arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1312.0482cs.CL
收藏

短语翻译模型的语义表示学习

Learning Semantic Representations for the Phrase Translation Model

Microsoft Research(微软研究院)

Jianfeng Gao, Xiaodong He, Wen-tau Yih, Li Deng

摘要:

本文提出了一种新的基于语义的短语翻译模型。将一对源短语和目标短语投影到低维潜在语义空间中的连续值向量表示中,在该低维潜在语义空间中,通过该对短语之间的距离来计算它们的翻译得分。投影是由一个多层神经网络,其权重是学习并行训练数据。该学习旨在直接优化端到端机器翻译结果的质量。实验评估已进行两个Europarl翻译任务,英语-法语和德语-英语。实验结果表明,新的基于语义的短语翻译模型显著提高了基于短语的统计机器翻译系统的性能,获得了0.7-1.0的BLEU积分。

英文摘要:

This paper presents a novel semantic-based phrase translation model. A pair of source and target phrases are projected into continuous-valued vector representations in a low-dimensional latent semantic space, where their translation score is computed by the distance between the pair in this new space. The projection is performed by a multi-layer neural network whose weights are learned on parallel training data. The learning is aimed to directly optimize the quality of end-to-end machine translation results. Experimental evaluation has been performed on two Europarl translation tasks, English-French and German-English. The results show that the new semantic-based phrase translation model significantly improves the performance of a state-of-the-art phrase-based statistical machine translation sys-tem, leading to a gain of 0.7-1.0 BLEU points.

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。

↑