Integrating Multi-source Bilingual Information for Chinese Word Segmentation in Statistical Machine Translation

	Integrating Multi-source Bilingual Information for Chinese Word Segmentation in Statistical Machine Translation
	Chen W(陈炜); Wei W(韦玮); Chen ZB(陈振标); Xu B(徐波); Chen,Wei
	2013-10
会议名称	Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data.(CCL)
会议录名称	Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data.(CCL)
会议日期	2013-10
会议地点	Suzhou,China
摘要	Chinese texts are written without spaces between the words, which is problematic for Chinese-English statistical machine translation (SMT). The most widely used approach in existing SMT systems is apply a fixed segmentations produced by the off-the-shelf Chinese word segmentation (CWS) systems to train the standard translation model. Such approach is sub-optimal and unsuitable for SMT systems. We propose a joint model to integrate the multi-source bilingual information to optimize the segmentations in SMT. We also propose an unsupervised algorithm to improve the quality of the joint model iteratively. Experiments show that our method improve both segmentation and translation performance in different data environment.
关键词	Chinese Word Segmentation Bilingual Information Statistical Machine Translation
收录类别	EI
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/41230
专题	复杂系统认知与决策实验室_听觉模型与认知计算数字内容技术与服务研究中心
通讯作者	Chen,Wei
推荐引用方式 GB/T 7714	Chen W,Wei W,Chen ZB,et al. Integrating Multi-source Bilingual Information for Chinese Word Segmentation in Statistical Machine Translation[C],2013.