基于局部和全局语义融合的跨语言句子语义相似度计算模型  

Cross-Lingual Semantic Sentence Similarity Modeling Based on Local and Global Semantic Fusion

作　　者：李霞 刘承标 章友豪 蒋盛益 LI Xia;LIU Chengbiao;ZHANG Youhao;JIANG Shengyi(Eastern Language Processing Center,Guangzhou, Guangdong 510006, China;School of Information Science and Technology, Guangdong University of Foreign Studies, Guangzhou. Guangdong 510006,China)

机构地区：[1]广州市非通用语种智能处理重点实验室,广东广州510006 [2]广东外语外贸大学信息科学与技术学院,广东广州510006

出　　处：《中文信息学报》2019年第6期18-26,共9页Journal of Chinese Information Processing

基　　金：国家自然科学基金(61402119,61572145)

摘　　要：跨语言句子语义相似度计算旨在计算不同语言句子之间的语义相似程度。近年来,前人提出了基于神经网络的跨语言句子语义相似度模型,这些模型多数使用卷积神经网络来捕获文本的局部语义信息,缺少对句子中远距离单词之间语义相关信息的获取。该文提出一种融合门控卷积神经网络和自注意力机制的神经网络结构,用于获取跨语言文本句子中的局部和全局语义相关关系,从而得到文本的综合语义表示。在SemEval-2017多个数据集上的实验结果表明,该文提出的模型能够从多个方面捕捉句子间的语义相似性,结果优于基准方法中基于纯神经网络的模型方法。Cross-lingual semantic textual similarity(STS)is to measure the degree of semantic similarity between texts in different languages.Most current neural network-based models use convolutional neural network to capture the local information of the text,without covering the semantic information between long-distance words in sentences.In this paper,we propose a neural network structure that combines gated convolutional neural networks and self-attention mechanism to obtain the local and global semantic correlations of cross-lingual text sentences,thus obtaining a better semantic representation of the sentences.The experimental results on several datasets of SemEval-2017 show that our model can capture the semantic similarity between sentences from different aspects,and outperforms the baselines based solely on neural network model.

关 键 词：跨语言文本句子语义相似度 自注意力机制 门控卷积神经网络 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]