?作者?|?蔣錦昊

學(xué)校?|?中國人民大學(xué)博士生

研究方向?|?知識推理和問答系統(tǒng)

引言

基于知識圖譜的問答系統(tǒng)（Knowledge Based Question Answering, KBQA）目標(biāo)是根據(jù)提供的知識圖譜（Knowledge Graph, KG）回答事實(shí)型問題。本文總結(jié)了近年來研究KBQA任務(wù)的相關(guān)論文（共77篇），并分為簡單KBQA和復(fù)雜KBQA兩大類，每一類分為基于語義解析的方法、基于信息檢索的方法以及其它方法。簡單KBQA主要指通過在知識圖譜某個(gè)三元組即能解決問題；復(fù)雜KBQA主要指需要知識圖譜上的多個(gè)三元組才能定位到答案。

本列表論文是根據(jù)我們最新發(fā)布在IJCAI 2021上的綜述論文進(jìn)行整理的，以下是原論文鏈接，歡迎大家關(guān)注：

https://arxiv.org/abs/2105.11644

下述是相關(guān)研究者對原綜述論文的中文介紹，歡迎大家查看：

復(fù)雜知識庫問答最新綜述:方法、挑戰(zhàn)與解決方案

本文整理的論文列表已經(jīng)同步更新到 GitHub，也會(huì)進(jìn)行持續(xù)的更新，歡迎大家關(guān)注和 Star。

https://github.com/RUCAIBox/KBQAPapers

為方便讀者進(jìn)一步了解相關(guān)工作，本文盡可能直接給出了相關(guān)論文的 PDF 鏈接、官方主頁或者官方代碼實(shí)現(xiàn)，并標(biāo)注在論文名稱后面。但由于公眾號推文不支持外部鏈接，請到 GitHub 頁面查看鏈接。

綜述

按年份排序已有綜述：

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]

數(shù)據(jù)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]

簡單KBQA

4.1 基于語義解析的方法

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 基于信息檢索的方法

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] .

復(fù)雜KBQA

5.1 基于語義解析的方法

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 基于信息檢索的方法

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]

特別鳴謝

感謝 TCCI 天橋腦科學(xué)研究院對于 PaperWeekly 的支持。TCCI 關(guān)注大腦探知、大腦功能和大腦健康。

更多閱讀

#投 稿?通 道#

?讓你的文字被更多人看到?

如何才能讓更多的優(yōu)質(zhì)內(nèi)容以更短路徑到達(dá)讀者群體，縮短讀者尋找優(yōu)質(zhì)內(nèi)容的成本呢？答案就是：你不認(rèn)識的人。

總有一些你不認(rèn)識的人，知道你想知道的東西。PaperWeekly 或許可以成為一座橋梁，促使不同背景、不同方向的學(xué)者和學(xué)術(shù)靈感相互碰撞，迸發(fā)出更多的可能性。?

PaperWeekly 鼓勵(lì)高校實(shí)驗(yàn)室或個(gè)人，在我們的平臺上分享各類優(yōu)質(zhì)內(nèi)容，可以是最新論文解讀，也可以是學(xué)術(shù)熱點(diǎn)剖析、科研心得或競賽經(jīng)驗(yàn)講解等。我們的目的只有一個(gè)，讓知識真正流動(dòng)起來。

?????稿件基本要求：

? 文章確系個(gè)人原創(chuàng)作品，未曾在公開渠道發(fā)表，如為其他平臺已發(fā)表或待發(fā)表的文章，請明確標(biāo)注?

? 稿件建議以?markdown?格式撰寫，文中配圖以附件形式發(fā)送，要求圖片清晰，無版權(quán)問題

? PaperWeekly 尊重原作者署名權(quán)，并將為每篇被采納的原創(chuàng)首發(fā)稿件，提供業(yè)內(nèi)具有競爭力稿酬，具體依據(jù)文章閱讀量和文章質(zhì)量階梯制結(jié)算

?????投稿通道：

? 投稿郵箱：hr@paperweekly.site?

? 來稿請備注即時(shí)聯(lián)系方式（微信），以便我們在稿件選用的第一時(shí)間聯(lián)系作者

? 您也可以直接添加小編微信（pwbot02）快速投稿，備注：姓名-投稿

△長按添加PaperWeekly小編

????

現(xiàn)在，在「知乎」也能找到我們了

進(jìn)入知乎首頁搜索「PaperWeekly」

點(diǎn)擊「關(guān)注」訂閱我們的專欄吧

關(guān)于PaperWeekly

PaperWeekly 是一個(gè)推薦、解讀、討論、報(bào)道人工智能前沿論文成果的學(xué)術(shù)平臺。如果你研究或從事 AI 領(lǐng)域，歡迎在公眾號后臺點(diǎn)擊「交流群」，小助手將把你帶入 PaperWeekly 的交流群里。

總結(jié)

以上是生活随笔為你收集整理的KBQA相关论文分类整理：简单KBQA和复杂KBQA的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。