©作者 | 蒋锦昊

学校 | 中国人民大学博士生

研究方向 | 知识推理和问答系统

引言

基于知识图谱的问答系统（Knowledge Based Question Answering, KBQA）目标是根据提供的知识图谱（Knowledge Graph, KG）回答事实型问题。本文总结了近年来研究KBQA任务的相关论文（共77篇），并分为简单KBQA和复杂KBQA两大类，每一类分为基于语义解析的方法、基于信息检索的方法以及其它方法。简单KBQA主要指通过在知识图谱某个三元组即能解决问题；复杂KBQA主要指需要知识图谱上的多个三元组才能定位到答案。

本列表论文是根据我们最新发布在IJCAI 2021上的综述论文进行整理的，以下是原论文链接，欢迎大家关注：

https://arxiv.org/abs/2105.11644

下述是相关研究者对原综述论文的中文介绍，欢迎大家查看：

复杂知识库问答最新综述:方法、挑战与解决方案

本文整理的论文列表已经同步更新到 GitHub，也会进行持续的更新，欢迎大家关注和 Star。

https://github.com/RUCAIBox/KBQAPapers

为方便读者进一步了解相关工作，本文尽可能直接给出了相关论文的 PDF 链接、官方主页或者官方代码实现，并标注在论文名称后面。但由于公众号推文不支持外部链接，请到 GitHub 页面查看链接。

综述

按年份排序已有综述：

1. Core techniques of question answering systems over knowledge bases: a survey. Dennis Diefenbach, Vanessa Lopez, Kamal Singh, Pierre Maret. Knowledge and Information Systems(2017). [PDF]

2. A Survey of Question Answering over Knowledge Base. Peiyun Wu, Xiaowang Zhang, Zhiyong Feng. CCIS(2019). [PDF]

3. A Survey on Complex Question Answering over Knowledge Base: Recent Advances and Challenges. Bin Fu, Yunqi Qiu, Chengguang Tang, Yang Li, Haiyang Yu, Jian Sun. arXiv(2020). [PDF]

4. Introduction to Neural Network based Approaches for Question Answering over Knowledge Graphs. Nilesh Chakraborty, Denis Lukovnikov, Gaurav Maheshwari, Priyansh Trivedi, Jens Lehmann, Asja Fischer. WIDM(2021). [PDF]

5. A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutions. Yunshi Lan, Gaole He, Jinhao Jiang, Jing Jiang, Wayne Xin Zhao, Ji-Rong Wen. IJCAI(2021). [PDF]

数据集

1. WebQuestions: "Semantic parsing on freebase from question-answer pairs". EMNLP(2013). [PDF] [Homepage]

2. ComplexQuestions: "Constraint based question answering with knowledge graph". COLING(2016). [PDF] [Homepage]

3. WebQuestionsSP: "The value of semantic parse labeling for knowledge base question answering". ACL(2016). [PDF] [Homepage]

4. ComplexWebQuestions: "The web as a knowledge-base for answering complex questions". NAACL(2018). [PDF] [Homepage]

5. QALD: "Evaluating question answering over linked data". Web Semantics Science Services And Agents On The World Wide Web(2013). [PDF] [Homepage]

6. LC-QuAD 1.0: "Lc-quad: A corpus for complex question answering over knowledge graphs". ISWC(2017). [PDF] [Homepage]

7. LC-QuAD 2.0: "“Lc-quad 2.0: A large dataset for complex question answering over wikidata and dbpedia". ISWC(2019). [PDF] [Homepage]

8. MetaQA Vanilla: "Variational reasoning for question answering with knowledge graph". AAAI(2018). [PDF] [Homepage]

9. CFQ: "Measuring compositional generalization: A comprehensive method on realistic data". ICLR(2020). [PDF] [Homepage]

10. KQA Pro: "Kqa pro: A large diagnostic dataset for complex question answering over knowledge base". arXiv(2020). [PDF]  [Homepage]

11. GrailQA: "Beyond I.I.D.: three levels of generalization for question answering on knowledge bases". WWW(2021). [PDF] [Homepage]

简单KBQA

4.1 基于语义解析的方法

Template-based question answering over RDF data. Unger, Christina, Lorenz Bühmann, Jens Lehmann, A. N. Ngomo, D. Gerber, P. Cimiano. WWW(2012). [PDF]

Large-scale semantic parsing via schema matching and lexicon extension. Qingqing Cai, Alexander Yates. ACL(2013). [PDF]

Semantic parsing on freebase from question-answer pairs. Jonathan Berant, Andrew Chou, Roy Frostig, Percy Liang. EMNLP(2013). [PDF]

Large-scale semantic parsing without question-answer pairs. Siva Reddy, Mirella Lapata, Mark Steedman. TACL(2014). [PDF]

Semantic parsing for single relation question answering. Wen-tau Yih, Xiaodong He, Christopher Meek. ACL(2014). [PDF]

Information extraction over structured data: Question answering with Freebase. Xuchen Yao, Benjamin Van Durme. ACL(2014). [PDF]

Semantic parsing via staged query graph generation: Question answering with knowledge base. Wen-tau Yih, Ming-Wei Chang, Xiaodong He, Jianfeng Gao. ACL(2015). [PDF]

Simple question answering by attentive convolutional neural network. Wenpeng Yin, Mo Yu, Bing Xiang, Bowen Zhou, Hinrich Schütze. COLING(2016). [PDF]

Learning to compose neural networks for question answering. Jacob Andreas, Marcus Rohrbach, Trevor Darrell, Dan Klein. NAACL(2016). [PDF] [Code]

Knowledge base question answering with a matching-aggregation model and question-specific contextual relations. Yunshi Lan, Shuohang Wang, Jing Jiang. TASLP(2019). [PDF]

4.2 基于信息检索的方法

1. Open question answering with weakly supervised embedding models. Antoine Bordes, Jason Weston, Nicolas Usunier. Machine Learning and Knowledge Discovery in Databases(2014). [PDF]

2. Question answering with subgraph embeddings. Antoine Bordes, Sumit Chopra, Jason Weston. EMNLP(2014). [PDF]

3. Larges cale simple question answering with memory networks. Antoine Bordes, Nicolas Usunier, Sumit Chopra, Jason Weston. arXiv(2015). [PDF] [Code]

4. Question answering over freebase with multi-column convolutional neural networks. Li Dong, Furu Wei, Ming Zhou, Ke Xu. ACL(2015). [PDF]

5. Question answering over knowledge base using factual memory networks. Sarthak Jain. NAACL(2016). [PDF]

6. An end-to-end model for question answering over knowledge base with cross-attention combining global knowledge. Yanchao Hao, Yuanzhe Zhang, Kang Liu, Shizhu He, Zhanyi Liu, Hua Wu, Jun Zhao. ACL(2017). [PDF]

7. Bidirectional Attentive Memory Networks for Question Answering over Knowledge Bases. Yu Chen, Lingfei Wu, Mohammed J. Zaki. NAACL(2019). [PDF] [Code]

4.3 其他方法

1. Hybrid question answering over knowledge base and free text. Kun Xu, Yansong Feng, Songfang Huang, Dongyan Zhao. COLING(2016). [PDF]

2. Question answering on freebase via relation extraction and textual evidence. Kun Xu, Siva Reddy, Yansong Feng, Songfang Huang, Dongyan Zhao. ACL(2016). [PDF] [Code]

3. Improved neural relation detection for knowledge base question answering. Mo Yu, Wenpeng Yin, Kazi Saidul Hasan, Cicero dos Santos, Bing Xiang, Bowen Zhou. ACL(2017). [PDF]

4. KBQA: learning question answering over QA corpora and knowledge bases. Wanyun Cui, Yanghua Xiao, Haixun Wang, Yangqiu Song, Seung-won Hwang, Wei Wang. VLDB(2017). [PDF]

5. Knowledge base question answering with topic units. Yunshi Lan , Shuohang Wang, Jing Jiang. IJCAI(2019). [PDF]

6. Retrieval, Re-ranking and Multi-task Learning for Knowledge-Base Question Answering. Zhiguo Wang, Patrick Ng, Ramesh Nallapati, Bing Xiang. EACL(2021). [PDF] .

复杂KBQA

5.1 基于语义解析的方法

1. Automated template generation for question answering over knowledge graphs. Abujabal, Abdalghani, Mohamed Yahya, Mirek Riedewald, G. Weikum. WWW(2017). [PDF]

2. Neural symbolic machines: Learning semantic parsers on Freebase with weak supervision. Chen Liang, Jonathan Berant, Quoc Le, Kenneth D. Forbus, Ni Lao. ACL(2017). [PDF] [Code]

3. Knowledge base question answering via encoding of complex query graphs. Kangqi Luo, Fengli Lin, Xusheng Luo, Kenny Zhu. EMNLP(2018). [PDF] [Code]

4. Neverending learning for open-domain question answering over knowledge bases. Abujabal, Abdalghani, Rishiraj Saha Roy, Mohamed Yahya, G. Weikum. WWW(2018). [PDF]

5. A state-transition framework to answer complex questions over knowledge base. Sen Hu, Lei Zou, Xinbo Zhang. EMNLP(2018). [PDF]

6. Question answering over knowledge graphs: Question understanding via template decomposition. Weiguo Zheng, Jeffrey Xu Yu, Lei Zou, Hong Cheng. VLDB(2018). [PDF]

7. Learning to answer complex questions over knowledge bases with query composition. Bhutani, Nikita, Xinyi Zheng, H. Jagadish. CIKM(2019). [PDF]

8. UHop: An unrestricted-hop relation extraction framework for knowledge-based question answering. Zi-Yuan Chen, Chih-Hung Chang, Yi-Pei Chen, Jijnasa Nayak, Lun-Wei Ku. NAACL(2019). [PDF]

9. Multi-hop knowledge base question answering with an iterative sequence matching model. * Yunshi Lan, Shuohang Wang, Jing Jiang*. ICDM(2019). [PDF]

10. Learning to rank query graphs for complex question answering over knowledge graphs. Gaurav Maheshwari, Priyansh Trivedi, Denis Lukovnikov, Nilesh Chakraborty, Asja Fischer, Jens Lehmann. ISWC(2019). [PDF] [Code]

11. Complex program induction for querying knowledge bases in the absence of gold programs. Amrita Saha, Ghulam Ahmed Ansari, Abhishek Laddha, Karthik Sankaranarayanan, Soumen Chakrabarti. TACL(2019). [PDF][Code]

12. Leveraging Frequent Query Substructures to Generate Formal Queries for Complex Question Answering. Jiwei Ding, Wei Hu, Qixin Xu, Yuzhong Qu. EMNLP(2019). [PDF]

13. Hierarchical query graph generation for complex question answering over knowledge graph. Qiu, Yunqi, K. Zhang, Yuanzhuo Wang, Xiaolong Jin, Long Bai, Saiping Guan, Xueqi Cheng. CIKM(2020). [PDF]

14. SPARQA: skeleton-based semantic parsing for complex questions over knowledge bases. Yawei Sun, Lingling Zhang, Gong Cheng, Yuzhong Qu. AAAI(2020). [PDF] [Code]

15. Formal query building with query structure prediction for complex question answering over knowledge base. Yongrui Chen, Huiying Li, Yuncheng Hua, Guilin Qi. IJCAI(2020). [PDF] [Code]

16. Query graph generation for answering multi-hop complex questions from knowledge bases. Yunshi Lan, Jing Jiang. ACL(2020). [PDF] [Code]

17. Answering Complex Questions by Combining Information from Curated and Extracted Knowledge Bases. Nikita Bhutani, Xinyi Zheng, Kun Qian, Yunyao Li, H. Jagadish. ACL(2020). [PDF]

18. Leveraging abstract meaning representation for knowledge base question answering. Pavan Kapanipathi, Ibrahim Abdelaziz, Srinivas Ravishankar, Salim Roukos, Alexander Gray, Ramon Astudillo, Maria Chang, Cristina Cornelio, Saswati Dana, Achille Fokoue, Dinesh Garg, Alfio Gliozzo, Sairam Gurajada, Hima Karanam, Naweed Khan, Dinesh Khandelwal, Young-Suk Lee, Yunyao Li, Francois Luus, Ndivhuwo Makondo, Nandana Mihindukulasooriya, Tahira Naseem, Sumit Neelam, Lucian Popa, Revanth Reddy, Ryan Riegel, Gaetano Rossiello, Udit Sharma, G P Shrivatsa Bhargav, Mo Yu. Findings of ACL(2021). [PDF]

5.2 基于信息检索的方法

1. Open domain question answering based on text enhanced knowledge graph with hyperedge infusion. Jiale Han, Bo Cheng, Xu Wang. Findings of EMNLP(2018). [PDF]

2. Open domain question answering using early fusion of knowledge bases and text. Haitian Sun, Bhuwan Dhingra, Manzil Zaheer, Kathryn Mazaitis, Ruslan Salakhutdinov, William Cohen. EMNLP(2018). [PDF] [Code]

3. An interpretable reasoning network for multi-relation question answering. Mantong Zhou, Minlie Huang, Xiaoyan Zhu. COLING(2018). [PDF] [Code]

4. Variational reasoning for question answering with knowledge graph. Yuyu Zhang, Hanjun Dai, Zornitsa Kozareva, Alexander J. Smola, Le Song. AAAI(2018). [PDF] [Code]

5. Enhancing key-value memory neural networks for knowledge based question answering. Kun Xu, Yuxuan Lai, Yansong Feng, Zhiguo Wang. NAACL(2019). [PDF]

6. Pullnet: Open domain question answering with iterative retrieval on knowledge bases and text. Haitian Sun, Tania Bedrax-Weiss, William W. Cohen. EMNLP(2019). [PDF]

7. Improving question answering over incomplete kbs with knowledge-aware reader. Wenhan Xiong, Mo Yu, Shiyu Chang, Xiaoxiao Guo, William Yang Wang. ACL(2019). [PDF] [Code]

8. Answering Complex Questions by Joining Multi-Document Evidence with Quasi Knowledge Graphs. Xiaolu Lu, Soumajit Pramanik, Rishiraj Saha Roy, Abdalghani Abujabal, Yafang Wang, Gerhard Weikum. SIGIR(2019). [PDF]

9. Two-phase Hypergraph Based Reasoning With Dynamic Relations For Multi-Hop KBQA. Jiale Han, Bo Cheng, Xu Wang. IJCAI(2020). [PDF]

10. Improving multi-hop question answering over knowledge graphs using knowledge base embeddings. Apoorv Saxena, Aditay Tripathi, Partha Talukdar. ACL(2020). [PDF] [Code]

11. Stepwise reasoning for multi-relation question answering over knowledge graph with weak supervision. Qiu, Yunqi, Yuanzhuo Wang, Xiaolong Jin, K. Zhang. WSDM(2020). [PDF] [Code]

12. Modeling Long-distance Node Relations for KBQA with Global Dynamic Graph. Xu Wang, Shuai Zhao, Jiale Han, Bo Cheng, Hao Yang, Jianchang Ao, Zhenzi Li. COLING(2020). [PDF]

13. Improving multi-hop knowledge base question answering by learning intermediate supervision signals. Gaole He, Yunshi Lan, Jing Jiang, Wayne Xin Zhao, Ji-Rong Wen. WSDM(2021). [PDF] [Code]

5.3 其它方法

1. QUINT: Interpretable Question Answering over Knowledge Bases. Abdalghani Abujabal, Rishiraj Saha Roy, Mohamed Yahya, Gerhard Weikum. EMNLP(2017). [PDF]

2. Modeling Semantics with Gated Graph Neural Networks for Knowledge Base Question Answering. Daniil Sorokin, Iryna Gurevych. COLING(2018). [PDF] [Code]

3. PERQ: Predicting, Explaining, and Rectifying Failed Questions in KB-QA Systems. Zhiyong Wu, Ben Kao, Tien-Hsuan Wu, Pengcheng Yin, Qun Liu. WSDM(2020). [PDF]

4. Few-Shot Complex Knowledge Base Question Answering via Meta Reinforcement Learning. Yuncheng Hua, Yuan-Fang Li, Gholamreza Haffari, Guilin Qi, Tongtong Wu. EMNLP(2020). [PDF] [Code]

5. Question Answering Over Temporal Knowledge Graphs. Apoorv Saxena, Soumen Chakrabarti, Partha Talukdar. ACL(2021). [PDF] [Code]

6. Improving Zero-Shot Cross-lingual Transfer for Multilingual Question Answering over Knowledge Graph. Yucheng Zhou, Xiubo Geng, Tao Shen, Wenqiang Zhang, Daxin Jiang. NAACL(2021). [PDF]

7. Complex Question Answering on knowledge graphs using machine translation and multi-task learning. Saurabh Srivastava, Mayur Patidar, Sudip Chowdhury, Puneet Agarwal, Indrajit Bhattacharya, Gautam Shroff. EACL(2021). [PDF]

特别鸣谢

感谢 TCCI 天桥脑科学研究院对于 PaperWeekly 的支持。TCCI 关注大脑探知、大脑功能和大脑健康。

更多阅读

#投 稿 通 道#

 让你的文字被更多人看到 

如何才能让更多的优质内容以更短路径到达读者群体，缩短读者寻找优质内容的成本呢？答案就是：你不认识的人。

总有一些你不认识的人，知道你想知道的东西。PaperWeekly 或许可以成为一座桥梁，促使不同背景、不同方向的学者和学术灵感相互碰撞，迸发出更多的可能性。

PaperWeekly 鼓励高校实验室或个人，在我们的平台上分享各类优质内容，可以是最新论文解读，也可以是学术热点剖析、科研心得或竞赛经验讲解等。我们的目的只有一个，让知识真正流动起来。

???? 稿件基本要求：

• 文章确系个人原创作品，未曾在公开渠道发表，如为其他平台已发表或待发表的文章，请明确标注

• 稿件建议以 markdown 格式撰写，文中配图以附件形式发送，要求图片清晰，无版权问题

• PaperWeekly 尊重原作者署名权，并将为每篇被采纳的原创首发稿件，提供业内具有竞争力稿酬，具体依据文章阅读量和文章质量阶梯制结算

???? 投稿通道：

• 投稿邮箱：hr@paperweekly.site

• 来稿请备注即时联系方式（微信），以便我们在稿件选用的第一时间联系作者

• 您也可以直接添加小编微信（pwbot02）快速投稿，备注：姓名-投稿

△长按添加PaperWeekly小编

????

现在，在「知乎」也能找到我们了

进入知乎首页搜索「PaperWeekly」

点击「关注」订阅我们的专栏吧

关于PaperWeekly

PaperWeekly 是一个推荐、解读、讨论、报道人工智能前沿论文成果的学术平台。如果你研究或从事 AI 领域，欢迎在公众号后台点击「交流群」，小助手将把你带入 PaperWeekly 的交流群里。