@inproceedings{175309fb7f37423089b30447f3c06834,
title = "Extracting parallel phrases from comparable corpora",
abstract = "The state-of-the-art statistical machine translation models are trained with the parallel corpora. However, the traditional SMT loses its power when it comes to language pairs with few bilingual resources. This paper proposes a novel method that treats the phrase extraction as a classification task. We first automatically generate the training and testing phrase pairs for the classifier. Then, we train a SVM classifier which can determine the phrase pairs are either parallel or non-parallel. The proposed approach is evaluated on the translation task of Chinese-English. Experimental results show that the precision of the classifier on test sets is above 70\% and the accuracy is above 98\% The quality of the extracted data is also evaluated by measuring the impact on the performance of a state-of-the-art SMT system, which is built with a small parallel corpus. It shows better results over the baseline system.",
keywords = "Statistical Machine Translation, Support Vector Machine, classification, comparable corpus",
author = "Jiexin Zhang and Hailong Cao and Tiejun Zhao",
note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; International Conference on Asian Language Processing 2014, IALP 2014 ; Conference date: 20-10-2014 Through 22-10-2014",
year = "2014",
month = dec,
day = "3",
doi = "10.1109/IALP.2014.6973501",
language = "英语",
series = "Proceedings of the International Conference on Asian Language Processing 2014, IALP 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "166--169",
editor = "Banchs, \{Rafael E.\} and Minghui Dong and Yanfeng Lu and Bali Ranaivo-Malancon",
booktitle = "Proceedings of the International Conference on Asian Language Processing 2014, IALP 2014",
address = "美国",
}