A hybrid extraction model for chinese noun/verb synonym bi-gram collocations

Wanyin Li; Qin Lu

A hybrid extraction model for chinese noun/verb synonym bi-gram collocations

Wanyin Li
, Qin Lu

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

1 Citation (Scopus)

Abstract

Statistical-based collocation extraction approaches suffer from (1) low precision rate because high co-occurrence bi-grams may be syntactically unrelated and are thus not true collocations; (2) low recall rate because some true collocations with low occurrences cannot be identified successfully by statistical-based models. To integrate both syntactic rules as well as semantic knowledge into a statistical model for collocation extraction is one way to achieve a high precision while keeping a reasonable recall. This paper designs a cascade system which employs a hybrid model by integrating both syntactic and semantic knowledge into a statistical model for Chinese synonymous noun/verb collocations extraction. The grammatically bounded noun/verb collocations are extracted first from a syntactic-rule based module, which is then inputted to a semantic-based module for further retrieval of low frequent bi-gram collocations.

Original language	English
Title of host publication	PACLIC 25 - Proceedings of the 25th Pacific Asia Conference on Language, Information and Computation
Pages	430-439
Number of pages	10
Publication status	Published - 1 Dec 2011
Event	25th Pacific Asia Conference on Language, Information and Computation, PACLIC 25 - , Singapore Duration: 16 Dec 2011 → 18 Dec 2011

Conference

Conference	25th Pacific Asia Conference on Language, Information and Computation, PACLIC 25
Country/Territory	Singapore
Period	16/12/11 → 18/12/11

Keywords

Collocation extraction
Hownet
Semantic relationship
Similarity calculation
Statistical model
Syntactic rules

ASJC Scopus subject areas

Language and Linguistics
Computer Science (miscellaneous)

More information

http://hdl.handle.net/10397/5202

Cite this

@inproceedings{c1f19e5a202e47b4941efd0e9c5b1962,

title = "A hybrid extraction model for chinese noun/verb synonym bi-gram collocations",

abstract = "Statistical-based collocation extraction approaches suffer from (1) low precision rate because high co-occurrence bi-grams may be syntactically unrelated and are thus not true collocations; (2) low recall rate because some true collocations with low occurrences cannot be identified successfully by statistical-based models. To integrate both syntactic rules as well as semantic knowledge into a statistical model for collocation extraction is one way to achieve a high precision while keeping a reasonable recall. This paper designs a cascade system which employs a hybrid model by integrating both syntactic and semantic knowledge into a statistical model for Chinese synonymous noun/verb collocations extraction. The grammatically bounded noun/verb collocations are extracted first from a syntactic-rule based module, which is then inputted to a semantic-based module for further retrieval of low frequent bi-gram collocations.",

keywords = "Collocation extraction, Hownet, Semantic relationship, Similarity calculation, Statistical model, Syntactic rules",

author = "Wanyin Li and Qin Lu",

year = "2011",

month = dec,

day = "1",

language = "English",

isbn = "9784905166023",

pages = "430--439",

booktitle = "PACLIC 25 - Proceedings of the 25th Pacific Asia Conference on Language, Information and Computation",

note = "25th Pacific Asia Conference on Language, Information and Computation, PACLIC 25 ; Conference date: 16-12-2011 Through 18-12-2011",

}

TY - GEN

T1 - A hybrid extraction model for chinese noun/verb synonym bi-gram collocations

AU - Li, Wanyin

AU - Lu, Qin

PY - 2011/12/1

Y1 - 2011/12/1

N2 - Statistical-based collocation extraction approaches suffer from (1) low precision rate because high co-occurrence bi-grams may be syntactically unrelated and are thus not true collocations; (2) low recall rate because some true collocations with low occurrences cannot be identified successfully by statistical-based models. To integrate both syntactic rules as well as semantic knowledge into a statistical model for collocation extraction is one way to achieve a high precision while keeping a reasonable recall. This paper designs a cascade system which employs a hybrid model by integrating both syntactic and semantic knowledge into a statistical model for Chinese synonymous noun/verb collocations extraction. The grammatically bounded noun/verb collocations are extracted first from a syntactic-rule based module, which is then inputted to a semantic-based module for further retrieval of low frequent bi-gram collocations.

AB - Statistical-based collocation extraction approaches suffer from (1) low precision rate because high co-occurrence bi-grams may be syntactically unrelated and are thus not true collocations; (2) low recall rate because some true collocations with low occurrences cannot be identified successfully by statistical-based models. To integrate both syntactic rules as well as semantic knowledge into a statistical model for collocation extraction is one way to achieve a high precision while keeping a reasonable recall. This paper designs a cascade system which employs a hybrid model by integrating both syntactic and semantic knowledge into a statistical model for Chinese synonymous noun/verb collocations extraction. The grammatically bounded noun/verb collocations are extracted first from a syntactic-rule based module, which is then inputted to a semantic-based module for further retrieval of low frequent bi-gram collocations.

KW - Collocation extraction

KW - Hownet

KW - Semantic relationship

KW - Similarity calculation

KW - Statistical model

KW - Syntactic rules

UR - https://www.scopus.com/pages/publications/84863869937

M3 - Conference article published in proceeding or book

SN - 9784905166023

SP - 430

EP - 439

BT - PACLIC 25 - Proceedings of the 25th Pacific Asia Conference on Language, Information and Computation

T2 - 25th Pacific Asia Conference on Language, Information and Computation, PACLIC 25

Y2 - 16 December 2011 through 18 December 2011

ER -

A hybrid extraction model for chinese noun/verb synonym bi-gram collocations

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this