A statistical approach for universal networking language-based relation extraction

Dat P T Nguyen, Mitsuru Ishizuka

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

5 Citations (Scopus)

Abstract

In the effort to enrich available information with machine-processable semantics, Universal Networking Language (UNL) was defined as an artificial intelligent language that is able to represent information and knowledge described in natural languages. One of the main components of UNL is a set of binary relations that represents semantic relationships between concepts in sentences. To provide machine-processable semantics for computers, extraction of such semantic relationships from natural language text is a must. In this paper, we present a method to solve the problem of UNL semantic relation extraction in English sentences. With the assumption that the positions of phrases in a sentence between which there exists a relation have been identified, we focus on the problem of classifying the relation between the given phrases. The UNL relation classifier was developed by using statistical techniques applied on several lexical and syntactic features. In addition to the common used features, we also propose a new feature that reflects the actual semantic relation of two phrases independent on words in the between. Using our new feature in this problem gives the preliminary results that have shown the promising advantages of the feature in some other semantic relation recognition tasks. The evaluation on dataset supplied by UNDL organization shows that our system obtained the result at about 79% accuracy.

Original languageEnglish
Title of host publicationProceedings of the 4th IEEE International Conference on Research, Innovation and Vision for the Future, RIVF'06
Pages153-160
Number of pages8
DOIs
Publication statusPublished - 2006
Externally publishedYes
Event4th IEEE International Conference on Research, Innovation and Vision for the Future, RIVF'06 - Ho Chi Minh City
Duration: 2006 Feb 122006 Feb 16

Other

Other4th IEEE International Conference on Research, Innovation and Vision for the Future, RIVF'06
CityHo Chi Minh City
Period06/2/1206/2/16

Fingerprint

Semantics
Syntactics
Classifiers

Keywords

  • Semantic relation classification
  • Semantic relation extraction
  • Universal networking language

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Nguyen, D. P. T., & Ishizuka, M. (2006). A statistical approach for universal networking language-based relation extraction. In Proceedings of the 4th IEEE International Conference on Research, Innovation and Vision for the Future, RIVF'06 (pp. 153-160). [1696432] https://doi.org/10.1109/RIVF.2006.1696432

A statistical approach for universal networking language-based relation extraction. / Nguyen, Dat P T; Ishizuka, Mitsuru.

Proceedings of the 4th IEEE International Conference on Research, Innovation and Vision for the Future, RIVF'06. 2006. p. 153-160 1696432.

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

Nguyen, DPT & Ishizuka, M 2006, A statistical approach for universal networking language-based relation extraction. in Proceedings of the 4th IEEE International Conference on Research, Innovation and Vision for the Future, RIVF'06., 1696432, pp. 153-160, 4th IEEE International Conference on Research, Innovation and Vision for the Future, RIVF'06, Ho Chi Minh City, 06/2/12. https://doi.org/10.1109/RIVF.2006.1696432
Nguyen DPT, Ishizuka M. A statistical approach for universal networking language-based relation extraction. In Proceedings of the 4th IEEE International Conference on Research, Innovation and Vision for the Future, RIVF'06. 2006. p. 153-160. 1696432 https://doi.org/10.1109/RIVF.2006.1696432
Nguyen, Dat P T ; Ishizuka, Mitsuru. / A statistical approach for universal networking language-based relation extraction. Proceedings of the 4th IEEE International Conference on Research, Innovation and Vision for the Future, RIVF'06. 2006. pp. 153-160
@inproceedings{d1f2f3f8bc6945af8edc8af3b7a3beaf,
title = "A statistical approach for universal networking language-based relation extraction",
abstract = "In the effort to enrich available information with machine-processable semantics, Universal Networking Language (UNL) was defined as an artificial intelligent language that is able to represent information and knowledge described in natural languages. One of the main components of UNL is a set of binary relations that represents semantic relationships between concepts in sentences. To provide machine-processable semantics for computers, extraction of such semantic relationships from natural language text is a must. In this paper, we present a method to solve the problem of UNL semantic relation extraction in English sentences. With the assumption that the positions of phrases in a sentence between which there exists a relation have been identified, we focus on the problem of classifying the relation between the given phrases. The UNL relation classifier was developed by using statistical techniques applied on several lexical and syntactic features. In addition to the common used features, we also propose a new feature that reflects the actual semantic relation of two phrases independent on words in the between. Using our new feature in this problem gives the preliminary results that have shown the promising advantages of the feature in some other semantic relation recognition tasks. The evaluation on dataset supplied by UNDL organization shows that our system obtained the result at about 79{\%} accuracy.",
keywords = "Semantic relation classification, Semantic relation extraction, Universal networking language",
author = "Nguyen, {Dat P T} and Mitsuru Ishizuka",
year = "2006",
doi = "10.1109/RIVF.2006.1696432",
language = "English",
isbn = "1424403162",
pages = "153--160",
booktitle = "Proceedings of the 4th IEEE International Conference on Research, Innovation and Vision for the Future, RIVF'06",

}

TY - GEN

T1 - A statistical approach for universal networking language-based relation extraction

AU - Nguyen, Dat P T

AU - Ishizuka, Mitsuru

PY - 2006

Y1 - 2006

N2 - In the effort to enrich available information with machine-processable semantics, Universal Networking Language (UNL) was defined as an artificial intelligent language that is able to represent information and knowledge described in natural languages. One of the main components of UNL is a set of binary relations that represents semantic relationships between concepts in sentences. To provide machine-processable semantics for computers, extraction of such semantic relationships from natural language text is a must. In this paper, we present a method to solve the problem of UNL semantic relation extraction in English sentences. With the assumption that the positions of phrases in a sentence between which there exists a relation have been identified, we focus on the problem of classifying the relation between the given phrases. The UNL relation classifier was developed by using statistical techniques applied on several lexical and syntactic features. In addition to the common used features, we also propose a new feature that reflects the actual semantic relation of two phrases independent on words in the between. Using our new feature in this problem gives the preliminary results that have shown the promising advantages of the feature in some other semantic relation recognition tasks. The evaluation on dataset supplied by UNDL organization shows that our system obtained the result at about 79% accuracy.

AB - In the effort to enrich available information with machine-processable semantics, Universal Networking Language (UNL) was defined as an artificial intelligent language that is able to represent information and knowledge described in natural languages. One of the main components of UNL is a set of binary relations that represents semantic relationships between concepts in sentences. To provide machine-processable semantics for computers, extraction of such semantic relationships from natural language text is a must. In this paper, we present a method to solve the problem of UNL semantic relation extraction in English sentences. With the assumption that the positions of phrases in a sentence between which there exists a relation have been identified, we focus on the problem of classifying the relation between the given phrases. The UNL relation classifier was developed by using statistical techniques applied on several lexical and syntactic features. In addition to the common used features, we also propose a new feature that reflects the actual semantic relation of two phrases independent on words in the between. Using our new feature in this problem gives the preliminary results that have shown the promising advantages of the feature in some other semantic relation recognition tasks. The evaluation on dataset supplied by UNDL organization shows that our system obtained the result at about 79% accuracy.

KW - Semantic relation classification

KW - Semantic relation extraction

KW - Universal networking language

UR - http://www.scopus.com/inward/record.url?scp=34250709162&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34250709162&partnerID=8YFLogxK

U2 - 10.1109/RIVF.2006.1696432

DO - 10.1109/RIVF.2006.1696432

M3 - Conference contribution

SN - 1424403162

SN - 9781424403165

SP - 153

EP - 160

BT - Proceedings of the 4th IEEE International Conference on Research, Innovation and Vision for the Future, RIVF'06

ER -