Hierarchical semantic role labeling

Alessandro Moschitti, Ana Maria Giuglea, Bonaventura Coppola, Roberto Basili

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

25 Citations (Scopus)

Abstract

We present a four-step hierarchical SRL strategy which generalizes the classical two-level approach (boundary detection and classification). To achieve this, we have split the classification step by grouping together roles which share linguistic properties (e.g. Core Roles versus Adjuncts). The results show that the nonoptimized hierarchical approach is computationally more efficient than the traditional systems and it preserves their accuracy.

Original languageEnglish
Title of host publicationCoNLL 2005 - Proceedings of the Ninth Conference on Computational Natural Language Learning
Pages201-204
Number of pages4
Publication statusPublished - 1 Dec 2005
Externally publishedYes
Event9th Conference on Computational Natural Language Learning, CoNLL 2005 - Ann Arbor, MI, United States
Duration: 29 Jun 200530 Jun 2005

Other

Other9th Conference on Computational Natural Language Learning, CoNLL 2005
CountryUnited States
CityAnn Arbor, MI
Period29/6/0530/6/05

Fingerprint

Labeling
Semantics
semantics
Linguistics
grouping
linguistics

ASJC Scopus subject areas

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

Cite this

Moschitti, A., Giuglea, A. M., Coppola, B., & Basili, R. (2005). Hierarchical semantic role labeling. In CoNLL 2005 - Proceedings of the Ninth Conference on Computational Natural Language Learning (pp. 201-204)

Hierarchical semantic role labeling. / Moschitti, Alessandro; Giuglea, Ana Maria; Coppola, Bonaventura; Basili, Roberto.

CoNLL 2005 - Proceedings of the Ninth Conference on Computational Natural Language Learning. 2005. p. 201-204.

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

Moschitti, A, Giuglea, AM, Coppola, B & Basili, R 2005, Hierarchical semantic role labeling. in CoNLL 2005 - Proceedings of the Ninth Conference on Computational Natural Language Learning. pp. 201-204, 9th Conference on Computational Natural Language Learning, CoNLL 2005, Ann Arbor, MI, United States, 29/6/05.
Moschitti A, Giuglea AM, Coppola B, Basili R. Hierarchical semantic role labeling. In CoNLL 2005 - Proceedings of the Ninth Conference on Computational Natural Language Learning. 2005. p. 201-204
Moschitti, Alessandro ; Giuglea, Ana Maria ; Coppola, Bonaventura ; Basili, Roberto. / Hierarchical semantic role labeling. CoNLL 2005 - Proceedings of the Ninth Conference on Computational Natural Language Learning. 2005. pp. 201-204
@inproceedings{39f7ddbdccb043acb7cf376b9dbbe657,
title = "Hierarchical semantic role labeling",
abstract = "We present a four-step hierarchical SRL strategy which generalizes the classical two-level approach (boundary detection and classification). To achieve this, we have split the classification step by grouping together roles which share linguistic properties (e.g. Core Roles versus Adjuncts). The results show that the nonoptimized hierarchical approach is computationally more efficient than the traditional systems and it preserves their accuracy.",
author = "Alessandro Moschitti and Giuglea, {Ana Maria} and Bonaventura Coppola and Roberto Basili",
year = "2005",
month = "12",
day = "1",
language = "English",
pages = "201--204",
booktitle = "CoNLL 2005 - Proceedings of the Ninth Conference on Computational Natural Language Learning",

}

TY - GEN

T1 - Hierarchical semantic role labeling

AU - Moschitti, Alessandro

AU - Giuglea, Ana Maria

AU - Coppola, Bonaventura

AU - Basili, Roberto

PY - 2005/12/1

Y1 - 2005/12/1

N2 - We present a four-step hierarchical SRL strategy which generalizes the classical two-level approach (boundary detection and classification). To achieve this, we have split the classification step by grouping together roles which share linguistic properties (e.g. Core Roles versus Adjuncts). The results show that the nonoptimized hierarchical approach is computationally more efficient than the traditional systems and it preserves their accuracy.

AB - We present a four-step hierarchical SRL strategy which generalizes the classical two-level approach (boundary detection and classification). To achieve this, we have split the classification step by grouping together roles which share linguistic properties (e.g. Core Roles versus Adjuncts). The results show that the nonoptimized hierarchical approach is computationally more efficient than the traditional systems and it preserves their accuracy.

UR - http://www.scopus.com/inward/record.url?scp=84862292702&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862292702&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84862292702

SP - 201

EP - 204

BT - CoNLL 2005 - Proceedings of the Ninth Conference on Computational Natural Language Learning

ER -