Classification-based Chinese collocation extraction

Ruifeng Xu; Qin Lu; Kam Fai Wong; Wenjie Li

doi:10.1109/NLPKE.2007.4368048

Classification-based Chinese collocation extraction

Ruifeng Xu, Qin Lu, Kam Fai Wong, Wenjie Li

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

5 Citations (Scopus)

Abstract

Most collocation extraction algorithms use a single set of criteria and a single threshold which is not quite appropriate because different types of collocations have different behaviors. This paper presents a window-based Chinese collocation extraction system, which identifies different types of collocations separately. By taking into consideration of compositional, non-substitutable, and non-modifiable properties as well as statistical significance, Chinese collocations are classified into four types. A multi-stage extraction system is then designed to separately identify different types of collocations by using different combinations of features. Furthermore, heuristic rules based on dependency knowledge are applied to filter out some pseudo collocations. Experiments show that the proposed system achieves better F1performance compared to most existing algorithms for Chinese collocation extraction.

Original language	English
Title of host publication	IEEE NLP-KE 2007 - Proceedings of International Conference on Natural Language Processing and Knowledge Engineering
Pages	308-315
Number of pages	8
DOIs	https://doi.org/10.1109/NLPKE.2007.4368048
Publication status	Published - 1 Dec 2007
Event	International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE 2007 - Beijing, China Duration: 30 Aug 2007 → 1 Sept 2007

Conference

Conference	International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE 2007
Country/Territory	China
City	Beijing
Period	30/08/07 → 1/09/07

ASJC Scopus subject areas

Computer Science Applications
Information Systems
Information Systems and Management

More information

10.1109/NLPKE.2007.4368048

Cite this

@inproceedings{a2febb0c7ea44b4f8ade0f5d23b0c1e0,

title = "Classification-based Chinese collocation extraction",

abstract = "Most collocation extraction algorithms use a single set of criteria and a single threshold which is not quite appropriate because different types of collocations have different behaviors. This paper presents a window-based Chinese collocation extraction system, which identifies different types of collocations separately. By taking into consideration of compositional, non-substitutable, and non-modifiable properties as well as statistical significance, Chinese collocations are classified into four types. A multi-stage extraction system is then designed to separately identify different types of collocations by using different combinations of features. Furthermore, heuristic rules based on dependency knowledge are applied to filter out some pseudo collocations. Experiments show that the proposed system achieves better F1performance compared to most existing algorithms for Chinese collocation extraction.",

author = "Ruifeng Xu and Qin Lu and Wong, {Kam Fai} and Wenjie Li",

year = "2007",

month = dec,

day = "1",

doi = "10.1109/NLPKE.2007.4368048",

language = "English",

isbn = "9781424416103",

pages = "308--315",

booktitle = "IEEE NLP-KE 2007 - Proceedings of International Conference on Natural Language Processing and Knowledge Engineering",

note = "International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE 2007 ; Conference date: 30-08-2007 Through 01-09-2007",

}

Xu, R, Lu, Q, Wong, KF & Li, W 2007, Classification-based Chinese collocation extraction. in IEEE NLP-KE 2007 - Proceedings of International Conference on Natural Language Processing and Knowledge Engineering., 4368048, pp. 308-315, International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE 2007, Beijing, China, 30/08/07. https://doi.org/10.1109/NLPKE.2007.4368048

Classification-based Chinese collocation extraction. / Xu, Ruifeng; Lu, Qin; Wong, Kam Fai et al.
IEEE NLP-KE 2007 - Proceedings of International Conference on Natural Language Processing and Knowledge Engineering. 2007. p. 308-315 4368048.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Classification-based Chinese collocation extraction

AU - Xu, Ruifeng

AU - Lu, Qin

AU - Wong, Kam Fai

AU - Li, Wenjie

PY - 2007/12/1

Y1 - 2007/12/1

N2 - Most collocation extraction algorithms use a single set of criteria and a single threshold which is not quite appropriate because different types of collocations have different behaviors. This paper presents a window-based Chinese collocation extraction system, which identifies different types of collocations separately. By taking into consideration of compositional, non-substitutable, and non-modifiable properties as well as statistical significance, Chinese collocations are classified into four types. A multi-stage extraction system is then designed to separately identify different types of collocations by using different combinations of features. Furthermore, heuristic rules based on dependency knowledge are applied to filter out some pseudo collocations. Experiments show that the proposed system achieves better F1performance compared to most existing algorithms for Chinese collocation extraction.

AB - Most collocation extraction algorithms use a single set of criteria and a single threshold which is not quite appropriate because different types of collocations have different behaviors. This paper presents a window-based Chinese collocation extraction system, which identifies different types of collocations separately. By taking into consideration of compositional, non-substitutable, and non-modifiable properties as well as statistical significance, Chinese collocations are classified into four types. A multi-stage extraction system is then designed to separately identify different types of collocations by using different combinations of features. Furthermore, heuristic rules based on dependency knowledge are applied to filter out some pseudo collocations. Experiments show that the proposed system achieves better F1performance compared to most existing algorithms for Chinese collocation extraction.

UR - http://www.scopus.com/inward/record.url?scp=47749119147&partnerID=8YFLogxK

U2 - 10.1109/NLPKE.2007.4368048

DO - 10.1109/NLPKE.2007.4368048

M3 - Conference article published in proceeding or book

SN - 9781424416103

SP - 308

EP - 315

BT - IEEE NLP-KE 2007 - Proceedings of International Conference on Natural Language Processing and Knowledge Engineering

T2 - International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE 2007

Y2 - 30 August 2007 through 1 September 2007

ER -

Classification-based Chinese collocation extraction

Abstract

Conference

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this