Bilingual semantic network construction

Authors:
Jianyong Duan;Yi Hu;Ruzhan Lu;Yan Tian;Hui Liu
Affiliations:
Department of computer science and engineering, Shanghai Jiaotong University, Shanghai, P.R. China;Department of computer science and engineering, Shanghai Jiaotong University, Shanghai, P.R. China;Department of computer science and engineering, Shanghai Jiaotong University, Shanghai, P.R. China;Department of computer science and engineering, Shanghai Jiaotong University, Shanghai, P.R. China;Department of computer science and engineering, Shanghai Jiaotong University, Shanghai, P.R. China
Venue:
ICIC'05 Proceedings of the 2005 international conference on Advances in Intelligent Computing - Volume Part II
Year:
2005

Citing 5
Cited 0

Building a Chinese-English wordnet for translingual applications

ACM Transactions on Asian Language Information Processing (TALIP)
A class-based approach to word alignment

Computational Linguistics
Word translation disambiguation using bilingual bootstrapping

Computational Linguistics
Self-organizing Chinese and Japanese semantic maps

COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
An unsupervised method for multilingual word sense tagging using parallel corpora: a preliminary investigation

WorkSense '00 Proceedings of the ACL-2000 Workshop on Word Senses and Multi-Linguality

Quantified Score

Hi-index	0.00

Visualization

Abstract

This article proposes a neural network for building Chinese and English semantic resources connection. Abundant monolingual semantic information is stored into its bipartite graph structure respectively. Two hidden layers are also set in every part, word layer and concept layer. Every word associates with different concepts separately; every concept includes different vocabularies; and these two layers also independently connect to their counterparts through bipartite graph. These distributed characteristics in hidden layers meet the need of parallel network computing. The unsupervised method is used to train the network, and samples are translation lexicons, results of the bilingual word-level alignment algorithm. The training principle comes from the inspiration of bilingual semantic asymmetry. Every translational equivalent contains the unambiguous information by comparison between source and target languages. These translation lexicons are viewed as a kind of special context. They almost have definite meaning. Every input will activate and suppress various kinds of potential connections by the interaction of hidden layers, and modify their connective weights. Finally a demo test presents.