Automatic extraction of is-a relations in taxonomy learning

Mahmood Neshati, Hassan Abolhassani, Hassan Fatemi

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

Abstract

Taxonomy learning is a prerequisite step for ontology learning. In order to create a taxonomy, first of all, existing 'is-a' relations between words should be extracted. A known way to extract 'is-a' relations is finding lexicosyntactic patterns in large text corpus. Although this approach produces results with high precision but it suffers from low values of recall. Furthermore developing a comprehensive set of patterns is tedious and cumbersome. In this paper, firstly, we introduce an approach for developing lexico-syntactic patterns automatically using the snippets of search engine results and then, challenge the law recall of this approach using a combined model, which is based on cooccurrence of pair words in the web and neural network classifier. Using our approach both precision and recall of extracted 'is-a' relations improved and FMeasure value reaches 0.72.

Original languageEnglish
Title of host publicationCommunications in Computer and Information Science
Pages17-24
Number of pages8
Volume6 CCIS
DOIs
Publication statusPublished - 1 Dec 2008
Event13th International Computer Society of Iran Computer Conference on Advances in Computer Science and Engineering, CSICC 2008 - Kish Island
Duration: 9 Mar 200811 Mar 2008

Publication series

NameCommunications in Computer and Information Science
Volume6 CCIS
ISSN (Print)18650929

Other

Other13th International Computer Society of Iran Computer Conference on Advances in Computer Science and Engineering, CSICC 2008
CityKish Island
Period9/3/0811/3/08

Fingerprint

Taxonomies
Syntactics
Search engines
Ontology
Classifiers
Neural networks

Keywords

  • Ontology Engineering
  • Semantic Web
  • Taxonomy Learning

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Neshati, M., Abolhassani, H., & Fatemi, H. (2008). Automatic extraction of is-a relations in taxonomy learning. In Communications in Computer and Information Science (Vol. 6 CCIS, pp. 17-24). (Communications in Computer and Information Science; Vol. 6 CCIS). https://doi.org/10.1007/978-3-540-89985-3_3

Automatic extraction of is-a relations in taxonomy learning. / Neshati, Mahmood; Abolhassani, Hassan; Fatemi, Hassan.

Communications in Computer and Information Science. Vol. 6 CCIS 2008. p. 17-24 (Communications in Computer and Information Science; Vol. 6 CCIS).

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

Neshati, M, Abolhassani, H & Fatemi, H 2008, Automatic extraction of is-a relations in taxonomy learning. in Communications in Computer and Information Science. vol. 6 CCIS, Communications in Computer and Information Science, vol. 6 CCIS, pp. 17-24, 13th International Computer Society of Iran Computer Conference on Advances in Computer Science and Engineering, CSICC 2008, Kish Island, 9/3/08. https://doi.org/10.1007/978-3-540-89985-3_3
Neshati M, Abolhassani H, Fatemi H. Automatic extraction of is-a relations in taxonomy learning. In Communications in Computer and Information Science. Vol. 6 CCIS. 2008. p. 17-24. (Communications in Computer and Information Science). https://doi.org/10.1007/978-3-540-89985-3_3
Neshati, Mahmood ; Abolhassani, Hassan ; Fatemi, Hassan. / Automatic extraction of is-a relations in taxonomy learning. Communications in Computer and Information Science. Vol. 6 CCIS 2008. pp. 17-24 (Communications in Computer and Information Science).
@inproceedings{26c93dd401714c278e1bc9e58e47a0b1,
title = "Automatic extraction of is-a relations in taxonomy learning",
abstract = "Taxonomy learning is a prerequisite step for ontology learning. In order to create a taxonomy, first of all, existing 'is-a' relations between words should be extracted. A known way to extract 'is-a' relations is finding lexicosyntactic patterns in large text corpus. Although this approach produces results with high precision but it suffers from low values of recall. Furthermore developing a comprehensive set of patterns is tedious and cumbersome. In this paper, firstly, we introduce an approach for developing lexico-syntactic patterns automatically using the snippets of search engine results and then, challenge the law recall of this approach using a combined model, which is based on cooccurrence of pair words in the web and neural network classifier. Using our approach both precision and recall of extracted 'is-a' relations improved and FMeasure value reaches 0.72.",
keywords = "Ontology Engineering, Semantic Web, Taxonomy Learning",
author = "Mahmood Neshati and Hassan Abolhassani and Hassan Fatemi",
year = "2008",
month = "12",
day = "1",
doi = "10.1007/978-3-540-89985-3_3",
language = "English",
isbn = "3540899847",
volume = "6 CCIS",
series = "Communications in Computer and Information Science",
pages = "17--24",
booktitle = "Communications in Computer and Information Science",

}

TY - GEN

T1 - Automatic extraction of is-a relations in taxonomy learning

AU - Neshati, Mahmood

AU - Abolhassani, Hassan

AU - Fatemi, Hassan

PY - 2008/12/1

Y1 - 2008/12/1

N2 - Taxonomy learning is a prerequisite step for ontology learning. In order to create a taxonomy, first of all, existing 'is-a' relations between words should be extracted. A known way to extract 'is-a' relations is finding lexicosyntactic patterns in large text corpus. Although this approach produces results with high precision but it suffers from low values of recall. Furthermore developing a comprehensive set of patterns is tedious and cumbersome. In this paper, firstly, we introduce an approach for developing lexico-syntactic patterns automatically using the snippets of search engine results and then, challenge the law recall of this approach using a combined model, which is based on cooccurrence of pair words in the web and neural network classifier. Using our approach both precision and recall of extracted 'is-a' relations improved and FMeasure value reaches 0.72.

AB - Taxonomy learning is a prerequisite step for ontology learning. In order to create a taxonomy, first of all, existing 'is-a' relations between words should be extracted. A known way to extract 'is-a' relations is finding lexicosyntactic patterns in large text corpus. Although this approach produces results with high precision but it suffers from low values of recall. Furthermore developing a comprehensive set of patterns is tedious and cumbersome. In this paper, firstly, we introduce an approach for developing lexico-syntactic patterns automatically using the snippets of search engine results and then, challenge the law recall of this approach using a combined model, which is based on cooccurrence of pair words in the web and neural network classifier. Using our approach both precision and recall of extracted 'is-a' relations improved and FMeasure value reaches 0.72.

KW - Ontology Engineering

KW - Semantic Web

KW - Taxonomy Learning

UR - http://www.scopus.com/inward/record.url?scp=78449264178&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78449264178&partnerID=8YFLogxK

U2 - 10.1007/978-3-540-89985-3_3

DO - 10.1007/978-3-540-89985-3_3

M3 - Conference contribution

SN - 3540899847

SN - 9783540899846

VL - 6 CCIS

T3 - Communications in Computer and Information Science

SP - 17

EP - 24

BT - Communications in Computer and Information Science

ER -