Annotating an extension layer of semantic structure for natural language text

Yulan Yan, Yutaka Matsuo, Mitsuru Ishizuka, Toshio Yokoi

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

8 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. The parsing task is a relation extraction process with two steps: relation detection and relation classification. We advance a hybrid approach using different methods for two steps: first, based on dependency analysis, a rule-based method is presented to detect all entity pairs between each pair for which there exists a relationship; secondly, we use a feature-based method to assign a CDL.nl relation to each detected entity pair using Support Vector Machine. We report the preliminary experimental results carried out on our manual dataset annotated with CDL.nl relations.

Original languageEnglish
Title of host publicationProceedings - IEEE International Conference on Semantic Computing 2008, ICSC 2008
Pages174-181
Number of pages8
DOIs
Publication statusPublished - 2008
Externally publishedYes
Event2nd Annual IEEE International Conference on Semantic Computing, ICSC 2008 - Santa Clara, CA
Duration: 2008 Aug 42008 Aug 7

Other

Other2nd Annual IEEE International Conference on Semantic Computing, ICSC 2008
CitySanta Clara, CA
Period08/8/408/8/7

Fingerprint

Semantics
Labeling
Support vector machines

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Cite this

Yan, Y., Matsuo, Y., Ishizuka, M., & Yokoi, T. (2008). Annotating an extension layer of semantic structure for natural language text. In Proceedings - IEEE International Conference on Semantic Computing 2008, ICSC 2008 (pp. 174-181). [4597189] https://doi.org/10.1109/ICSC.2008.11

Annotating an extension layer of semantic structure for natural language text. / Yan, Yulan; Matsuo, Yutaka; Ishizuka, Mitsuru; Yokoi, Toshio.

Proceedings - IEEE International Conference on Semantic Computing 2008, ICSC 2008. 2008. p. 174-181 4597189.

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

Yan, Y, Matsuo, Y, Ishizuka, M & Yokoi, T 2008, Annotating an extension layer of semantic structure for natural language text. in Proceedings - IEEE International Conference on Semantic Computing 2008, ICSC 2008., 4597189, pp. 174-181, 2nd Annual IEEE International Conference on Semantic Computing, ICSC 2008, Santa Clara, CA, 08/8/4. https://doi.org/10.1109/ICSC.2008.11
Yan Y, Matsuo Y, Ishizuka M, Yokoi T. Annotating an extension layer of semantic structure for natural language text. In Proceedings - IEEE International Conference on Semantic Computing 2008, ICSC 2008. 2008. p. 174-181. 4597189 https://doi.org/10.1109/ICSC.2008.11
Yan, Yulan ; Matsuo, Yutaka ; Ishizuka, Mitsuru ; Yokoi, Toshio. / Annotating an extension layer of semantic structure for natural language text. Proceedings - IEEE International Conference on Semantic Computing 2008, ICSC 2008. 2008. pp. 174-181
@inproceedings{e186e1210e694734b548b8f25f27573b,
title = "Annotating an extension layer of semantic structure for natural language 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. The parsing task is a relation extraction process with two steps: relation detection and relation classification. We advance a hybrid approach using different methods for two steps: first, based on dependency analysis, a rule-based method is presented to detect all entity pairs between each pair for which there exists a relationship; secondly, we use a feature-based method to assign a CDL.nl relation to each detected entity pair using Support Vector Machine. We report the preliminary experimental results carried out on our manual dataset annotated with CDL.nl relations.",
author = "Yulan Yan and Yutaka Matsuo and Mitsuru Ishizuka and Toshio Yokoi",
year = "2008",
doi = "10.1109/ICSC.2008.11",
language = "English",
isbn = "9780769532790",
pages = "174--181",
booktitle = "Proceedings - IEEE International Conference on Semantic Computing 2008, ICSC 2008",

}

TY - GEN

T1 - Annotating an extension layer of semantic structure for natural language 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. The parsing task is a relation extraction process with two steps: relation detection and relation classification. We advance a hybrid approach using different methods for two steps: first, based on dependency analysis, a rule-based method is presented to detect all entity pairs between each pair for which there exists a relationship; secondly, we use a feature-based method to assign a CDL.nl relation to each detected entity pair using Support Vector Machine. We report the preliminary experimental results carried out on our manual dataset annotated with CDL.nl relations.

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. The parsing task is a relation extraction process with two steps: relation detection and relation classification. We advance a hybrid approach using different methods for two steps: first, based on dependency analysis, a rule-based method is presented to detect all entity pairs between each pair for which there exists a relationship; secondly, we use a feature-based method to assign a CDL.nl relation to each detected entity pair using Support Vector Machine. We report the preliminary experimental results carried out on our manual dataset annotated with CDL.nl relations.

UR - http://www.scopus.com/inward/record.url?scp=52149103761&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=52149103761&partnerID=8YFLogxK

U2 - 10.1109/ICSC.2008.11

DO - 10.1109/ICSC.2008.11

M3 - Conference contribution

SN - 9780769532790

SP - 174

EP - 181

BT - Proceedings - IEEE International Conference on Semantic Computing 2008, ICSC 2008

ER -