arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1606.04597cs.CL
收藏

非平行语料库中平行词汇和短语的记忆学习

Agreement-based Learning of Parallel Lexicons and Phrases from Non-Parallel Corpora

Tsinghua University(清华大学);Jiangsu Collaborative Innovation Center for Language Competence(江苏省语言能力协同创新中心);Samsung R&D Institute of China(三星中国研发中心)

Chunyang Liu, Yang Liu, Huanbo Luan, Maosong Sun, Heng Yu

摘要:

我们介绍了一种基于协议的方法来学习非平行语料库中的平行词汇和短语。基本思想是鼓励两种不对称的潜变量翻译模型(即,源到目标和目标到源)以就识别潜在短语和单词对齐达成一致。协议在单词和短语两个级别上定义。我们开发了一个维特比EM算法,用于有效地联合训练两个单向模型。在汉英数据集上的实验表明,基于一致性的学习显著提高了对齐和翻译性能。

英文摘要:

We introduce an agreement-based approach to learning parallel lexicons and phrases from non-parallel corpora. The basic idea is to encourage two asymmetric latent-variable translation models (i.e., source-to-target and target-to-source) to agree on identifying latent phrase and word alignments. The agreement is defined at both word and phrase levels. We develop a Viterbi EM algorithm for jointly training the two unidirectional models efficiently. Experiments on the Chinese-English dataset show that agreement-based learning significantly improves both alignment and translation performance.

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。

↑