arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1602.07019cs.CL
收藏

基于词汇分解和合成的句子相似性学习

Sentence Similarity Learning by Lexical Decomposition and Composition

IBM T.J. Watson Research Center(IBM T.J. Watson 研究中心)

Zhiguo Wang, Haitao Mi, Abraham Ittycheriah

摘要:

传统的句子相似度方法大多只关注两个输入句子中相似的部分,而忽略了不相似的部分,这些部分通常会给我们一些关于句子的线索和语义意义。在这项工作中,我们提出了一个模型,以考虑到的相似性和不同之处,通过分解和组成句子的词汇语义。该模型将每个单词表示为一个向量,并根据另一个句子中的所有单词为每个单词计算语义匹配向量。然后,每个词向量被分解为一个相似的组件和一个不相似的组件的基础上的语义匹配向量。在此之后,一个双通道CNN模型被用来捕捉特征,通过组成的相似和不相似的组件。最后,在组合特征向量上估计相似性得分。实验结果表明,该模型在回答句选择任务上取得了最好的性能,在释义识别任务上也取得了相当的效果。

英文摘要:

Most conventional sentence similarity methods only focus on similar parts of two input sentences, and simply ignore the dissimilar parts, which usually give us some clues and semantic meanings about the sentences. In this work, we propose a model to take into account both the similarities and dissimilarities by decomposing and composing lexical semantics over sentences. The model represents each word as a vector, and calculates a semantic matching vector for each word based on all words in the other sentence. Then, each word vector is decomposed into a similar component and a dissimilar component based on the semantic matching vector. After this, a two-channel CNN model is employed to capture features by composing the similar and dissimilar components. Finally, a similarity score is estimated over the composed feature vectors. Experimental results show that our model gets the state-of-the-art performance on the answer sentence selection task, and achieves a comparable result on the paraphrase identification task.

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。

↑