模式识别与人工智能
2025年4月4日 星期五   首 页     期刊简介     编委会     投稿指南     伦理声明     联系我们                                                                English
模式识别与人工智能  2016, Vol. 29 Issue (9): 825-831    DOI: 10.16451/j.cnki.issn1003-6059.201609007
研究与应用 最新目录| 下期目录| 过刊浏览| 高级检索 |
面向知识库问答中复述问句评分的词向量构建方法*
詹晨迪,凌震华,戴礼荣
中国科学技术大学 语音及语言信息处理国家工程实验室 合肥 230027
Learning Word Embeddings for Paraphrase Scoring in Knowledge Base Based Question Answering
ZHAN Chendi, LING Zhenhua, DAI Lirong
National Engineering Laboratory for Speech and Language Information Processing, .University of Science and Technology of China, Hefei 230027

全文: PDF (417 KB)   HTML (1 KB) 
输出: BibTeX | EndNote (RIS)      
摘要 传统的词向量构建方法基于句子内部单词间的共现概率,采用与具体任务无关的无监督训练方法实现。文中提出基于复述关系约束的词向量构建方法,用于改进知识库问答中基于词向量和词袋模型的复述问句评分。首先从复述问句库中按一定规则收集得到满足复述关系的问句对和不满足复述关系的问句对,以问句对之间的相似度不等式表示句子级的语义约束信息,再将该不等式作为约束项加入词向量训练的目标函数中。实验表明,相比传统词向量构建方法,文中方法可以提高问句间复述关系评价的准确度及知识库问答系统中问题回答的准确度。
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
詹晨迪
凌震华
戴礼荣
关键词 知识库问答 复述问句 词向量    
Abstract:The conventional word embeddings are learned from the co-occurrence probabilities between the words within a same sentence. The learning algorithm is task-independent and unsupervised. A method for constructing word embeddings is proposed by utilizing the constraints of paraphrasing to improve the performance of paraphrase scoring with word embeddings and bag-of-words model in knowledge base (KB) based question answering (QA). In the proposed method, the pairs of paraphrase questions and non-paraphrase questions are collected respectively from a database of question paraphrases according to some designed rules. Then, the inequalities describing the similarities between the pairs of questions are adopted to represent the semantic constraint at the sentence level. These inequalities are integrated into the objective function for training word embeddings. Experimental results show that the proposed method improves the accuracies of paraphrase scoring and KB-based question answering compared with conventional word embedding methods.
Key wordsKnowledge Base Based Question Answering    Question Paraphrase    Word Embedding   
收稿日期: 2016-03-29     
ZTFLH: TP 391.1  
基金资助:安徽省科技攻关计划(No.2014z02006)、中央高校基本科研业务费专项资金(No.WK2350000001)资助
作者简介: 詹晨迪,男,1992年生,硕士研究生,主要研究方向为自然语言处理.E-mail:cdzhan@mail.ustc.edu.cn.凌震华(通讯作者),男,1979年生,博士,副教授,主要研究方向为语音合成、自然语言处理.E-mail:zhling@ustc.edu.cn.戴礼荣,男,1962年生,博士,教授,主要研究方向为数字信号处理、人机语音通信.E-mail:lrdai@ustc.edu.cn.
引用本文:   
詹晨迪,凌震华,戴礼荣. 面向知识库问答中复述问句评分的词向量构建方法*[J]. 模式识别与人工智能, 2016, 29(9): 825-831. ZHAN Chendi, LING Zhenhua, DAI Lirong. Learning Word Embeddings for Paraphrase Scoring in Knowledge Base Based Question Answering. , 2016, 29(9): 825-831.
链接本文:  
http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.201609007      或     http://manu46.magtech.com.cn/Jweb_prai/CN/Y2016/V29/I9/825
版权所有 © 《模式识别与人工智能》编辑部
地址:安微省合肥市蜀山湖路350号 电话:0551-65591176 传真:0551-65591176 Email:bjb@iim.ac.cn
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn