A model for ranking sentence pairs in parallel corpora

Author

Chen, Yi-Dong ; Shi, Xiao-Dong ; Zhou, Chang-Le ; Hong, Qing-Yang

Author_Institution

Dept. of Comput. Sci., Xiamen Univ., China

Volume

6

fYear

2005

fDate

18-21 Aug. 2005

Firstpage

3820

Abstract

In this paper, the problem of ranking sentence pairs in parallel corpora was addressed for the first time. To solve this problem, a novel model was proposed. In this model, both syntax features and semantics features of sentence pairs are considered. Since most today´s statistical machine translation models depend on word alignment, features related to word alignment information are also included. Two experiments were carried out and the results showed that the model had promising performance.

Keywords

language translation; learning (artificial intelligence); statistical analysis; word processing; parallel corpora; sentence pair ranking; sentence pair semantics features; sentence pair syntax features; statistical machine translation model; word alignment; Computer science; Concurrent computing; Cybernetics; Large-scale systems; Machine learning; Statistical analysis; Surface-mount technology; Ranking; corpus revision; parallel corpora; statistical machine translation;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics, 2005. Proceedings of 2005 International Conference on

Conference_Location

Guangzhou, China

Print_ISBN

0-7803-9091-1

Type

conf

DOI

10.1109/ICMLC.2005.1527605

Filename

1527605