RTV

Tree kernels for thematic role classification

Daniele Pighin, Alessandro Moschitti, Roberto Basili

Research output: Contribution to conferencePaper

Abstract

We present a simple, two-steps supervised strategy for the identification and classification of thematic roles in natural language texts. We employ no external source of information but automatic parse trees of the input sentences. We use a few attribute-value features and tree kernel functions applied to specialized structured features. The resulting system has an F1 of 75.44 on the SemEval2007 closed task on semantic role labeling.

Original languageEnglish
Pages288-291
Number of pages4
Publication statusPublished - 1 Jan 2007
Event4th International Workshop on Semantic Evaluations, SemEval 2007 - Prague, Czech Republic
Duration: 23 Jun 200724 Jun 2007

Other

Other4th International Workshop on Semantic Evaluations, SemEval 2007
CountryCzech Republic
CityPrague
Period23/6/0724/6/07

Fingerprint

Labeling
Semantics
kernel
Kernel Function
Natural Language
Attribute
Closed
Strategy
Text

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Theoretical Computer Science

Cite this

Pighin, D., Moschitti, A., & Basili, R. (2007). RTV: Tree kernels for thematic role classification. 288-291. Paper presented at 4th International Workshop on Semantic Evaluations, SemEval 2007, Prague, Czech Republic.

RTV : Tree kernels for thematic role classification. / Pighin, Daniele; Moschitti, Alessandro; Basili, Roberto.

2007. 288-291 Paper presented at 4th International Workshop on Semantic Evaluations, SemEval 2007, Prague, Czech Republic.

Research output: Contribution to conferencePaper

Pighin, D, Moschitti, A & Basili, R 2007, 'RTV: Tree kernels for thematic role classification' Paper presented at 4th International Workshop on Semantic Evaluations, SemEval 2007, Prague, Czech Republic, 23/6/07 - 24/6/07, pp. 288-291.
Pighin D, Moschitti A, Basili R. RTV: Tree kernels for thematic role classification. 2007. Paper presented at 4th International Workshop on Semantic Evaluations, SemEval 2007, Prague, Czech Republic.
Pighin, Daniele ; Moschitti, Alessandro ; Basili, Roberto. / RTV : Tree kernels for thematic role classification. Paper presented at 4th International Workshop on Semantic Evaluations, SemEval 2007, Prague, Czech Republic.4 p.
@conference{9348a39afa1140f0824ab6d258ad2d6b,
title = "RTV: Tree kernels for thematic role classification",
abstract = "We present a simple, two-steps supervised strategy for the identification and classification of thematic roles in natural language texts. We employ no external source of information but automatic parse trees of the input sentences. We use a few attribute-value features and tree kernel functions applied to specialized structured features. The resulting system has an F1 of 75.44 on the SemEval2007 closed task on semantic role labeling.",
author = "Daniele Pighin and Alessandro Moschitti and Roberto Basili",
year = "2007",
month = "1",
day = "1",
language = "English",
pages = "288--291",
note = "4th International Workshop on Semantic Evaluations, SemEval 2007 ; Conference date: 23-06-2007 Through 24-06-2007",

}

TY - CONF

T1 - RTV

T2 - Tree kernels for thematic role classification

AU - Pighin, Daniele

AU - Moschitti, Alessandro

AU - Basili, Roberto

PY - 2007/1/1

Y1 - 2007/1/1

N2 - We present a simple, two-steps supervised strategy for the identification and classification of thematic roles in natural language texts. We employ no external source of information but automatic parse trees of the input sentences. We use a few attribute-value features and tree kernel functions applied to specialized structured features. The resulting system has an F1 of 75.44 on the SemEval2007 closed task on semantic role labeling.

AB - We present a simple, two-steps supervised strategy for the identification and classification of thematic roles in natural language texts. We employ no external source of information but automatic parse trees of the input sentences. We use a few attribute-value features and tree kernel functions applied to specialized structured features. The resulting system has an F1 of 75.44 on the SemEval2007 closed task on semantic role labeling.

UR - http://www.scopus.com/inward/record.url?scp=85036476970&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85036476970&partnerID=8YFLogxK

M3 - Paper

SP - 288

EP - 291

ER -