Cross-lingual conversion of lexical semantic relations: Building parallel wordnets

Chu Ren Huang; I. Li Su; Jia Fei Hong; Xiang Bing Li

Cross-lingual conversion of lexical semantic relations: Building parallel wordnets

Chu Ren Huang, I. Li Su, Jia Fei Hong, Xiang Bing Li

Research output: Contribution to conference › Paper › peer-review

Abstract

Parallel wordnets built upon correspondences between different languages can play a crucial role in multilingual knowledge processing. Since there is no homomorphism between pairs of monolingual wordnets, we must rely on lexical semantic relation (LSR) mappings to ensure conceptual cohesion. In this paper, we propose and implement a model for bootstrapping parallel wordnets based on one monolingual wordnet and a set of cross-lingual lexical semantic relations. In particular, we propose a set of inference rules to predict Chinese wordnet structure based on English wordnet and English-Chinese translation relations. We show that this model of parallel wordnet building is effective and achieves higher precision in LSR prediction.

Original language	English
Pages	48-55
Number of pages	8
Publication status	Published - 2005
Externally published	Yes
Event	5th Workshop on Asian Language Resources, ALR 2005 and 1st Symposium on Asian Language Resources Network, ALRN 2005 - Jeju Island, Korea, Republic of Duration: 2005 Oct 14 → …

Conference

Conference	5th Workshop on Asian Language Resources, ALR 2005 and 1st Symposium on Asian Language Resources Network, ALRN 2005
Country/Territory	Korea, Republic of
City	Jeju Island
Period	2005/10/14 → …

ASJC Scopus subject areas

Artificial Intelligence
Computer Vision and Pattern Recognition
Signal Processing
Linguistics and Language

Cite this

Cross-lingual conversion of lexical semantic relations: Building parallel wordnets. / Huang, Chu Ren; Su, I. Li; Hong, Jia Fei et al.
2005. 48-55 Paper presented at 5th Workshop on Asian Language Resources, ALR 2005 and 1st Symposium on Asian Language Resources Network, ALRN 2005, Jeju Island, Korea, Republic of.

Research output: Contribution to conference › Paper › peer-review

@conference{7195b90945ab436b8f0449d50c349d14,

title = "Cross-lingual conversion of lexical semantic relations: Building parallel wordnets",

abstract = "Parallel wordnets built upon correspondences between different languages can play a crucial role in multilingual knowledge processing. Since there is no homomorphism between pairs of monolingual wordnets, we must rely on lexical semantic relation (LSR) mappings to ensure conceptual cohesion. In this paper, we propose and implement a model for bootstrapping parallel wordnets based on one monolingual wordnet and a set of cross-lingual lexical semantic relations. In particular, we propose a set of inference rules to predict Chinese wordnet structure based on English wordnet and English-Chinese translation relations. We show that this model of parallel wordnet building is effective and achieves higher precision in LSR prediction.",

author = "Huang, {Chu Ren} and Su, {I. Li} and Hong, {Jia Fei} and Li, {Xiang Bing}",

note = "Publisher Copyright: {\textcopyright} 2005 5th Workshop on Asian Language Resources, ALR 2005 and 1st Symposium on Asian Language Resources Network, ALRN 2005 - Proceedings. All rights reserved.; 5th Workshop on Asian Language Resources, ALR 2005 and 1st Symposium on Asian Language Resources Network, ALRN 2005 ; Conference date: 14-10-2005",

year = "2005",

language = "English",

pages = "48--55",

}

TY - CONF

T1 - Cross-lingual conversion of lexical semantic relations

T2 - 5th Workshop on Asian Language Resources, ALR 2005 and 1st Symposium on Asian Language Resources Network, ALRN 2005

AU - Huang, Chu Ren

AU - Su, I. Li

AU - Hong, Jia Fei

AU - Li, Xiang Bing

PY - 2005

Y1 - 2005

N2 - Parallel wordnets built upon correspondences between different languages can play a crucial role in multilingual knowledge processing. Since there is no homomorphism between pairs of monolingual wordnets, we must rely on lexical semantic relation (LSR) mappings to ensure conceptual cohesion. In this paper, we propose and implement a model for bootstrapping parallel wordnets based on one monolingual wordnet and a set of cross-lingual lexical semantic relations. In particular, we propose a set of inference rules to predict Chinese wordnet structure based on English wordnet and English-Chinese translation relations. We show that this model of parallel wordnet building is effective and achieves higher precision in LSR prediction.

AB - Parallel wordnets built upon correspondences between different languages can play a crucial role in multilingual knowledge processing. Since there is no homomorphism between pairs of monolingual wordnets, we must rely on lexical semantic relation (LSR) mappings to ensure conceptual cohesion. In this paper, we propose and implement a model for bootstrapping parallel wordnets based on one monolingual wordnet and a set of cross-lingual lexical semantic relations. In particular, we propose a set of inference rules to predict Chinese wordnet structure based on English wordnet and English-Chinese translation relations. We show that this model of parallel wordnet building is effective and achieves higher precision in LSR prediction.

UR - http://www.scopus.com/inward/record.url?scp=85117683835&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85117683835&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85117683835

SP - 48

EP - 55

Y2 - 14 October 2005

ER -

Cross-lingual conversion of lexical semantic relations: Building parallel wordnets

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this