@inproceedings{8f56c58f48c14006ad436662ed9d0bf9,
title = "A hybrid sentence splitting method by comma insertion for machine translation with CRF",
abstract = "When writing formal articles many English writers often use long sentences with few punctuation marks. Since long sentences bring difficulty to machine translation systems, many researchers try to split them using punctuation marks before translation. But dealing with sentences with few punctuation marks is still intractable. In this paper we use a log linear model to insert commas into proper positions to split long sentence, trying to shorten the length of sub-sentence and benefit to machine translation. Experiment results show that our method can reasonably segment long sentences, and improve the quality of machine translation.",
author = "Shuli Yang and Chong Feng and Heyan Huang",
note = "Publisher Copyright: {\textcopyright} Springer International Publishing Switzerland 2015.; 14th China National Conference on Chinese Computational Linguistics, CCL 2015 and 3rd International Symposium on Natural Language Processing Based on Naturally Annotated Big Data, NLP-NABD 2015 ; Conference date: 13-11-2015 Through 14-11-2015",
year = "2015",
doi = "10.1007/978-3-319-25816-4\_12",
language = "English",
isbn = "9783319258157",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "141--152",
editor = "Maosong Sun and Zhiyuan Liu and Yang Liu and Min Zhang",
booktitle = "Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data - 14th China National Conference, CCL 2015 and 3rd International Symposium, NLP-NABD 2015, Proceedings",
address = "Germany",
}