Knowledge Base Question Answering through Recursive Hypergraphs

Knowledge Base Question Answering (KBQA) is the problem of predicting an answer for a factoid question over a given knowledge base (KB). Answering questions typically requires reasoning over multiple links in the given KB. Humans tend to answer questions by grouping different objects to perform reasoning over acquired knowledge. Hypergraphs provide a natural tool to model group relationships. In this work, inspired by typical human intelligence, we propose a new method for KBQA based on hypergraphs. Existing methods for KBQA, though effective, do not explicitly incorporate the recursive relational group structure in the given KB. Our method, which we name RecHyperNet (Recursive Hypergraph Network), exploits a new way of modelling KBs through recursive hypergraphs to organise such group relationships in KBs. Experiments on multiple KBQA benchmarks demonstrate the effectiveness of the proposed RecHyperNet. We have released the code.

[1]  Lei Li,et al.  Dynamically Fused Graph Network for Multi-hop Reasoning , 2019, ACL.

[2]  Xiaojun Wan,et al.  SemSUM: Semantic Dependency Guided Neural Abstractive Summarization , 2020, AAAI.

[3]  Ruslan Salakhutdinov,et al.  Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text , 2018, EMNLP.

[4]  Diego Marcheggiani,et al.  Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling , 2017, EMNLP.

[5]  Jason Weston,et al.  Key-Value Memory Networks for Directly Reading Documents , 2016, EMNLP.

[6]  Ming Tu,et al.  Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documents , 2020, AAAI.

[7]  Ting Liu,et al.  Is Graph Structure Necessary for Multi-hop Reasoning? , 2020, ArXiv.

[8]  Bowen Zhou,et al.  Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs , 2019, ACL.

[9]  Yansong Feng,et al.  Semantic Graphs for Generating Deep Questions , 2020, ACL.

[10]  Yu Cao,et al.  BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering , 2019, NAACL.

[11]  Yue Gao,et al.  Hypergraph Neural Networks , 2018, AAAI.

[12]  Khalil Sima'an,et al.  Graph Convolutional Encoders for Syntax-aware Neural Machine Translation , 2017, EMNLP.

[13]  Partha P. Talukdar,et al.  Graph-based Deep Learning in Natural Language Processing , 2019, EMNLP/IJCNLP.

[14]  Xinwei Feng,et al.  Machine Reading Comprehension Using Structural Knowledge Graph-aware Network , 2019, EMNLP.

[15]  Jason Weston,et al.  Translating Embeddings for Modeling Multi-relational Data , 2013, NIPS.

[16]  Kai Wang,et al.  Relational Graph Attention Network for Aspect-based Sentiment Analysis , 2020, ACL.

[17]  Xuanyu Zhang,et al.  CFGNN: Cross Flow Graph Neural Networks for Question Answering on Complex Tables , 2020, AAAI.

[18]  Nicola De Cao,et al.  Question Answering by Reasoning Across Documents with Graph Convolutional Networks , 2018, NAACL.

[19]  Xinwei Feng,et al.  Capturing Sentence Relations for Answer Sentence Selection with Multi-Perspective Graph Encoding , 2020, AAAI.

[20]  Apoorv Saxena,et al.  Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings , 2020, ACL.

[21]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

[22]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[23]  Xu Wang,et al.  Two-Phase Hypergraph Based Reasoning with Dynamic Relations for Multi-Hop KBQA , 2020, IJCAI.

[24]  Furu Wei,et al.  Language Generation with Multi-hop Reasoning on Commonsense Knowledge Graph , 2020, EMNLP.

[25]  William W. Cohen,et al.  PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text , 2019, EMNLP.

[26]  Xiang Ren,et al.  KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning , 2019, EMNLP.

[27]  Wei Chu,et al.  Question Directed Graph Attention Network for Numerical Reasoning over Text , 2020, EMNLP.

[28]  Chang Zhou,et al.  Cognitive Graph for Multi-Hop Reading Comprehension at Scale , 2019, ACL.

[29]  Guillaume Bouchard,et al.  Complex Embeddings for Simple Link Prediction , 2016, ICML.

[30]  Jian Sun,et al.  A Survey on Complex Question Answering over Knowledge Base: Recent Advances and Challenges , 2020, ArXiv.

[31]  Nojun Kwak,et al.  Textbook Question Answering with Multi-modal Context Graph Understanding and Self-supervised Open-set Comprehension , 2018, ACL.

[32]  Wenhan Xiong,et al.  Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader , 2019, ACL.

[33]  Omer Levy,et al.  RoBERTa: A Robustly Optimized BERT Pretraining Approach , 2019, ArXiv.

[34]  Cliff Joslyn,et al.  Ubergraphs: A Definition of a Recursive Hypergraph Structure , 2017, ArXiv.

[35]  Partha Pratim Talukdar,et al.  HyperGCN: A New Method of Training Graph Convolutional Networks on Hypergraphs , 2018 .

[36]  Wanxiang Che,et al.  Document Modeling with Graph Attention Networks for Multi-grained Machine Reading Comprehension , 2020, ACL.

[37]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[38]  Le Song,et al.  Variational Reasoning for Question Answering with Knowledge Graph , 2017, AAAI.

[39]  Jun Yan,et al.  Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering , 2020, EMNLP.

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

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

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

[43]  Telmo Menezes,et al.  Semantic Hypergraphs , 2019, ArXiv.