复杂知识库问答最新综述:方法、挑战与解决方案
论文题目:
A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutions
论文地址:
https://arxiv.org/abs/2105.11644
Complex KBQA Example
Main Challenge
Mainstream Approaches
基于语义解析的方法(SP)
(2)利用逻辑解析模块将编码后的问题转化为一个还未实例化(未填充具体实体关系)的逻辑形式。
(3)针对知识库,将逻辑形式与结构化的知识库进行语义对齐,进一步实例化上一步的逻辑形式。
(4)对知识库执行解析后的逻辑形式,通过知识库执行模块生成预测答案。
基于信息检索的方法(IR)
(1)确定中心实体,并从知识库中提取出特定于问题的子图。理想情况下,该图应该包含所有语文题相关的实体和关系。
(2)通过一个问题表示模块,对输入的问题进行编码,该模块分析问题的编码并输出推理指令,这些指令并非具有明确含义的,而是一个向量。
(3)基于图的推理模块通过基于向量的计算进行语义匹配,将信息沿着图中的相邻实体传播并聚合。
(4)利用答案排序模块根据推理结束时的推理状态对图中的实体进行排序。
Overview
Challenges and Solutions
5.1 Semantic Parsing-based Methods
5.1.1 Overview
5.1.2 Understanding Complex Semantics and Syntax
5.1.3 Parsing Complex Queries
5.1.4 Grounding with Large Search Space
[Lan 等人,2019c [18] ] 提出了一种迭代匹配模块,在每个搜索步骤中无需重新访问生成的查询图即可对问题进行解析。这种顺序展开过程只在回答多跳问题时有效,而对于有约束或数值运算的问题则无能为力。[Lan 和 Jiang, 2020 [19] ] 定义了更多的操作来支持三个典型的复杂查询,这可以大大减少搜索空间。
5.1.5 Training under Weak Supervision Signals
5.2 Information Retrieval-based Methods
5.2.1 Overview
5.2.2 Reasoning under Incomplete KB
5.2.3 Understanding Complex Semantics
5.2.4 Uninterpretable Reasoning
5.2.5 Training under Weak Supervision Signals
Conclusion and Future Directions
6.1 Evolutionary KBQA
6.2 Robust and Interpretable Models
6.3 More General Knowledge Base
参考文献
[1] Abdalghani Abujabal, Mohamed Yahya, Mirek Riedewald, and Gerhard Weikum. Automated template generation for question answering over knowledge graphs. In WWW, 2017.
[2] [Luo et al., 2018] Kangqi Luo, Fengli Lin, Xusheng Luo, and Kenny Q. Zhu. Knowledge base question answering via encoding of complex query graphs. In EMNLP, 2018.
[3] [Kapanipathi et al., 2020] Pavan Kapanipathi, Ibrahim Abdelaziz, Srinivas Ravishankar, Salim Roukos, Alexander G. Gray, Ram´on Fernandez 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 P. S. Luus, Ndivhuwo Makondo, Nandana Mihindukulasooriya, Tahira Naseem, Sumit Neelam, Lucian Popa, Revanth Gangi Reddy, Ryan Riegel, Gaetano Rossiello, Udit Sharma, G. P. Shrivatsa Bhargav, and Mo Yu. Question answering over knowledge bases by leveraging semantic parsing and neuro-symbolic reasoning. In AAAI, 2020.
[4] [Sun et al., 2020] Yawei Sun, Lingling Zhang, Gong Cheng, and Yuzhong Qu. SPARQA: skeleton-based semantic parsing for complex questions over knowledge bases. In AAAI, 2020.
[5] [Zhu et al., 2020] Shuguang Zhu, Xiang Cheng, and Sen Su. Knowledge-based question answering by tree-to-sequence learning. Neurocomputing, 2020.
[6] [Maheshwari et al., 2019] Gaurav Maheshwari, Priyansh Trivedi, Denis Lukovnikov, Nilesh Chakraborty, Asja Fischer, and Jens Lehmann. Learning to rank query graphs for complex question answering over knowledge graphs. In ISWC, 2019.
[7] [Chen et al., 2020] Yongrui Chen, Huiying Li, Yuncheng Hua, and Guilin Qi. Formal query building with query structure prediction for complex question answering over knowledge base. In IJCAI, 2020.
[8] [Cai and Yates, 2013] Qingqing Cai and Alexander Yates. Large-scale semantic parsing via schema matching and lexicon extension. In ACL, 2013.
[9] [Kwiatkowski et al., 2013] Tom Kwiatkowski, Eunsol Choi, Yoav Artzi, and Luke Zettlemoyer. Scaling semantic parsers with on-the-fly ontology matching. In EMNLP, 2013.
[10] [Reddy et al., 2014] Siva Reddy, Mirella Lapata, and Mark Steedman. Large-scale semantic parsing without questionanswer pairs. TACL, 2014.
[11] [Yih et al., 2015] Wen-tau Yih, Ming-Wei Chang, Xiaodong He, and Jianfeng Gao. Semantic parsing via staged query graph generation: Question answering with knowledge base. In ACL, 2015.
[12] [Bast and Haussmann, 2015] Hannah Bast and Elmar Haussmann. More accurate question answering on freebase. In CIKM, 2015.
[13] [Ding et al., 2019] Jiwei Ding, Wei Hu, Qixin Xu, and Yuzhong Qu. Leveraging frequent query substructures to generate formal queries for complex question answering. In EMNLP, 2019.
[14] [Hu et al., 2018b] Sen Hu, Lei Zou, and Xinbo Zhang. Astate-transition framework to answer complex questionsover knowledge base. In EMNLP, 2018.
[15] [Zheng et al., 2018b] Weiguo Zheng, Jeffrey Xu Yu, Lei Zou, and Hong Cheng. Question answering over knowledgegraphs: Question understanding via template decomposition. In VLDB Endow., 2018.
[16] [Bhutani et al., 2019] Nikita Bhutani, Xinyi Zheng, and H. V. Jagadish. Learning to answer complex questions over knowledge bases with query composition. In CIKM, 2019.
[17] [Chen et al., 2019] Zi-Yuan Chen, Chih-Hung Chang, Yi- Pei Chen, Jijnasa Nayak, and Lun-Wei Ku. UHop: An unrestricted-hop relation extraction framework for knowledge-based question answering. In NAACL, 2019.
[18] [Lan et al., 2019c] Yunshi Lan, Shuohang Wang, and Jing Jiang. Multi-hop knowledge base question answering with an iterative sequence matching model. In ICDM, 2019.
[19] [Lan and Jiang, 2020] Yunshi Lan and Jing Jiang. Query graph generation for answering multi-hop complex questions from knowledge bases. In ACL, 2020.
[20] [Liang et al., 2017] Chen Liang, Jonathan Berant, Quoc Le, Kenneth D. Forbus, and Ni Lao. Neural symbolic machines: Learning semantic parsers on Freebase with weak supervision. In ACL, 2017.
[21] [Qiu et al., 2020b] Yunqi Qiu, Kun Zhang, Yuanzhuo Wang, Xiaolong Jin, Long Bai, Saiping Guan, and Xueqi Cheng. Hierarchical query graph generation for complex question answering over knowledge graph. In CIKM, 2020.
[22] [Saha et al., 2019] Amrita Saha, Ghulam Ahmed Ansari, Abhishek Laddha, Karthik Sankaranarayanan, and Soumen Chakrabarti. Complex program induction for querying knowledge bases in the absence of gold programs. TACL, 2019.
[23] [Hua et al., 2020b] Yuncheng Hua, Yuan-Fang Li, Guilin Qi, Wei Wu, Jingyao Zhang, and Daiqing Qi. Less is more: Data-efficient complex question answering over knowledge bases. J. Web Semant., 2020.
[24] [Min et al., 2013] Bonan Min, Ralph Grishman, Li Wan, Chang Wang, and David Gondek. Distant supervision for relation extraction with an incomplete knowledge base. In NAACL-HLT, 2013.
[25] [Sun et al., 2018] Haitian Sun, Bhuwan Dhingra, Manzil Zaheer, Kathryn Mazaitis, Ruslan Salakhutdinov, and William Cohen. Open domain question answering using early fusion of knowledge bases and text. In EMNLP, 2018.
[26] [Sun et al., 2019] Haitian Sun, Tania Bedrax-Weiss, and William Cohen. Pullnet: Open domain question answering with iterative retrieval on knowledge bases and text. In EMNLP, 2019.
[27] [Xiong et al., 2019] Wenhan Xiong, Mo Yu, Shiyu Chang, Xiaoxiao Guo, and William Yang Wang. Improving question answering over incomplete kbs with knowledge-aware reader. In ACL, 2019.
[28] [Han et al., 2020a] Jiale Han, Bo Cheng, and Xu Wang. Open domain question answering based on text enhanced knowledge graph with hyperedge infusion. In EMNLP, 2020.
[29] [Saxena et al., 2020] Apoorv Saxena, Aditay Tripathi, and Partha Talukdar. Improving multi-hop question answering over knowledge graphs using knowledge base embeddings. In ACL, 2020.
[30] [Miller et al., 2016] Alexander Miller, Adam Fisch, Jesse Dodge, Amir-Hossein Karimi, Antoine Bordes, and Jason Weston. Key-value memory networks for directly reading documents. In EMNLP, 2016.
[31] [Zhou et al., 2018] Mantong Zhou, Minlie Huang, and Xiaoyan Zhu. An interpretable reasoning network for multirelation question answering. In COLING, 2018.
[32] [Xu et al., 2019] Kun Xu, Yuxuan Lai, Yansong Feng, and Zhiguo Wang. Enhancing key-value memory neural networks for knowledge based question answering. In NAACL-HLT, 2019.
[33] [He et al., 2021] Gaole He, Yunshi Lan, Jing Jiang, Wayne Xin Zhao, and Ji-Rong Wen. Improving multihop knowledge base question answering by learning intermediate supervision signals. In WSDM, 2021
[34] [Han et al., 2020b] Jiale Han, Bo Cheng, and Xu Wang. Two-phase hypergraph based reasoning with dynamic relations for multi-hop kbqa. In IJCAI, 2020.
[35] [Qiu et al., 2020a] Yunqi Qiu, Yuanzhuo Wang, Xiaolong Jin, and Kun Zhang. Stepwise reasoning for multi-relation question answering over knowledge graph with weak supervision. In WSDM, 2020.
[36] [Zhang et al., 2018] Yuyu Zhang, Hanjun Dai, Zornitsa Kozareva, Alexander J Smola, and Le Song. Variational reasoning for question answering with knowledge graph. In AAAI, 2018.
[37] [Abujabal et al., 2018] Abdalghani Abujabal, Rishiraj Saha Roy, Mohamed Yahya, and Gerhard Weikum. Neverending learning for open-domain question answering over knowledge bases. In WWW, 2018.
[38] [Zheng et al., 2018a] Weiguo Zheng, Hong Cheng, Jeffrey Xu Yu, Lei Zou, and Kangfei Zhao. Never-ending learning for open-domain question answering over knowledge bases. In InfoScience, 2018.
[39] [Gu et al., 2020] Yu Gu, Sue Kase, Michelle Vanni, Brian M. Sadler, Percy Liang, Xifeng Yan, and Yu Su. Beyond I.I.D.: three levels of generalization for question answering on knowledge bases. In WWW, 2020.
[40] [Keysers et al., 2020] Daniel Keysers, Nathanael Sch¨arli, Nathan Scales, Hylke Buisman, Daniel Furrer, Sergii Kashubin, Nikola Momchev, Danila Sinopalnikov, Lukasz Stafiniak, Tibor Tihon, Dmitry Tsarkov, Xiao Wang, Marc van Zee, and Olivier Bousquet. Measuring compositional generalization: A comprehensive method on realistic data. In ICLR, 2020.
[41] [Xie et al., 2017] Ruobing Xie, Zhiyuan Liu, Huanbo Luan, and Maosong Sun. Image-embodied knowledge representation learning. In IJCAI, pages 3140–3146, 2017.
[42] [He et al., 2020] Gaole He, Junyi Li,Wayne Xin Zhao, Peiju Liu, and Ji-Rong Wen. Mining implicit entity preference from user-item interaction data for knowledge graph completion via adversarial learning. In WWW, 2020.
[43] [Hudson and Manning, 2019] Drew A. Hudson and Christopher D. Manning. Learning by abstraction: The neural state machine. In NeurIPS, 2019.
[44] [Petroni et al., 2019] Fabio Petroni, Tim Rockt¨aschel, Sebastian Riedel, Patrick S. H. Lewis, Anton Bakhtin, Yuxiang Wu, and Alexander H. Miller. Language models as knowledge bases? In EMNLP, 2019.
[45] [Bouraoui et al., 2020] Zied Bouraoui, Jos´e Camacho- Collados, and Steven Schockaert. Inducing relational knowledge from BERT. In AAAI, 2020.
[46] [Jiang et al., 2020] Zhengbao Jiang, Frank F. Xu, Jun Araki, and Graham Neubig. How can we know what language models know. TACL, 2020.
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。