Improving semantic role classification with selectional preferences

Beñat Zapirain, Eneko Agirre, Lluís Marquez, Mihai Surdeanu

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

13 Citations (Scopus)

Abstract

This work incorporates Selectional Preferences (SP) into a Semantic Role (SR) Classification system. We learn separate selectional preferences for noun phrases and prepositional phrases and we integrate them in a state-of-the-art SR classification system both in the form of features and individual class predictors. We show that the inclusion of the refined SPs yields statistically significant improvements on both in domain and out of domain data (14.07% and 11.67% error reduction, respectively). The key factor for success is the combination of several SP methods with the original classification model using meta-classification.

Original languageEnglish (US)
Title of host publicationNAACL HLT 2010 - Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference
Pages373-376
Number of pages4
StatePublished - 2010
Externally publishedYes
Event2010 Human Language Technologies Conference ofthe North American Chapter of the Association for Computational Linguistics, NAACL HLT 2010 - Los Angeles, CA, United States
Duration: Jun 2 2010Jun 4 2010

Other

Other2010 Human Language Technologies Conference ofthe North American Chapter of the Association for Computational Linguistics, NAACL HLT 2010
CountryUnited States
CityLos Angeles, CA
Period6/2/106/4/10

Fingerprint

semantics
inclusion
Semantic Roles
Classification System
Noun Phrase
Inclusion
Predictors
Prepositional Phrase

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

Zapirain, B., Agirre, E., Marquez, L., & Surdeanu, M. (2010). Improving semantic role classification with selectional preferences. In NAACL HLT 2010 - Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference (pp. 373-376)

Improving semantic role classification with selectional preferences. / Zapirain, Beñat; Agirre, Eneko; Marquez, Lluís; Surdeanu, Mihai.

NAACL HLT 2010 - Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference. 2010. p. 373-376.

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

Zapirain, B, Agirre, E, Marquez, L & Surdeanu, M 2010, Improving semantic role classification with selectional preferences. in NAACL HLT 2010 - Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference. pp. 373-376, 2010 Human Language Technologies Conference ofthe North American Chapter of the Association for Computational Linguistics, NAACL HLT 2010, Los Angeles, CA, United States, 6/2/10.
Zapirain B, Agirre E, Marquez L, Surdeanu M. Improving semantic role classification with selectional preferences. In NAACL HLT 2010 - Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference. 2010. p. 373-376
Zapirain, Beñat ; Agirre, Eneko ; Marquez, Lluís ; Surdeanu, Mihai. / Improving semantic role classification with selectional preferences. NAACL HLT 2010 - Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference. 2010. pp. 373-376
@inproceedings{d1e62300a2e64457b725365d4c79a9fc,
title = "Improving semantic role classification with selectional preferences",
abstract = "This work incorporates Selectional Preferences (SP) into a Semantic Role (SR) Classification system. We learn separate selectional preferences for noun phrases and prepositional phrases and we integrate them in a state-of-the-art SR classification system both in the form of features and individual class predictors. We show that the inclusion of the refined SPs yields statistically significant improvements on both in domain and out of domain data (14.07{\%} and 11.67{\%} error reduction, respectively). The key factor for success is the combination of several SP methods with the original classification model using meta-classification.",
author = "Be{\~n}at Zapirain and Eneko Agirre and Llu{\'i}s Marquez and Mihai Surdeanu",
year = "2010",
language = "English (US)",
isbn = "1932432655",
pages = "373--376",
booktitle = "NAACL HLT 2010 - Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference",

}

TY - GEN

T1 - Improving semantic role classification with selectional preferences

AU - Zapirain, Beñat

AU - Agirre, Eneko

AU - Marquez, Lluís

AU - Surdeanu, Mihai

PY - 2010

Y1 - 2010

N2 - This work incorporates Selectional Preferences (SP) into a Semantic Role (SR) Classification system. We learn separate selectional preferences for noun phrases and prepositional phrases and we integrate them in a state-of-the-art SR classification system both in the form of features and individual class predictors. We show that the inclusion of the refined SPs yields statistically significant improvements on both in domain and out of domain data (14.07% and 11.67% error reduction, respectively). The key factor for success is the combination of several SP methods with the original classification model using meta-classification.

AB - This work incorporates Selectional Preferences (SP) into a Semantic Role (SR) Classification system. We learn separate selectional preferences for noun phrases and prepositional phrases and we integrate them in a state-of-the-art SR classification system both in the form of features and individual class predictors. We show that the inclusion of the refined SPs yields statistically significant improvements on both in domain and out of domain data (14.07% and 11.67% error reduction, respectively). The key factor for success is the combination of several SP methods with the original classification model using meta-classification.

UR - http://www.scopus.com/inward/record.url?scp=84858405660&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84858405660&partnerID=8YFLogxK

M3 - Conference contribution

SN - 1932432655

SN - 9781932432657

SP - 373

EP - 376

BT - NAACL HLT 2010 - Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference

ER -