[1]彭 怀,宋井宽,唐向红.基于信息匹配方法的中文知识库问答系统[J].计算机技术与发展,2022,32(02):14-19.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 002]
　PENG Huai,SONG Jing-kuan,TANG Xiang-hong.Question Answering System of Chinese Knowledge Base Based on Information Matching Method[J].,2022,32(02):14-19.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 002]
点击复制

基于信息匹配方法的中文知识库问答系统()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年02期
页码:
14-19
栏目:
人工智能
出版日期:
2022-02-10

文章信息/Info

Title:
Question Answering System of Chinese Knowledge Base Based on Information Matching Method
文章编号:
1673-629X(2022)02-0014-06
作者:
彭 怀1 ; 宋井宽2 ; 唐向红1
1. 贵州大学,贵州 贵阳 550025;
2. 电子科技大学,四川 成都 610054
Author(s):
PENG Huai1 ; SONG Jing-kuan2 ; TANG Xiang-hong1
1. Guizhou University,Guiyang 550025,China;
2. University of Electronic Science and Technology of China,Chengdu 610054,China
关键词:
知识库问答; 自然语言处理; 实体识别; 实体链接; 预训练模型; 文本匹配
Keywords:
knowledge base question answering;  natural language processing;  entity recognition;  entity linking;  pre - training model; text matching
分类号:
TP18
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 02. 002
摘要:
知识库问答任务是自然语言处理领域中的研究热点之一,目前国内外学者对知识库问答方法的研究大多数是基于英文数据,基于中文数据的研究非常少。 由于中文存在语言多变性、语法不明确性、语言歧义性等特点,导致很多英文知识库问答研究方法很难应用于中文数据。 针对以上问题,该文提出一种基于信息匹配的中文知识库问答研究方法,探索方法在中文数据上的效果。 首先对问题进行主语实体识别和属性值识别;其次将问句中的实体链接到知识库中的实体,使用逻辑回归对候选实体进行筛选;再次抽取其两跳内关系作为候选查询路径,将候选查询路径和问题进行相似度匹配得到匹配度最高的候选路径;最后使用实体拼接来得到多实体情况的查询路径,查询知识库获得最终答案。 该方法在CCKS2019 CKBQA 测试集上的 F 值达到了 75. 6% 。
Abstract:
Knowledge base question answering is one of the hot topics in the field of natural language processing. At present,most of theresearches on knowledge base question answering are based on English data,but few are based on Chinese data. Due to the language variability,grammar ambiguity and language ambiguity, many question answering methods of English knowledge base are difficult to beapplied to Chinese data. To solve the above problems, we propose a question - and - answer research method based on informationmatching for Chinese knowledge base to explore its effect on Chinese data. Firstly,subject entity identification and attribute value identification are carried out. Secondly,the entity in the question is linked to the entity in the knowledge base,and the candidate entity isscreened by logistic regression. Thirdly,the two-hop internal relationship is extracted as the candidate query path,and the text matchingmethod based on the pre-trained language model is used to select the candidate path with the highest similarity to the question. Finally,the query path of multi-entity case is obtained by using entity splicing,and the final answer is obtained by querying the knowledge base.The proposed method achieves an F value of 75. 6% on the CCKS2019 CKBQA test set.

相似文献/References:

[1]陈国华 赵克 李亚涛 易帅.自然语言处理系统中的事件类名词的耦合处理[J].计算机技术与发展,2008,(06):60.
　CHEN Guo-hua,ZHAO Ke,LI Ya-tao,et al.Coupling Processing of Event Noun in NLP Systems[J].,2008,(02):60.
[2]程节华.基于FAQ的智能答疑系统中分词模块的设计[J].计算机技术与发展,2008,(07):181.
　CHENG Jie-hua.Design of Words Module in Intelligent Q/A System Based on FAQ[J].,2008,(02):181.
[3]杨欢 许威 赵克 陈余.动词属性在自然语言处理当中的研究与应用[J].计算机技术与发展,2008,(07):233.
　YANG Huan,XU Wei,ZHAO Ke,et al.Research and Application of Verb Attributes in Natural Language Processing[J].,2008,(02):233.
[4]孙超 张仰森.面向综合语言知识库的知识融合与获取研究[J].计算机技术与发展,2010,(08):25.
　SUN Chao,ZHANG Yang-sen.Research of Knowledge Integration and Obtaining Oriented Comprehensive Language Knowledge System[J].,2010,(02):25.
[5]党建 亿珍珍 赵克 殷鸿.数学领域集体词结构形式化处理研究[J].计算机技术与发展,2007,(05):121.
　DANG Jian,YI Zhen-zhen,ZHAO Ke,et al.Research of Formalization Processing for Collective Structures in Mathematics Domain[J].,2007,(02):121.
[6]江有福 郑庆华.自然语言网络答疑系统中倒排索引技术的研究[J].计算机技术与发展,2006,(02):126.
　JIANG You-fu,ZHENG Qing-hua.Research of Inverted Index in NLWAS[J].,2006,(02):126.
[7]刘亚清 张瑾 于纯妍.基于义原同现频率的汉语词义排歧系统[J].计算机技术与发展,2006,(05):184.
　LIU Ya-qing,ZHANG Jin,YU Chun-yan.A Chinese Word Sense Disambiguation System Based on Primitive CO- Occurrence Data[J].,2006,(02):184.
[8]刘政怡 李炜 吴建国.基于IMM—IME的汉字键盘输入法编程技术研究[J].计算机技术与发展,2006,(12):43.
　LIU Zheng-yi,LI Wei,WU Jian-guo.Research of Programming Technology of Chinese Input Method Based on IMM- IME[J].,2006,(02):43.
[9]赵鹏 何留进 孙凯 方薇[].基于情感计算的网络中文信息分析技术[J].计算机技术与发展,2010,(11):146.
　ZHAO Peng,HE Liu-jin,SUN Kai,et al.Analyzing Technologies of Internet Chinese Information Based on Affective Computing[J].,2010,(02):146.
[10]徐远方 李成城.基于SVM和词间特征的新词识别研究[J].计算机技术与发展,2012,(05):134.
　XU Yuan-fang,LI Cheng-cheng.Research on New Word Identification Based on SVM and Word Characteristics[J].,2012,(02):134.

更新日期/Last Update: 2022-02-10