arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1607.08692cs.CL
收藏

一种新的基于双语义团的词汇翻译双语词嵌入方法

A Novel Bilingual Word Embedding Method for Lexical Translation Using Bilingual Sense Clique

Shanghai Jiao Tong University(上海交通大学);Centre National de la Recherche Scientifique(法国国家科学研究中心);National Institute of Information and Communications Technology(信息通信研究机构)

Rui Wang, Hai Zhao, Sabine Ploux, Bao-Liang Lu, Masao Utiyama, Eiichiro Sumita

摘要:

现有的双语词嵌入方法大多只考虑了浅上下文或简单的共现信息。本文提出了一种潜在双语语义单元(Bilingual Sense Clique,BSC),它是由双语语料库上基于逐点互信息的图的最大完全子图导出的。这样,我们平等地对待源和目标词,并且不再需要在大多数现有作品中必须使用的单独的双语投影处理。几种降维方法进行评估,总结BSC的字的关系。在双语词典翻译任务上对所提出的方法进行了评估,实验结果表明,双语意义嵌入方法优于现有的双语词嵌入方法。

英文摘要:

Most of the existing methods for bilingual word embedding only consider shallow context or simple co-occurrence information. In this paper, we propose a latent bilingual sense unit (Bilingual Sense Clique, BSC), which is derived from a maximum complete sub-graph of pointwise mutual information based graph over bilingual corpus. In this way, we treat source and target words equally and a separated bilingual projection processing that have to be used in most existing works is not necessary any more. Several dimension reduction methods are evaluated to summarize the BSC-word relationship. The proposed method is evaluated on bilingual lexicon translation tasks and empirical results show that bilingual sense embedding methods outperform existing bilingual word embedding methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑