A lexical knowledge acquisition model using unsupervised learning method

Doo Soon Park, Wonhee Yu, Kinam Park, Heui Seok Lim

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

Abstract

This paper proposes a computational lexical entry acquisition model based on a representation model of the mental lexicon. The proposed model acquires lexical entries from a raw corpus by unsupervised learning like human. The model is composed of full-form and morpheme acquisition modules. We experimented the model with a Korean raw corpus of which size is about 16 million Korean full-forms. The experimental results show that the model successively acquires major Korean fullforms and morphemes with the average precision of 100% and 99.04%, respectively.

Original languageEnglish
Title of host publication2010 Proceedings of the 5th International Conference on Ubiquitous Information Technologies and Applications, CUTE 2010
DOIs
Publication statusPublished - 2010 Dec 1
Event5th International Conference on Ubiquitous Information Technologies and Applications, CUTE 2010 - Sanya, China
Duration: 2010 Dec 162010 Dec 18

Other

Other5th International Conference on Ubiquitous Information Technologies and Applications, CUTE 2010
CountryChina
CitySanya
Period10/12/1610/12/18

Fingerprint

Unsupervised learning
Knowledge acquisition

Keywords

  • Lexical acquisition
  • Lexical entry
  • Unsupervised learning

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems

Cite this

Park, D. S., Yu, W., Park, K., & Lim, H. S. (2010). A lexical knowledge acquisition model using unsupervised learning method. In 2010 Proceedings of the 5th International Conference on Ubiquitous Information Technologies and Applications, CUTE 2010 [5678174] https://doi.org/10.1109/ICUT.2010.5678174

A lexical knowledge acquisition model using unsupervised learning method. / Park, Doo Soon; Yu, Wonhee; Park, Kinam; Lim, Heui Seok.

2010 Proceedings of the 5th International Conference on Ubiquitous Information Technologies and Applications, CUTE 2010. 2010. 5678174.

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

Park, DS, Yu, W, Park, K & Lim, HS 2010, A lexical knowledge acquisition model using unsupervised learning method. in 2010 Proceedings of the 5th International Conference on Ubiquitous Information Technologies and Applications, CUTE 2010., 5678174, 5th International Conference on Ubiquitous Information Technologies and Applications, CUTE 2010, Sanya, China, 10/12/16. https://doi.org/10.1109/ICUT.2010.5678174
Park DS, Yu W, Park K, Lim HS. A lexical knowledge acquisition model using unsupervised learning method. In 2010 Proceedings of the 5th International Conference on Ubiquitous Information Technologies and Applications, CUTE 2010. 2010. 5678174 https://doi.org/10.1109/ICUT.2010.5678174
Park, Doo Soon ; Yu, Wonhee ; Park, Kinam ; Lim, Heui Seok. / A lexical knowledge acquisition model using unsupervised learning method. 2010 Proceedings of the 5th International Conference on Ubiquitous Information Technologies and Applications, CUTE 2010. 2010.
@inproceedings{f35e7ebe9d4e4d4fb3c7770c7bbff0cd,
title = "A lexical knowledge acquisition model using unsupervised learning method",
abstract = "This paper proposes a computational lexical entry acquisition model based on a representation model of the mental lexicon. The proposed model acquires lexical entries from a raw corpus by unsupervised learning like human. The model is composed of full-form and morpheme acquisition modules. We experimented the model with a Korean raw corpus of which size is about 16 million Korean full-forms. The experimental results show that the model successively acquires major Korean fullforms and morphemes with the average precision of 100{\%} and 99.04{\%}, respectively.",
keywords = "Lexical acquisition, Lexical entry, Unsupervised learning",
author = "Park, {Doo Soon} and Wonhee Yu and Kinam Park and Lim, {Heui Seok}",
year = "2010",
month = "12",
day = "1",
doi = "10.1109/ICUT.2010.5678174",
language = "English",
isbn = "9781424488124",
booktitle = "2010 Proceedings of the 5th International Conference on Ubiquitous Information Technologies and Applications, CUTE 2010",

}

TY - GEN

T1 - A lexical knowledge acquisition model using unsupervised learning method

AU - Park, Doo Soon

AU - Yu, Wonhee

AU - Park, Kinam

AU - Lim, Heui Seok

PY - 2010/12/1

Y1 - 2010/12/1

N2 - This paper proposes a computational lexical entry acquisition model based on a representation model of the mental lexicon. The proposed model acquires lexical entries from a raw corpus by unsupervised learning like human. The model is composed of full-form and morpheme acquisition modules. We experimented the model with a Korean raw corpus of which size is about 16 million Korean full-forms. The experimental results show that the model successively acquires major Korean fullforms and morphemes with the average precision of 100% and 99.04%, respectively.

AB - This paper proposes a computational lexical entry acquisition model based on a representation model of the mental lexicon. The proposed model acquires lexical entries from a raw corpus by unsupervised learning like human. The model is composed of full-form and morpheme acquisition modules. We experimented the model with a Korean raw corpus of which size is about 16 million Korean full-forms. The experimental results show that the model successively acquires major Korean fullforms and morphemes with the average precision of 100% and 99.04%, respectively.

KW - Lexical acquisition

KW - Lexical entry

KW - Unsupervised learning

UR - http://www.scopus.com/inward/record.url?scp=78751687565&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78751687565&partnerID=8YFLogxK

U2 - 10.1109/ICUT.2010.5678174

DO - 10.1109/ICUT.2010.5678174

M3 - Conference contribution

SN - 9781424488124

BT - 2010 Proceedings of the 5th International Conference on Ubiquitous Information Technologies and Applications, CUTE 2010

ER -