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 1503.03244cs.CLcs.LGcs.NE
收藏

用于自然语言句子匹配的卷积神经网络结构

Convolutional Neural Network Architectures for Matching Natural Language Sentences

Huawei Technologies Co. Ltd.(华为技术有限公司)

Baotian Hu, Zhengdong Lu, Hang Li, Qingcai Chen

摘要:

语义匹配对于许多自然语言任务\cite{bordes2014semantic,RetrievalQA}来说是至关重要的。一个成功的匹配算法需要对语言对象的内部结构以及它们之间的交互进行充分的建模。作为实现这一目标的一步,我们提出了匹配两个句子的卷积神经网络模型,通过适应视觉和语音中的卷积策略。所提出的模型不仅很好地代表了层次结构的句子与他们的逐层组合和池,但也捕捉丰富的匹配模式在不同的水平。我们的模型是相当通用的,不需要语言的先验知识,因此可以应用于匹配不同性质和不同语言的任务。对多种匹配任务的实证研究表明,该模型对多种匹配任务的有效性和竞争对手的模型的优越性。

英文摘要:

Semantic matching is of central importance to many natural language tasks \cite{bordes2014semantic,RetrievalQA}. A successful matching algorithm needs to adequately model the internal structures of language objects and the interaction between them. As a step toward this goal, we propose convolutional neural network models for matching two sentences, by adapting the convolutional strategy in vision and speech. The proposed models not only nicely represent the hierarchical structures of sentences with their layer-by-layer composition and pooling, but also capture the rich matching patterns at different levels. Our models are rather generic, requiring no prior knowledge on language, and can hence be applied to matching tasks of different nature and in different languages. The empirical study on a variety of matching tasks demonstrates the efficacy of the proposed model on a variety of matching tasks and its superiority to competitor models.

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。

↑