Learning to Answer Complex Questions over Knowledge Bases with Query Composition

Recent years have seen a surge of knowledge-based question answering (KB-QA) systems which provide crisp answers to user-issued questions by translating them to precise structured queries over a knowledge base (KB). A major challenge in KB-QA is bridging the gap between natural language expressions and the complex schema of the KB. As a result, existing methods focus on simple questions answerable with one main relation path in the KB and struggle with complex questions that require joining multiple relations. We propose a KB-QA system, TextRay, which answers complex questions using a novel decompose-execute-join approach. It constructs complex query patterns using a set of simple queries. It uses a semantic matching model which is able to learn simple queries using implicit supervision from question-answer pairs, thus eliminating the need for complex query patterns. Our proposed system significantly outperforms existing KB-QA systems on complex questions while achieving comparable results on simple questions.

[1]  Yue Zhang,et al.  Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural Networks , 2018, ArXiv.

[2]  Alexander J. Smola,et al.  Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning , 2017, ICLR.

[3]  Lei Zou,et al.  Answering Natural Language Questions by Subgraph Matching over Knowledge Graphs , 2018, IEEE Transactions on Knowledge and Data Engineering.

[4]  Phil Blunsom,et al.  Teaching Machines to Read and Comprehend , 2015, NIPS.

[5]  Lei Zou,et al.  Question Answering Over Knowledge Graphs: Question Understanding Via Template Decomposition , 2018, Proc. VLDB Endow..

[6]  Dongyan Zhao,et al.  Natural language question answering over RDF: a graph data driven approach , 2014, SIGMOD Conference.

[7]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[8]  Dongyan Zhao,et al.  Hybrid Question Answering over Knowledge Base and Free Text , 2016, COLING.

[9]  Andrew Chou,et al.  Semantic Parsing on Freebase from Question-Answer Pairs , 2013, EMNLP.

[10]  Yi Yang,et al.  S-MART: Novel Tree-based Structured Learning Algorithms Applied to Tweet Entity Linking , 2015, ACL.

[11]  Christopher D. Manning,et al.  Effective Approaches to Attention-based Neural Machine Translation , 2015, EMNLP.

[12]  Ming-Wei Chang,et al.  Maximum Margin Reward Networks for Learning from Explicit and Implicit Supervision , 2017, EMNLP.

[13]  Chen Liang,et al.  Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision , 2016, ACL.

[14]  Dongyan Zhao,et al.  Question Answering on Freebase via Relation Extraction and Textual Evidence , 2016, ACL.

[15]  Xuchen Yao,et al.  Information Extraction over Structured Data: Question Answering with Freebase , 2014, ACL.

[16]  Ming Zhou,et al.  Answering Questions with Complex Semantic Constraints on Open Knowledge Bases , 2015, CIKM.

[17]  Jonathan Berant,et al.  Semantic Parsing via Paraphrasing , 2014, ACL.

[18]  Wenhan Xiong,et al.  DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning , 2017, EMNLP.

[19]  Gerhard Weikum,et al.  Automated Template Generation for Question Answering over Knowledge Graphs , 2017, WWW.

[20]  Jason Weston,et al.  Open Question Answering with Weakly Supervised Embedding Models , 2014, ECML/PKDD.

[21]  Fei Li,et al.  Constructing an Interactive Natural Language Interface for Relational Databases , 2014, Proc. VLDB Endow..

[22]  Praveen Paritosh,et al.  Freebase: a collaboratively created graph database for structuring human knowledge , 2008, SIGMOD Conference.

[23]  Jonathan Berant,et al.  The Web as a Knowledge-Base for Answering Complex Questions , 2018, NAACL.

[24]  Ming-Wei Chang,et al.  Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base , 2015, ACL.

[25]  Hannah Bast,et al.  More Accurate Question Answering on Freebase , 2015, CIKM.

[26]  Bowen Zhou,et al.  Improved Neural Relation Detection for Knowledge Base Question Answering , 2017, ACL.

[27]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[28]  Seung-won Hwang,et al.  KBQA: Learning Question Answering over QA Corpora and Knowledge Bases , 2019, Proc. VLDB Endow..

[29]  Ming-Wei Chang,et al.  The Value of Semantic Parse Labeling for Knowledge Base Question Answering , 2016, ACL.

[30]  Kenny Q. Zhu,et al.  Knowledge Base Question Answering via Encoding of Complex Query Graphs , 2018, EMNLP.

[31]  Gerhard Weikum,et al.  YAGO2: A Spatially and Temporally Enhanced Knowledge Base from Wikipedia: Extended Abstract , 2013, IJCAI.

[32]  Ming-Wei Chang,et al.  Search-based Neural Structured Learning for Sequential Question Answering , 2017, ACL.

[33]  Jens Lehmann,et al.  Template-based question answering over RDF data , 2012, WWW.

[34]  Tiejun Zhao,et al.  Constraint-Based Question Answering with Knowledge Graph , 2016, COLING.