@inproceedings{55910729ad3f4716b68bfc6325ae1296,
title = "Pseudo-word for phrase-based machine translation",
abstract = "The pipeline of most Phrase-Based Statistical Machine Translation (PB-SMT) systems starts from automatically word aligned parallel corpus. But word appears to be too fine-grained in some cases such as non-compositional phrasal equivalences, where no clear word alignments exist. Using words as inputs to PBSMT pipeline has inborn deficiency. This paper proposes pseudo-word as a new start point for PB-SMT pipeline. Pseudo-word is a kind of basic multi-word expression that characterizes minimal sequence of consecutive words in sense of translation. By casting pseudo-word searching problem into a parsing framework, we search for pseudo-words in a monolingual way and a bilingual synchronous way. Experiments show that pseudo-word significantly outperforms word for PB-SMT model in both travel translation domain and news translation domain.",
author = "Xiangyu Duan and Min Zhang and Haizhou Li",
year = "2010",
language = "英语",
isbn = "9781617388088",
series = "ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",
pages = "148--156",
booktitle = "ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",
note = "48th Annual Meeting of the Association for Computational Linguistics, ACL 2010 ; Conference date: 11-07-2010 Through 16-07-2010",
}