基于词对关联网络的句子对齐研究

句子对齐能够为跨语言的自然语言处理任务提供高质量的对齐句子对。受对齐句子对通常包含大量对齐的单词对这种直觉的启发,该文通过探索神经网络框架下词对间的语义相互作用来解决句子对齐问题。特别地,该文提出的词对关联网络通过融合三种相似性度量方法从不同角度来捕获词对之间的语义关系,并进一步融合它们之间的语义关系来确定两个句子是否对齐。在单调和非单调文本上的实验结果表明,该文提出的方法显著提高了句子对齐的性能。

Word-Pair Relevance Network for Sentence Alignment

Sentence alignment provides high quality parallel sentence pairs for cross-language natural language processing tasks. Inspired by the intuition that aligned sentence pairs consists of a large number of aligned word pairs, this paper proposes the sentence alignment method by the semantic interaction between word pairs in neural network framework. In particular, this paper proposes word-pair relevance network, which first captures the semantic interaction between word pairs from different perspectives, then incorporates the semantic interaction to predict whether a sentence pair is aligned or not. Experimental results on monotonic and non-monotonic bitexts show that the proposed approach significantly improves the performance of sentence alignment.