A Phrase Combination Approach to Patent SMT

DOI

10.2991/jcis.2008.99How to use a DOI?

Keywords

statistical machine translation, patent, phrase combination, word segmentation

Abstract

This paper presents a phrase combination approach to patent SMT (Statistical Ma-chine Translation) for Japanese to English. To minimize the segmentation problems caused by the rich OOV (out-of-vocabulary) words in the patent texts, the character based translation phrases are first introduced to avoid the segmentation errors in translation modeling. Then the word based translation phrases, which are established to utilize the dependent word level information, are combined with character translation table by linearly integrating their probability. Our experiments on NTCIR corpus indicate that the proposed method significantly out-performed the originally word based approach.

Copyright

© 2008, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Junguo Zhu
AU  - Muyun Yang
AU  - Tiejun Zhao
AU  - Sheng Li
AU  - Qi Haoliang
PY  - 2008/12
DA  - 2008/12
TI  - A Phrase Combination Approach to Patent SMT
BT  - Proceedings of the 11th Joint Conference on Information Sciences (JCIS 2008)
PB  - Atlantis Press
SP  - 590
EP  - 594
SN  - 1951-6851
UR  - https://doi.org/10.2991/jcis.2008.99
DO  - 10.2991/jcis.2008.99
ID  - Zhu2008/12
ER  -