基于多粒度特征表示的知识图谱问答

doi:10.3969/j.issn.1006-2475.2018.09.002

计算机与现代化

基于多粒度特征表示的知识图谱问答

(1.中国科学院大学电子电气与通信工程学院,北京100049;2.中国科学院电子学研究所,北京100190;
3.中国科学院空间信息处理与应用系统技术重点实验室,北京100190)

收稿日期:2018-03-15 出版日期:2018-09-29 发布日期:2018-09-30
作者简介:申存(1992-)，男，四川广安人，中国科学院大学电子电气与通信工程学院、中国科学院电子学研究所硕士研究生，研究方向：自然语言处理，知识图谱; 黄廷磊(1971-)，男，研究员，博士生导师，博士，研究方向：数据挖掘，大数据分析; 梁霄(1981-)，男，助理研究员，博士，研究方向：数据组织管理，知识图谱。
基金资助:
国家自然科学基金资助项目(61725105, 61331017)

Knowledge Graph Question Answering Based on Multi-granularity Feature Representation

(1. School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100049, China;
2. Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, China;
3. Key Laboratory of Technology in Geo-Spatial Information Processing and Application System,
Chinese Academy of Sciences, Beijing 100190, China)

Received:2018-03-15 Online:2018-09-29 Published:2018-09-30

摘要/Abstract

摘要： 近年来，基于知识图谱的问答系统逐渐成为学术界和工业界的研究和应用热点方向，而传统方法通常存在效率不高以及未充分利用数据信息的问题。针对以上问题，本文将中文知识图谱问答分为实体抽取和属性选择2个子任务，采用双向长短期记忆条件随机场（Bi-LSTM-CRF）模型来进行实体识别，并提出一种多粒度特征表示的属性选择模型。该模型采用字符级别以及词级别分别对问句和属性进行嵌入表示并通过编码器进行编码，对于属性同时还引入热度编码的信息。通过不同粒度文本表示的结合，并对问句和属性进行相似度计算，最终该系统在NLPCC-ICCPOL 2016 KBQA数据集上取得了73.96%的F1值，能够较好地完成知识图谱问答任务。

关键词: 知识图谱, 问答系统, 实体抽取, 属性选择

Abstract: Recently, knowledge graph question answering has gradually become the focus of academic and industrial circles. However, traditional methods often have problems of inefficiency and insufficient use of data information. In order to solve the problems above, this paper divides the Chinese knowledge graph question answering into two sub-tasks: entity extraction and property selection. The Bi-LSTM-CRF model is used to identify entities, and a multi-granularity feature representation model is proposed to carry out property selection. The model utilizes character-level and word-level to represent questions and properties and encode them through the encoder. At the same time, it also introduces the one-hot information for the properties. Through the combination of multi-granularity text representations and the similarity calculation of questions and properties, the system finally achieves a 73.96% F1 value on the NLPCC-ICCPOL 2016 KBQA data set, which finishes the knowledge graph question and answer task successfully.

Key words: knowledge graph, question answering system, entity extraction, property selection

中图分类号:

TP391

申存1,2,3，黄廷磊2,3，梁霄2,3. 基于多粒度特征表示的知识图谱问答[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2018.09.002.

SHEN Cun1,2,3, HUANG Ting-lei2,3, LIANG Xiao2,3. Knowledge Graph Question Answering Based on Multi-granularity Feature Representation[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2018.09.002.

参考文献

［1］ Bollacker K, Evans C, Paritosh P, et al. Freebase:A collaboratively created graph database for structuring human knowledge［C］// Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data. 2008:1247-1249.
［2］ Auer S, Bizer C, Kobilarov G, et al. DBpedia: A nucleus for a Web of open data［C］// Proceedings of the 6th International Semantic Web Conference and the 2nd Asian Semantic Web Conference. 2007:722-735.
［3］ Niu Xing, Sun Xinruo, Wang Haofen, et al. Zhishi.me: Weaving Chinese linking open data［C］// Proceedings of the 10th International Conference on the Semantic Web. 2011,2:205-220.
［4］ Wang Zhi-chun, Wang Zhi-gang, Li Juan-zi, et al. Knowledge extraction from Chinese wiki encyclopedias［J］. Journal of Zhejiang University-Science C(Computers & Electronics), 2012,13(4):268-280.
［5］ Berant J, Chou A, Frostig R, et al. Semantic parsing on freebase from question-answer pairs［C］// Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. 2013:1533-1544.
［6］ 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. 2015,1:260-269.
［7］ Yu Lei, Hermann K M, Blunsom P, et al. Deep Learning for Answer Sentence Selection［DB/OL］. https://arxiv.org/pdf/1412.1632v1.pdf, 2014-12-04.
［8］ Bordes A, Usunier N, Chopra S, et al. Large-scaleSimple Question Answering with Memory Networks［DB/OL］. https://arxiv.org/pdf/1506.02075v1.pdf, 2015-06-05.
［9］ Golub D, He Xiaodong. Character-level question answering with attention［C］// Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. 2016:1598-1607.
［10］Yih W, Chang M W, He Xiaodong, et al. Semantic parsing via staged query graph generation: Question answering with knowledge base［C］// Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. 2015,1:1321-1331.
［11］Yin Wenpeng, Yu Mo, Xiang Bing, et al. Simple question answering by attentive convolutional neural network［C］// Proceedings of the 26th International Conference on Computational Linguistics. 2016:1746-1756.
［12］Cai Qingqing, Yates A. Large-scale semantic parsing via schema matching and lexicon extension［C］// Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics. 2013,1:423-433.
［13］Yao Xuchen, 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. 2014,1:956-966.
［14］Dai Zihang, Li Lei, Xu Wei. CFO: Conditional focused neural question answering with large-scale knowledge bases［C］// Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. 2016,1:800-810.
［15］Bordes A, Weston J, Usunier N. Open question answering with weakly supervised embedding models［C］// Proceedings of the 2014 European Conference on Machine Learning and Knowledge Discovery in Databases. 2014:165-180.
［16］Bordes A, Usunier N, Garcia-Duran A, et al. Translating embeddings for modeling multi-relational data［C］// Proceedings of the 2013 International Conference on Neural Information Processing Systems. 2013:2787-2795.
［17］Lample G, Ballesteros M, Subramanian S, et al. Neuralarchitectures for named entity recognition［C］// Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2016:260-270.
［18］Dong Chuanhai, Zhang Jiajun, Zong Chengqing, et al. Character-based LSTM-CRF with radical-level features for Chinese named entity recognition［C］// Proceedings of the 24th International Conference on Computer Processing of Oriental Languages and the 5th CCF Conference on Natural Language Processing and Chinese Computing. 2016:239-250.
［19］周志华. 机器学习［M］. 北京:清华大学出版社, 2016.
［20］Lai Yuxian, Lin Yang, Chen Jiahao, et al. Open domain question answering system based on knowledge base［C］// Proceedings of the 24th International Conference on Computer Processing of Oriental Languages and the 5th CCF Conference on Natural Language Processing and Chinese Computing. 2016:722-733.
［21］Yang Fengyu, Gan Liang, Li Aiping, et al. Combining deep learning with information retrieval for question answering［C］// Proceedings of the 24th International Conference on Computer Processing of Oriental Languages and the 5th CCF Conference on Natural Language Processing and Chinese Computing. 2016:917-925.
［22］Xie Zhiwen, Zeng Zhao, Zhou Guangyou, et al. Knowledge base question answering based on deep learning models［C］// Proceedings of the 24th International Conference on Computer Processing of Oriental Languages and the 5th CCF Conference on Natural Language Processing and Chinese Computing. 2016:300-311.

[1]	王运乾, 王以松, 陈攀峰, 邹龙. 融合注意力机制的药用植物文本命名实体识别[J]. 计算机与现代化, 2021, 0(11): 100-105.
[2]	王钰蓥, 王勇. 基于知识图谱和Bi-LSTM的推荐算法[J]. 计算机与现代化, 2021, 0(09): 90-98.
[3]	耿化聪, 梁宏涛, 刘国柱. 基于知识图谱与协同过滤的饮食推荐算法[J]. 计算机与现代化, 2021, 0(08): 24-29.
[4]	张艳, 杨芳, 杨蕾, 韩奎国, 李辉. 基于知识图谱的区块链技术及电力行业应用分析[J]. 计算机与现代化, 2020, 0(12): 55-60.
[5]	冯云霞, 衣鹏, 韩正亮, 宋波. 基于CNN-BGRU-CRF的中文电子病历实体抽取方法[J]. 计算机与现代化, 2020, 0(11): 60-64.
[6]	张紫璇,陆佳民,姜笑,冯钧. 面向水利信息资源的智能问答系统构建与应用[J]. 计算机与现代化, 2020, 0(03): 65-.
[7]	项威. 事件知识图谱构建技术与应用综述[J]. 计算机与现代化, 2020, 0(01): 10-.
[8]	冯钧，徐新，陆佳民. 水利信息知识图谱的构建与应用[J]. 计算机与现代化, 2019, 0(09): 35-.
[9]	冯钧,柳菁铧,孔盛球. 融合多特征的中文集成实体链接方法[J]. 计算机与现代化, 2019, 0(01): 69-.
[10]	王通,艾中良,张先国. 基于深度学习的威胁情报知识图谱构建技术[J]. 计算机与现代化, 2018, 0(12): 21-.
[11]	王良萸. 面向碳交易领域的知识图谱构建方法[J]. 计算机与现代化, 2018, 0(08): 114-.
[12]	郭琳，翟社平，高山. 知识图谱中的语义推理算法[J]. 计算机与现代化, 2017, 0(12): 71-76.
[13]	蒋宗礼，赵洁. 关联首尾段落与首尾语句的多特征融合段落相似度计算[J]. 计算机与现代化, 2016, 0(9): 10-14+20.
[14]	蒋宗礼，李立新. 社区问答系统中问题推荐机制[J]. 计算机与现代化, 2015, 0(8): 89-92.
[15]	侯丽敏，张永强. 面向课程的中文FAQ自动问答系统模型[J]. 计算机与现代化, 2014, 0(10): 20-24.

基于多粒度特征表示的知识图谱问答

Knowledge Graph Question Answering Based on Multi-granularity Feature Representation

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价