Chinese morphological analysis with character-level POS tagging

Mo Shen, Hongxiao Liu, Daisuke Kawahara, Sadao Kurohashi

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

9 Citations (Scopus)

Abstract

The focus of recent studies on Chinese word segmentation, part-of-speech (POS) tagging and parsing has been shifting from words to characters. However, existing methods have not yet fully utilized the potentials of Chinese characters. In this paper, we investigate the usefulness of character-level part-of-speech in the task of Chinese morphological analysis. We propose the first tagset designed for the task of character-level POS tagging. We propose a method that performs character-level POS tagging jointly with word segmentation and word-level POS tagging. Through experiments, we demonstrate that by introducing character-level POS information, the performance of a baseline morphological analyzer can be significantly improved.

Original languageEnglish
Title of host publicationLong Papers
PublisherAssociation for Computational Linguistics (ACL)
Pages253-258
Number of pages6
Volume2
ISBN (Print)9781937284732
Publication statusPublished - Jan 1 2014
Event52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Baltimore, MD, United States
Duration: Jun 22 2014Jun 27 2014

Other

Other52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014
CountryUnited States
CityBaltimore, MD
Period6/22/146/27/14

Fingerprint

Experiments

Cite this

Shen, M., Liu, H., Kawahara, D., & Kurohashi, S. (2014). Chinese morphological analysis with character-level POS tagging. In Long Papers (Vol. 2, pp. 253-258). Association for Computational Linguistics (ACL).

Chinese morphological analysis with character-level POS tagging. / Shen, Mo; Liu, Hongxiao; Kawahara, Daisuke; Kurohashi, Sadao.

Long Papers. Vol. 2 Association for Computational Linguistics (ACL), 2014. p. 253-258.

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

Shen, M, Liu, H, Kawahara, D & Kurohashi, S 2014, Chinese morphological analysis with character-level POS tagging. in Long Papers. vol. 2, Association for Computational Linguistics (ACL), pp. 253-258, 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014, Baltimore, MD, United States, 6/22/14.
Shen M, Liu H, Kawahara D, Kurohashi S. Chinese morphological analysis with character-level POS tagging. In Long Papers. Vol. 2. Association for Computational Linguistics (ACL). 2014. p. 253-258
Shen, Mo ; Liu, Hongxiao ; Kawahara, Daisuke ; Kurohashi, Sadao. / Chinese morphological analysis with character-level POS tagging. Long Papers. Vol. 2 Association for Computational Linguistics (ACL), 2014. pp. 253-258
@inproceedings{a16ecb6390b94e42a4be7cf6c7b85d6b,
title = "Chinese morphological analysis with character-level POS tagging",
abstract = "The focus of recent studies on Chinese word segmentation, part-of-speech (POS) tagging and parsing has been shifting from words to characters. However, existing methods have not yet fully utilized the potentials of Chinese characters. In this paper, we investigate the usefulness of character-level part-of-speech in the task of Chinese morphological analysis. We propose the first tagset designed for the task of character-level POS tagging. We propose a method that performs character-level POS tagging jointly with word segmentation and word-level POS tagging. Through experiments, we demonstrate that by introducing character-level POS information, the performance of a baseline morphological analyzer can be significantly improved.",
author = "Mo Shen and Hongxiao Liu and Daisuke Kawahara and Sadao Kurohashi",
year = "2014",
month = "1",
day = "1",
language = "English",
isbn = "9781937284732",
volume = "2",
pages = "253--258",
booktitle = "Long Papers",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Chinese morphological analysis with character-level POS tagging

AU - Shen, Mo

AU - Liu, Hongxiao

AU - Kawahara, Daisuke

AU - Kurohashi, Sadao

PY - 2014/1/1

Y1 - 2014/1/1

N2 - The focus of recent studies on Chinese word segmentation, part-of-speech (POS) tagging and parsing has been shifting from words to characters. However, existing methods have not yet fully utilized the potentials of Chinese characters. In this paper, we investigate the usefulness of character-level part-of-speech in the task of Chinese morphological analysis. We propose the first tagset designed for the task of character-level POS tagging. We propose a method that performs character-level POS tagging jointly with word segmentation and word-level POS tagging. Through experiments, we demonstrate that by introducing character-level POS information, the performance of a baseline morphological analyzer can be significantly improved.

AB - The focus of recent studies on Chinese word segmentation, part-of-speech (POS) tagging and parsing has been shifting from words to characters. However, existing methods have not yet fully utilized the potentials of Chinese characters. In this paper, we investigate the usefulness of character-level part-of-speech in the task of Chinese morphological analysis. We propose the first tagset designed for the task of character-level POS tagging. We propose a method that performs character-level POS tagging jointly with word segmentation and word-level POS tagging. Through experiments, we demonstrate that by introducing character-level POS information, the performance of a baseline morphological analyzer can be significantly improved.

UR - http://www.scopus.com/inward/record.url?scp=84906932783&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84906932783&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84906932783

SN - 9781937284732

VL - 2

SP - 253

EP - 258

BT - Long Papers

PB - Association for Computational Linguistics (ACL)

ER -