知识图谱多跳问答推理研究进展、挑战与展望

doi:10.11959/j.issn.2096-0271.2021026

Abstract

Abstract:

Recently, knowledge graph based question answering has been widely used in many fields such as medical care, finance, and government affairs.Users are no longer satisfied with question answering service of single-hop entity attributes, but want service which can handle complex multi-hop question.In order to accurately and deeply understand multi-hop questions, various types of reasoning methods have been proposed.The latest research methods of multi-hop knowledge graph based question answering were systematically introduced, as well as related datasets and evaluation metrics.These

Key words: knowledge graph, multi-hop question answering, reasoning

CLC Number:

TP311

Huifang DU, Haofen WANG, Yinghui SHI, Meng WANG. Progress, challenges and research trends of reasoning in multi-hop knowledge graph based question answering[J]. Big Data Research, 2021, 7(3): 60-79.

Figures/Tables 8

References 71

[1]	王昊奋, 丁军, 胡芳槐 ,等. 大规模企业级知识图谱实践综述[J]. 计算机工程, 2020,46(7): 1-13.
	WANG H F , DING J , HU F H ,et al. Survey on large scale enterprise-level knowledge graph practices[J]. Computer Engineering, 2020,46(7): 1-13.
[2]	邱楠, 王昊奋, 邵浩 . 从聊天机器人到虚拟生命-人工智能技术的新机遇[J]. 中国人工智能学会通讯, 2017,11(7): 32-40.
	QIU N , WANG H F , SHAO H . From chatbots to virtual life - a new opportunity for artificial intelligence technology[J]. Communications of the CAAI, 2017,11(7): 32-40.
[3]	陈成, 陈跃国, 刘宸 ,等. 意图知识图谱的构建与应用[J]. 大数据, 2020,6(2): 57-68.
	CHEN C , CHEN Y G , LIU C ,et al. Constructing and analyzing intention knowledge graphs[J]. Big Data Research, 2020,6(2): 57-68.
[4]	WU T X , WANG H F , LI C ,et al. Knowledge graph construction from multiple online encyclopedias[J]. World Wide Web, 2020,23(5): 2671-2698.
[5]	WANG M , WANG H F , QI G L ,et al. Richpedia:a large-scale,comprehensive multi-modal knowledge graph[J]. Big Data Research, 2020,22: 100159.
[6]	邹艳珍, 王敏, 谢冰 ,等. 基于大数据的软件项目知识图谱构造及问答方法[J]. 大数据, 2021,7(1): 22-36.
	ZOU Y Z , WANG M , XIE B ,et al. Software knowledge graph construction and Q＆A technology based on big data[J]. Big Data Research, 2021,7(1): 22-36.
[7]	官赛萍, 靳小龙, 贾岩涛 ,等. 面向知识图谱的知识推理研究进展[J]. 软件学报, 2018,29(10): 2966-2994.
	GUAN S P , JIN X L , JIA Y T ,et al. Knowledge reasoning over knowledge graph:a survey[J]. Journal of Software, 2018,29(10): 2966-2994.
[8]	王昊奋, 奚宁, 周扬 . 企业计算中的机器人智能问答[J]. 中国计算机学会通讯, 2019,15(5): 28-37.
	WANG H F , XI N , ZHOU Y . Intelligent question answering in enterprise computing[J]. Communications of the CCF, 2019,15(5): 28-37.
[9]	WANG M , WANG R J , LIU J ,et al. Towards empty answers in SPARQL:approximating querying with RDF embedding[C]// Proceedings of the 17th International Semantic Web Conference. Cham:Springer, 2018: 513-529.
[10]	ZHU C H , REN K , LIU X ,et al. A graph traversal based approach to answer nonaggregation questions over DBpedia[C]// Proceedings of the 5th Joint International Semantic Technology Conference. Cham:Springer, 2015: 219-234.
[11]	WANG H F , LIU Q L , PENIN T ,et al. Semplore:a scalable IR approach to search the Web of data[J]. Web Semantics:Science,Services and Agents on the World Wide Web, 2009,7(3): 177-188.
[12]	BORDES A , WESTON J , USUNIER N . Open question answering with weakly supervised embedding models[J]. Lecture Notes in Computer Science, 2014,8724(PART 1): 165-180.
[13]	BORDES A , USUNIER N , GARCIADURAN A ,et al. Translating embeddings for modeling multi-relational data[C]// Proceedings of the 26th International Conference on Neural Information Processing Systems. New York:ACM Press, 2013: 2787-2795.
[14]	WANG Z , ZHANG J W , FENG J L ,et al. Knowledge graph embedding by translating on hyperplanes[C]// Proceedings of the 28th AAAI Conference on Artificial Intelligence.[S.l.:s.n.], 2014: 1112-1119.
[15]	LIN Y K , LIU Z Y , SUN M S ,et al. Learning entity and relation embeddings for knowledge graph completion[C]// Proceedings of the 29th AAAI Conference on Artificial Intelligence.[S.l.:s.n.], 2015.
[16]	LI D C , ZHANG J Y , LI P . Representation learning for question classification via topic sparse autoencoder and entity embedding[C]// Proceedings of the 2018 IEEE International Conference on Big Data. Piscataway:IEEE Press, 2019: 126-133.
[17]	HUANG X , ZHANG J Y , LI D C ,et al. Knowledge graph embedding based question answering[C]// Proceedings of the 12th ACM International Conference on Web Search and Data Mining.[S.l.:s.n.], 2019: 105-113.
[18]	BORDES A , CHOPRA S , WESTON J . Question answering with subgraph embeddings[C]// Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing.[S.l.:s.n.], 2014: 615-620.
[19]	DONG L , WEI F R , ZHOU M ,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.[S.l.:s.n.], 2015: 260-269.
[20]	YIH W T , CHANG M W , HE X D ,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.[S.l.:s.n.], 2015: 1321-1331.
[21]	HAO Y C , ZHANG Y Z , LIU K ,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.[S.l.:s.n.], 2017: 221-231.
[22]	SAXENA A , TRIPATHI A , TALUKDAR P . Improving multi-hop question answering over knowledge graphs using knowledge base embeddings[C]// Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.[S.l.:s.n.], 2020: 4498-4507.
[23]	TROUILLON T , WELBL J , RIEDEL S ,et al. Complex embeddings for simple link prediction[C]// Proceedings of the International Conference on Machine Learning.[S.l.:s.n.], 2016: 2071-2080.
[24]	LIU Y H , OTT M , GOYAL N ,et al. RoBERTa:a robustly optimized bert pretraining approach[J]. arXiv preprint, 2019,arXiv:1907.11692.
[25]	HE G L , LAN Y S , JIANG J ,et al. Improving multi-hop knowledge base question answering by learning intermediate supervision signals[J]. arXiv preprint, 2021,arXiv:2101.03737v1.
[26]	HINTON G , VINYALS O , DEAN J . Distilling the knowledge in a neural network[J]. arXiv preprint, 2015,arXiv:1503.02531.
[27]	YANG Z , SHOU L J , GONG M ,et al. Model compression with two-stage multi-teacher knowledge distillation for web question answering system[C]// Proceedings of the ACM 13th International Conference on Web Search and Data Mining. New York:ACM Press, 2020: 690-698.
[28]	KIPF T N , WELLING M . Semi-supervised classification with graph convolutional networks[C]// Proceedings of 5th International Conference on Learning Representations.[S.l.:s.n.], 2017.
[29]	SCHLICHTKRULL M , KIPF T N , BLOEM P ,et al. Modeling relational data with graph convolutional networks[C]// The Semantic Web:15th International Conference.[S.l.:s.n.], 2018: 593-607.
[30]	TERU K , DENIS E , HAMILTON W . Inductive relation prediction by subgraph reasoning[C]// Proceedings of the 37th International Conference on Machine Learning.[S.l.:s.n.], 2020: 9448-9457.
[31]	DEVLIN J , CHANG M W , LEE K ,et al. BERT:pre-training of deep bidirectional transformers for language understanding[C]// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.[S.l.:s.n.], 2019: 4171-4186.
[32]	LIN B Y , CHEN X Y , CHEN J ,et al. KagNet:knowledge-aware graph networks for commonsense reasoning[C]// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing.[S.l.:s.n.], 2019: 2829-2839.
[33]	FENG Y L , CHEN X Y , LIN B Y ,et al. Scalable multi-hop relational reasoning for knowledge-aware question answering[C]// Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing.[S.l.:s.n.], 2020: 1295-1309.
[34]	XU K , LAI Y X , FENG Y S ,et al. Enhancing key-value memory neural networks for knowledge based question answering[C]// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.[S.l.:s.n.], 2019: 2937-2947.
[35]	GREFF K , R K SRIVASTAVA , KOUTNíK J ,et al. LSTM:a search space odyssey[J]. IEEE Transactions on Neural Networks and Learning Systems, 2016,28(10): 2222-2232.
[36]	SUN H T , DHINGRA B , ZAHEER M ,et al. Open domain question answering using early fusion of knowledge bases and text[C]// Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Stroudsburg:ACL Press, 2018: 4321-4242.
[37]	SUN H T , BEDRAX-WEISS T , COHEN W W . PullNet:open domain question answering with iterative retrieval on knowledge bases and text[C]// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing.[S.l.:s.n.], 2019: 2380-2390.
[38]	HAVELIWALA T H . Topic-Sensitive Pagerank:a context-sensitive ranking algorithm for web search[J]. IEEE Transactions on Knowledge and Data Engineering, 2003,15(4): 784-796.
[39]	WESTON J , CHOPRA S , BORDES A . Memory networks[C]// Proceedings of the 3rd International Conference on Learning Representations.[S.l.:s.n.], 2015: 1-15.
[40]	MILLER A , FISCH A , DODGE J ,et al. Key-value memory networks for directly reading documents[C]// Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing.[S.l.:s.n.], 2016: 1400-1409.
[41]	CHEN Y , WU L F , ZAKI M J . Bidirectional attentive memory networks for question answering over knowledge bases[C]// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.[S.l.:s.n.], 2019: 2913-2923.
[42]	DAS R , ZAHEER M , REDDY S ,et al. Question answering on knowledge bases and text using universal schema and memory networks[C]// Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics.[S.l.:s.n.], 2017: 358-365.
[43]	KUMAR A , IRSOY O , ONDRUSKA P ,et al. Ask me anything:dynamic memory networks for natural language processing[C]// Proceedings of the 33rd International Conference on Machine Learning. New York:ACM Press, 2016: 2068-2078.
[44]	RAMACHANDRAN G S , SOHMSHETTY A . Ask me even more:dynamic memory tensor networks (extended model)[J]. arXiv preprint, 2017,arXiv:1703.03939v1.
[45]	ZHOU M T , HUANG M L , ZHU X Y . An interpretable reasoning network for multi-relation question answering[C]// Proceedings of the 27th International Conference on Computational Linguistics.[S.l.:s.n.], 2018: 2010-2022.
[46]	GARDNER M , TALUKDAR P , KISIEL B ,et al. Improving learning and inference in a large knowledge-base using latent syntactic cues[C]// Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing.[S.l.:s.n.], 2013: 833-838.
[47]	XIONG W H , HOANG T , WANG W Y . DeepPath:a reinforcement learning method for knowledge graph reasoning[C]// Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing.[S.l.:s.n.], 2017: 564-573.
[48]	MEILICKE C , CHEKOL M W , FINK M ,et al. Reinforced anytime bottom up rule learning for knowledge graph completion[J]. arXiv preprint, 2020,arXiv:2004.04412.
[49]	DAS R , DHULIAWALA S , ZAHEER M ,et al. Go for a walk and arrive at the answer:reasoning over paths in knowledge bases using reinforcement learning[C]// Proceedings of the 6th International Conference on Learning Representations.[S.l.:s.n.], 2018.
[50]	LIN X V , SOCHER R , XIONG C M . Multihop knowledge graph reasoning with reward shaping[C]// Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.[S.l.:s.n.], 2018: 3243-3253.
[51]	SHEN Y L , CHEN J S , HUANG P S ,et al. M-Walk:learning to walk over graphs using monte carlo tree search[C]// Proceedings of the 32nd International Conference on Neural Information Processing Systems.[S.l.:s.n.], 2018: 6786-6797.
[52]	CHEN W H , XIONG W H , YAN X F ,et al. Variational knowledge graph reasoning[C]// Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.[S.l.:s.n.], 2018: 1823-1832.
[53]	KINGMA D P , WELLING M . Autoencoding variational Bayes[C]// Proceedings of the 2nd International Conference on Learning Representations.[S.l.:s.n.], 2014: 1-14.
[54]	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.
[55]	BAO J W , DUAN N , YAN Z ,et al. Constraint-based question answering with knowledge graph[C]// Proceedings of the 26th International Conference on Computational Linguistics.[S.l.:s.n.], 2016: 2503-2514.
[56]	YU M , YIN W P , HASAN K S ,et al. Improved neural relation detection for knowledge base question answering[C]// Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics.[S.l.:s.n.], 2017: 571-581.
[57]	LAN Y S , JIANG J . Query graph generation for answering multi-hop complex questions from knowledge bases[C]// Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.[S.l.:s.n.], 2020: 969-974.
[58]	YIH W T , RICHARDSON M , MEEK C ,et al. The value of semantic parse labeling for knowledge base question answering[C]// Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Stroudsburg:ACL Press, 2016: 201-206.
[59]	RICHARDSON M , DOMINGOS P . Markov logic networks[J]. Machine Learning, 2006,62(1-2): 107-136.
[60]	SINGLA P , DOMINGOS P . Discriminative training of Markov logic networks[C]// Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto:AAAI Press, 2005: 868-873.
[61]	VARDHAN L V H , JIA G , KOK S . Probabilistic logic graph attention networks for reasoning[C]// Proceedings of the Web Conference 2020.[S.l.:s.n.], 2020: 669-673.
[62]	HAMILTON W , BAJAJ P , ZITNIK M ,et al. Embedding logical queries on knowledge graphs[C]// Proceedings of the 32nd International Conference on Neural Information Processing Systems.[S.l.:s.n.], 2018: 2030-2041.
[63]	REN H Y , LESKOVEC J . Beta embeddings for multi-hop logical reasoning in knowledge graphs[C]// Proceedings of the 34th International Conference on Neural Information Processing Systems.[S.l.:s.n.], 2020: 19716-19726.
[64]	DING B Y , WANG Q , WANG B ,et al. Improving knowledge graph embedding using simple constraints[C]// Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics.[S.l.:s.n.], 2018: 110-121.
[65]	GUO S , LI L , HUI Z ,et al. Knowledge graph embedding preserving soft logical regularity[C]// Proceedings of the 29th ACM International Conference on Information ＆ Knowledge Management. New York:ACM Press, 2020: 425-434.
[66]	QU M , TANG J . Probabilistic logic neural networks for reasoning[C]// Proceedings of the 33rd International Conference on Neural Information Processing Systems.[S.l.:s.n.], 2019: 7710-7720.
[67]	REN H Y , HU W H , LESKOVEC J . Query2Box:reasoning over knowledge graphs in vector space using box embeddings[C]// Proceedings of the 8th International Conference on Learning Representations.[S.l.:s.n.], 2020.
[68]	ZHANG Y Y , DAI H J , KOZAREVA Z ,et al. Variational reasoning for question answering with knowledge graph[C]// Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto:AAAI Press, 2018.
[69]	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. New York:ACM Press, 2008: 1247-1250.
[70]	TALMOR A , BERANT J . The web as a knowledge-base for answering complex questions[C]// Proceedings of the 16th Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.[S.l.:s.n.], 2018: 641-651.
[71]	TOUTANOVA K , CHEN D Q . Observed versus latent features for knowledge base and text inference[C]// Proceedings of the 3rd Workshop on Continuous Vector Space Models and Their Compositionality.[S.l.:s.n.], 2015: 57-66.

Metrics

Recommended 0

No Suggested Reading articles found!

模型		MetaQA		WebQSP	CWQ
模型	1-hop	2-hop	3-hop	WebQSP	CWQ
KV-MemNN	96.2%	82.7%	48.9%	46.7%	21.1%
GRAFT-Net	97.0%	94.8%	77.7%	66.4%	32.8%
PullNet	97.0%	99.9%	91.4%	68.1%	45.9%
EmbedKGQA	97.5%	98.8%	94.8%	66.6%	-
NSM_+h	97.2%	99.9%	98.9%	74.3%	48.8%

数据集	模型	1-hop	2-hop	3-hop
FB15k	BetaE	65.1%	25.7%	24.7%
	Q2B	68.0%	21.0%	14.2%
	GQE	54.6%	15.3%	10.8%
FB15k-237	BetaE	39.0%	10.9%	10.0%
	Q2B	40.6%	9.4%	6.8%
	GQE	35.0%	7.2%	5.3%
NELL-995	BetaE	53.0%	13.0%	11.4%
	Q2B	42.2%	14.0%	11.2%
	GQE	32.8%	11.9%	9.6%

指标	方法	FB15k	FB15k-237	NELL-995
Hits@1	MINERVA	-	21.7%	66.3%
	RewardShaping	-	32.7%	65.6%
MAP	DeepPath	57.2%	-	79.6%
	DIVA	59.8%	-	88.6%
	M-Walk	-	-	89.9%

多跳知识问答推理方法	优点	不足
基于嵌入的方法	减少对手工定义模板或规则的依赖；	可解释性方面存在欠缺；
	嵌入具有不确定语义	知识图谱中实体邻居信息稀疏时，语义表示效果差
基于路径的方法	具有较好的可解释性	处理属性型、事实型知识时，建模复杂
基于逻辑的方法	具有严密性、自然性、准确率高等特点	不能模拟不确定性；
		将逻辑运算转换为嵌入向量空间的几何操作不能很好地处理复杂知识查询

Progress, challenges and research trends of reasoning in multi-hop knowledge graph based question answering

RichHTML

PDF下载

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 8

References 71

Related Articles 15

Metrics

Recommended 0

[1]	Yuqi ZHANG, Xiaowen HUANG, Jitao SANG. Knowledge-enhanced policy-guided interactive reinforcement recommendation system [J]. Big Data Research, 2022, 8(5): 88-105.
[2]	Jingye SHI, Pan LI. Key technologies and application exploration of aerospace big data in the construction of new smart city [J]. Big Data Research, 2022, 8(2): 120-133.
[3]	Ling TAN, Haihong E, Zemin KUANG, Meina SONG, Yu LIU, Zhengyu CHEN, Xiaoxuan XIE, Jundi LI, Jiawei FAN, Qingchuan WANG, Xiaoyang KANG. Key technologies and research progress of medical knowledge graph construction [J]. Big Data Research, 2021, 7(4): 80-104.
[4]	Qingxia LIU, Junyou LI, Gong CHENG. An interpretive evaluation of entity summarization system [J]. Big Data Research, 2021, 7(3): 15-29.
[5]	Yuming SHEN, Jianfeng DU. Temporal knowledge graph completion:methods and progress [J]. Big Data Research, 2021, 7(3): 30-41.
[6]	Wenguang WANG. Knowledge graph reasoning: modern methods and applications [J]. Big Data Research, 2021, 7(3): 42-59.
[7]	Zhilei HU, Xiaolong JIN, Jianyun CHEN, Guanli HUANG. Construction, reasoning and applications of event graphs [J]. Big Data Research, 2021, 7(3): 80-96.
[8]	Huajun CHEN, Wen ZHANG, Chi-Man WONG, Ganqiang YE, Bo WEN, Wei ZHANG. Large scale pre-trained knowledge graph model and e-commerce application [J]. Big Data Research, 2021, 7(3): 97-115.
[9]	Qiang CHEN, Shiya DAI. Recognition method of accounting fraud risk based on financial knowledge graph [J]. Big Data Research, 2021, 7(3): 116-129.
[10]	Bing XIE, Xin PENG, Gang YIN, Xuandong LI, Jun WEI, Hailong SUN. Big data based intelligent software development methodology and environment [J]. Big Data Research, 2021, 7(1): 3-21.
[11]	Yanzhen ZOU, Min WANG, Bing XIE, Zeqi LIN. Software knowledge graph construction and Q＆amp;A technology based on big data [J]. Big Data Research, 2021, 7(1): 22-36.
[12]	Wei CHEN, Hongjie YE, Jiahong ZHOU, Jun WEI. An approach to automatically building Docker images by using domain knowledge [J]. Big Data Research, 2021, 7(1): 64-75.
[13]	Jian ZHANG, Xiangxin MENG, Hailong SUN, Xu WANG, Xudong LIU. Data driven intelligent collaboration of software developers [J]. Big Data Research, 2021, 7(1): 76-93.
[14]	Cheng CHEN, Yueguo CHEN, Chen LIU, Xiaotong LYU, Xiaoyong DU. Constructing and analyzing intention knowledge graphs [J]. Big Data Research, 2020, 6(2): 57-68.
[15]	Genlin ZANG, Yaqiang WANG, Qingrong WU, Chunli ZHAN, Yi LI. Model and construction method of the ontology of knowledge graph of smart city [J]. Big Data Research, 2020, 6(2): 96-106.