Relation classification for semantic structure annotation of text

Yulan Yan, Yutaka Matsuo, Mitsuru Ishizuka, Toshio Yokoi

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

3 Citations (Scopus)

Abstract

Confronting the challenges of annotating naturally occurring text into a semantically structured form to facilitate automatic information extraction, current Semantic Role Labeling (SRL) systems have been specifically examining a semantic predicate-argument structure. Based on the Concept Description Language for Natural Language (CDL.nl) which is intended to describe the concept structure of text using a set of pre-defined semantic relations, we develop a parser to add a new layer of semantic annotation of natural language sentences as an extension of SRL. With the assumption that all relation instances are detected, we present a relation classification approach facing the challenges of CDL.nl relation extraction. Preliminary evaluation on a manual dataset, using Support Vector Machine, shows that CDL.nl relations can be classified with good performance.

Original languageEnglish
Title of host publicationProceedings - 2008 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2008
Pages377-380
Number of pages4
DOIs
Publication statusPublished - 2008
Externally publishedYes
Event2008 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2008 - Sydney, NSW
Duration: 2008 Dec 92008 Dec 12

Other

Other2008 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2008
CitySydney, NSW
Period08/12/908/12/12

Fingerprint

Semantics
Labeling
Support vector machines

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Yan, Y., Matsuo, Y., Ishizuka, M., & Yokoi, T. (2008). Relation classification for semantic structure annotation of text. In Proceedings - 2008 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2008 (pp. 377-380). [4740476] https://doi.org/10.1109/WIIAT.2008.128

Relation classification for semantic structure annotation of text. / Yan, Yulan; Matsuo, Yutaka; Ishizuka, Mitsuru; Yokoi, Toshio.

Proceedings - 2008 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2008. 2008. p. 377-380 4740476.

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

Yan, Y, Matsuo, Y, Ishizuka, M & Yokoi, T 2008, Relation classification for semantic structure annotation of text. in Proceedings - 2008 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2008., 4740476, pp. 377-380, 2008 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2008, Sydney, NSW, 08/12/9. https://doi.org/10.1109/WIIAT.2008.128
Yan Y, Matsuo Y, Ishizuka M, Yokoi T. Relation classification for semantic structure annotation of text. In Proceedings - 2008 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2008. 2008. p. 377-380. 4740476 https://doi.org/10.1109/WIIAT.2008.128
Yan, Yulan ; Matsuo, Yutaka ; Ishizuka, Mitsuru ; Yokoi, Toshio. / Relation classification for semantic structure annotation of text. Proceedings - 2008 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2008. 2008. pp. 377-380
@inproceedings{866745c67a6747da9970e1bc06022fc0,
title = "Relation classification for semantic structure annotation of text",
abstract = "Confronting the challenges of annotating naturally occurring text into a semantically structured form to facilitate automatic information extraction, current Semantic Role Labeling (SRL) systems have been specifically examining a semantic predicate-argument structure. Based on the Concept Description Language for Natural Language (CDL.nl) which is intended to describe the concept structure of text using a set of pre-defined semantic relations, we develop a parser to add a new layer of semantic annotation of natural language sentences as an extension of SRL. With the assumption that all relation instances are detected, we present a relation classification approach facing the challenges of CDL.nl relation extraction. Preliminary evaluation on a manual dataset, using Support Vector Machine, shows that CDL.nl relations can be classified with good performance.",
author = "Yulan Yan and Yutaka Matsuo and Mitsuru Ishizuka and Toshio Yokoi",
year = "2008",
doi = "10.1109/WIIAT.2008.128",
language = "English",
isbn = "9780769534961",
pages = "377--380",
booktitle = "Proceedings - 2008 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2008",

}

TY - GEN

T1 - Relation classification for semantic structure annotation of text

AU - Yan, Yulan

AU - Matsuo, Yutaka

AU - Ishizuka, Mitsuru

AU - Yokoi, Toshio

PY - 2008

Y1 - 2008

N2 - Confronting the challenges of annotating naturally occurring text into a semantically structured form to facilitate automatic information extraction, current Semantic Role Labeling (SRL) systems have been specifically examining a semantic predicate-argument structure. Based on the Concept Description Language for Natural Language (CDL.nl) which is intended to describe the concept structure of text using a set of pre-defined semantic relations, we develop a parser to add a new layer of semantic annotation of natural language sentences as an extension of SRL. With the assumption that all relation instances are detected, we present a relation classification approach facing the challenges of CDL.nl relation extraction. Preliminary evaluation on a manual dataset, using Support Vector Machine, shows that CDL.nl relations can be classified with good performance.

AB - Confronting the challenges of annotating naturally occurring text into a semantically structured form to facilitate automatic information extraction, current Semantic Role Labeling (SRL) systems have been specifically examining a semantic predicate-argument structure. Based on the Concept Description Language for Natural Language (CDL.nl) which is intended to describe the concept structure of text using a set of pre-defined semantic relations, we develop a parser to add a new layer of semantic annotation of natural language sentences as an extension of SRL. With the assumption that all relation instances are detected, we present a relation classification approach facing the challenges of CDL.nl relation extraction. Preliminary evaluation on a manual dataset, using Support Vector Machine, shows that CDL.nl relations can be classified with good performance.

UR - http://www.scopus.com/inward/record.url?scp=62949170928&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=62949170928&partnerID=8YFLogxK

U2 - 10.1109/WIIAT.2008.128

DO - 10.1109/WIIAT.2008.128

M3 - Conference contribution

SN - 9780769534961

SP - 377

EP - 380

BT - Proceedings - 2008 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2008

ER -