中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Discriminative Word Alignment by Linear Modeling

文献类型:期刊论文

作者Liu, Yang; Liu, Qun; Lin, Shouxun
刊名COMPUTATIONAL LINGUISTICS
出版日期2010-09-01
卷号36期号:3页码:303-339
ISSN号0891-2017
英文摘要Word alignment plays an important role in many NLP tasks as it indicates the correspondence between words in a parallel text. Although widely used to align large bilingual corpora, generative models are hard to extend to incorporate arbitrary useful linguistic information. This article presents a discriminative framework for word alignment based on a linear model. Within this framework, all knowledge sources are treated as feature functions, which depend on a source language sentence, a target language sentence, and the alignment between them. We describe a number of features that could produce symmetric alignments. Our model is easy to extend and can be optimized with respect to evaluation metrics directly. The model achieves state-of-the-art alignment quality on three word alignment shared tasks for five language pairs with varying divergence and richness of resources. We further show that our approach improves translation performance for various statistical machine translation systems.
资助项目National Natural Science Foundation of China[60603095] ; National Natural Science Foundation of China[60573188]
WOS研究方向Computer Science ; Linguistics
语种英语
WOS记录号WOS:000281744900002
出版者M I T PRESS
源URL[http://119.78.100.204/handle/2XEOYT63/12328]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Liu, Yang
作者单位Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714
Liu, Yang,Liu, Qun,Lin, Shouxun. Discriminative Word Alignment by Linear Modeling[J]. COMPUTATIONAL LINGUISTICS,2010,36(3):303-339.
APA Liu, Yang,Liu, Qun,&Lin, Shouxun.(2010).Discriminative Word Alignment by Linear Modeling.COMPUTATIONAL LINGUISTICS,36(3),303-339.
MLA Liu, Yang,et al."Discriminative Word Alignment by Linear Modeling".COMPUTATIONAL LINGUISTICS 36.3(2010):303-339.

入库方式: OAI收割

来源:计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。