@inproceedings{454bcd1c7b68454287dd712944b37803,
title = "Phrasal syntactic category sequence model for phrase-based MT",
abstract = "Incorporating target syntax into phrase-based machine translation (PBMT) can generate syntactically well-formed translations. We propose a novel phrasal syntactic category sequence (PSCS) model which allows a PBMT decoder to prefer more grammatical translations. We parse all the sentences on the target side of the bilingual training corpus. In the standard phrase pair extraction procedure, we assign a syntactic category to each phrase pair and build a PSCS model from the parallel training data. Then, we log linearly incorporate the PSCS model into a standard PBMT system. Our method is very simple and yields a 0.7 BLEU point improvement when compared to the baseline PBMT system.",
keywords = "machine translation, natural language processing, phrase-based machine translation",
author = "Hailong Cao and Eiichiro Sumita and Tiejun Zhao and Sheng Li",
year = "2012",
doi = "10.1007/978-3-642-28601-8\_5",
language = "英语",
isbn = "9783642286001",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
number = "PART 2",
pages = "52--59",
booktitle = "Computational Linguistics and Intelligent Text Processing - 13th International Conference, CICLing 2012, Proceedings",
address = "德国",
edition = "PART 2",
note = "13th Annual Conference on Intelligent Text Processing and Computational Linguistics, CICLing 2012 ; Conference date: 11-03-2012 Through 17-03-2012",
}