基于多标签策略的中文知识图谱问答系统研究

doi:10.19678/j.issn.1000-3428.0056763

摘要/Abstract

摘要： 现有多数中文知识图谱问答（CKBQA）系统侧重于回答单个三元组查询的简单问题，而不能有效解决涉及多个实体和关系的复杂问题。提出一种基于多标签策略进行答案搜索的CKBQA系统，该系统主要包括问题处理和答案搜索2个部分。在问题处理部分，结合预训练语言模型构建新的模型框架，对问题进行实体提及识别、实体链接和关系抽取处理，通过设置3种分类标签将问题划分为简单问题、链式问题和多实体问题。在答案搜索部分，对上述3种分类问题分别给出不同的解决方法。实验结果表明，该系统在CCKS2019-CKBQA评测数据验证集上的平均F1值可达66.76%。

关键词: 知识图谱, 问答系统, 分类, 多标签策略, 实体, 关系

Abstract: Most of the existing Chinese Knowledge Base Question Answering(CKBQA) system focus on simple questions that need a single triplet query,but cannot solve complex questions involving multiple entities and relations. To address the problem,this paper proposes a CKBQA system for answer search based on multi-label strategy.The system mainly consists of two parts:question processing and answer search.In the question processing part,a new model framework is constructed based on the pre-trained language model to perform entity mention recognition,entity linking and relation extraction for the questions.By setting three classification labels,the questions are divided into simple questions,chain questions and multi-entity questions.In the answer search part,different processing methods are given for the above three kinds of classification questions.The experimental results show that the average F1 value of the proposed system reaches 66.76% on the validation set of evaluation data,CCKS2019-CKBQA.

Key words: knowledge base, question answering system, classification, multi-label strategy, entity, relation

中图分类号:

TP391

朱宗奎, 张鹏举, 贾永辉, 陈文亮, 张民. 基于多标签策略的中文知识图谱问答系统研究[J]. 计算机工程, 2021, 47(2): 103-110,117.

ZHU Zongkui, ZHANG Pengju, JIA Yonghui, CHEN Wenliang, ZHANG Min. Study of Chinese Knowledge Base Question Answering System Based on Multi-Label Strategy[J]. Computer Engineering, 2021, 47(2): 103-110,117.

https://www.ecice06.com/CN/Y2021/V47/I2/103

图/表 12

20210225091432

20210225091435

20210225091438

20210225091441

20210225091444

20210225091447

20210225091451

20210225091456

20210225091459

20210225091502

20210225091505

20210225091509

参考文献 33

[1]	ALLAM A,HAGGAG M.The question answering systems:a survey[EB/OL].[2019-11-10].http://www.aast.edu/pheed/staffadminview/pdf_retreive.php?url=19955_401_32_QA%20Survey%20Paper.pdf&stafftype=staffpdf.
[2]	MISHRA A,JAIN S K.A survey on question answering systems with classification[J].Journal of King Saud University-Computer and Information Sciences,2016,28(3):345-361.
[3]	MAO Xianling,LI Xiaoming.A survey on question and answering systems[J].Journal of Frontiers of Computer Science and Technology,2012,6(3):193-207.(in Chinese)毛先领,李晓明.问答系统研究综述[J].计算机科学与探索,2012,6(3):193-207.
[4]	BOLLACKER K,EVANS C,PARITOSH P,et al. Freebase:a collaboratively created graph database for structuring human knowledge[C]//Proceedings of 2008 ACM SIGMOD International Conference on Management of Data.New York,USA:ACM Press,2008:1247-1250.
[5]	SUCHANEK F M,KASNECI G, WEIKUM G.Yago:a core of semantic knowledge[C]//Proceedings of the 16th International Conference on World Wide Web.New York,USA:ACM Press,2007:697-706.
[6]	AUER S,BIZER C,KOBILAROV G,et al.DBpedia:a nucleus for a Web of open data[M].Berlin,Germany:Springer,2007.
[7]	NIU Xing,SUN Xinruo,WANG Haofen, et al. Zhishi.me-weaving Chinese linking open data[C]//Proceedings of International Semantic Web Conference.Berlin,Germany:Springer,2011:205-220.
[8]	PAN J Z.Knowledge extraction from Chinese wiki encyclopedias[J].Journal of Zhejiang University-Science C(Computers & Electronics),2012,13(4):268-280.
[9]	DU Zeyu,YANG Yan,HE Liang.Question answering system of electric business field based on Chinese knowledge map[J].Computer Applications and Software,2017,34(5):159-165.(in Chinese)杜泽宇,杨燕,贺樑.基于中文知识图谱的电商领域问答系统[J].计算机应用与软件,2017,34(5):159-165.
[10]	SHI Yu,GU Tianlong,BIN Chenzhong,et al.Question and answer system of tourist attractions based on knowledge graph[J].Journal of Guilin University of Electronic Technology,2018,38(4):42-48.(in Chinese)时雨,古天龙,宾辰忠,等.基于知识图谱的旅游景点问答系统[J].桂林电子科技大学学报,2018,38(4):42-48.
[11]	PETERS M,NEUMANN M,IYYER M,et al.Deep contextualized word representations[C]//Proceedings of the 9th American Chapter of the Association for Computational Linguistics.New Orleans,USA:Association for Computational Linguistics,2018:2227-2237.
[12]	DEVLIN J,CHANG M W,LEE K,et al.BERT:pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the 10th American Chapter of the Association for Computational Linguistics.New Orleans,USA:Association for Computational Linguistics,2019:4171-4186.
[13]	BERANT J,CHOU A,FROSTIG R,et al.Semantic parsing on freebase from question-answer pairs[C]//Proceedings of 2013 Conference on Empirical Methods in Natural Language Processing.Washington D.C.,USA:IEEE Press,2013:1533-1544.
[14]	CAI Q,YATES A.Semantic parsing freebase:towards open-domain semantic parsing[C]//Proceedings of the 2nd Joint Conference on Lexical and Computational Semantics.Washington D.C.,USA:IEEE Press,2013:328-338.
[15]	REDDY S,LAPATA M,STEEDMAN M.Large-scale semantic parsing without question-answer pairs[J].Transactions of the Association for Computational Linguistics,2014,2:377-392.
[16]	TAU YIH W,WEI CHANG M,HE X D,et al.Semantic parsing via staged query graph generation:question answering with knowledge base[EB/OL].[2019-11-10].https://www.aclweb.org/anthology/P15-1128.pdf.
[17]	YAO X,VAN DURME B.Information extraction over structured data:question answering with freebase[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics.Washington D.C.,USA:IEEE Press,2014:956-966.
[18]	BAST H,HAUSSMANN E.More accurate question answering on freebase[C]//Proceedings of the 24th ACM International Conference on Information and Knowledge Management.New York,USA:ACM Press,2015:1431-1440.
[19]	BORDES A,WESTON J,USUNIER N.Open question answering with weakly supervised embedding models[M]//DAELEMANS W,GOETHALS B,MORIK K.Machine learning and knowledge discovery in databases.Berlin,Germany:Springer,2014.
[20]	BORDES A,CHOPRA S,WESTON J.Question answering with subgraph embeddings[EB/OL].[2019-11-10].https://arxiv.org/abs/1406.3676.
[21]	BORDES A,USUNIER N,CHOPRA S,et al.Large-scale simple question answering with memory networks[EB/OL].[2019-11-10].https://arxiv.org/abs/1506.02075.
[22]	DONG Li,WEI Furu,ZHOU Ming,et al.Question answering over freebase with multi-column convolutional neural networks[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing.Stroudsburg,USA:Association for Computational Linguistics,2015:260-269.
[23]	HAO Yanchao,ZHANG Yuanzhe,LIU Kang,et al.An end-to-end model for question answering over knowledge base with cross-attention combining global knowledge[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. Stroudsburg,USA:Association for Computational Linguistics,2017:221-231.
[24]	LAI Yuxuan,FENG Yansong,YU Xiaohan,et al.Lattice CNNs for matching based Chinese question answering[C]//Proceedings of AAAI Conference on Artificial Intelligence.New York,USA:ACM Press,2019:6634-6641.
[25]	LAI Yuxuan,LIN Yang,CHEN Jiahao,et al.Open domain question answering system based on knowledge base[EB/OL].[2019-11-10].http://tcci.ccf.org.cn/conference/2016/papers/319.pdf.
[26]	LAI Yuxuan,JIA Yanyan,LIN Yang,et al.A Chinese question answering system for single-relation factoid questions[EB/OL].[2019-11-10].http://tcci.ccf.org.cn/conference/2017/papers/2003.pdf.
[27]	ZHOU Botong,SUN Chengjie,LIN Lei,et al.LSTM based question answering for large scale knowledge base[J].Acta Scientiarum Naturalium Universitatis Pekinensis,2018,54(2):286-292.(in Chinese)周博通,孙承杰,林磊,等.基于LSTM的大规模知识库自动问答[J].北京大学学报(自然科学版),2018,54(2):286-292.
[28]	SUN Zhaoyu,SONG Lei,YU Jiaming.A QA search algorithm based on the fusion integration of text similarity and graph computation[EB/OL].[2019-11-10].http://ceur-ws.org/Vol-2242/paper13.pdf.
[29]	LUO Jinchang,YIN Cunxiang,WU Xiaohui,et al.Chinese knowledge base question answering system based on hybrid semantic similarity[EB/OL].[2019-11-10].https://conference.bj.bcebos.com/ccks2019/eval/webpage/pdfs/eval_paper_6_1.pdf.(in Chinese)骆金昌,尹存祥,吴晓晖,等.混合语义相似度的中文知识图谱问答系统[EB/OL].[2019-11-10].https://conference.bj.bcebos.com/ccks2019/eval/webpage/pdfs/eval_paper_6_1.pdf.
[30]	HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780.
[31]	LAFFERTY J,MCCALLUM A,PEREIRA F C N. Conditional random fields:probabilistic models for segmenting and labeling sequence data[EB/OL].[2019-11-10].https://repository.upenn.edu/cgi/viewcontent.cgi?article=1162&context=cis_papers.
[32]	CHEN T,GUESTRIN C.XGBoost:a scalable tree boosting system[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York,USA:ACM Press,2016:785-794.
[33]	DUAN N.Overview of the NLPCC-ICCPOL 2016 shared task:open domain Chinese question answering[M]//LIN C Y,XUE N W,ZHAO D Y,et al.Natural language understanding and intelligent applications.Berlin,Germany:Springer,2016.

选择文件类型/文献管理软件名称

选择包含的内容