analysis",
abstract = "We describe the implementation of re ranking models for fine-grained opinion analysis - marking up opinion expressions and extracting opinion holders. The re ranking approach makes it possible to model complex relations between multiple opinions in a sentence, allowing us to represent how opinions interact through the syntactic and semantic structure. We carried out evaluations on the MPQA corpus, and the experiments showed significant improvements over a conventional system that only uses local information: for both tasks, our system saw recall boosts of over 10 points.",
author = "Richard Johansson and Alessandro Moschitti",
year = "2010",
month = "12",
day = "1",
language = "English",
volume = "2",
pages = "519--527",
booktitle = "Coling 2010 - 23rd International Conference on Computational Linguistics, Proceedings of the Conference",

}

TY - GEN

T1 - Re ranking Models in Fine-grained Opinion Analysis

AU - Johansson, Richard

AU - Moschitti, Alessandro

PY - 2010/12/1

Y1 - 2010/12/1

N2 - We describe the implementation of re ranking models for fine-grained opinion analysis - marking up opinion expressions and extracting opinion holders. The re ranking approach makes it possible to model complex relations between multiple opinions in a sentence, allowing us to represent how opinions interact through the syntactic and semantic structure. We carried out evaluations on the MPQA corpus, and the experiments showed significant improvements over a conventional system that only uses local information: for both tasks, our system saw recall boosts of over 10 points.

AB - We describe the implementation of re ranking models for fine-grained opinion analysis - marking up opinion expressions and extracting opinion holders. The re ranking approach makes it possible to model complex relations between multiple opinions in a sentence, allowing us to represent how opinions interact through the syntactic and semantic structure. We carried out evaluations on the MPQA corpus, and the experiments showed significant improvements over a conventional system that only uses local information: for both tasks, our system saw recall boosts of over 10 points.

UR - http://www.scopus.com/inward/record.url?scp=79959208778&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79959208778&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2

SP - 519

EP - 527

BT - Coling 2010 - 23rd International Conference on Computational Linguistics, Proceedings of the Conference

ER -