Knowledge Base Question Answering by Case-based Reasoning over Subgraphs

Question answering (QA) over knowledge bases (KBs) is challenging because of the diverse, essentially unbounded, types of reasoning patterns needed. However, we hypothesize in a large KB, reasoning patterns required to answer a query type reoccur for various entities in their respective subgraph neighborhoods. Leveraging this structural similarity between local neighborhoods of different subgraphs, we introduce a semiparametric model (CBR-SUBG) with (i) a nonparametric component that for each query, dynamically retrieves other similar $k$-nearest neighbor (KNN) training queries along with query-specific subgraphs and (ii) a parametric component that is trained to identify the (latent) reasoning patterns from the subgraphs of KNN queries and then apply them to the subgraph of the target query. We also propose an adaptive subgraph collection strategy to select a query-specific compact subgraph, allowing us to scale to full Freebase KB containing billions of facts. We show that CBR-SUBG can answer queries requiring subgraph reasoning patterns and performs competitively with the best models on several KBQA benchmarks. Our subgraph collection strategy also produces more compact subgraphs (e.g. 55\% reduction in size for WebQSP while increasing answer recall by 4.85\%)\footnote{Code, model, and subgraphs are available at \url{https://github.com/rajarshd/CBR-SUBG}}.

[1]  Rajarshi Das,et al.  Case-based Reasoning for Natural Language Queries over Knowledge Bases , 2021, EMNLP.

[2]  Jing Jiang,et al.  Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals , 2021, WSDM.

[3]  Mike Lewis,et al.  Nearest Neighbor Machine Translation , 2020, ICLR.

[4]  Yusuke Miyao,et al.  An empirical analysis of existing systems and datasets toward general simple question answering , 2020, COLING.

[5]  Zhangyang Wang,et al.  Graph Contrastive Learning with Augmentations , 2020, NeurIPS.

[6]  Manzil Zaheer,et al.  Probabilistic Case-based Reasoning in Knowledge Bases , 2020, FINDINGS.

[7]  William W. Cohen,et al.  Facts as Experts: Adaptable and Interpretable Neural Memory over Symbolic Knowledge , 2020, ArXiv.

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

[9]  Yuxiao Dong,et al.  GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training , 2020, KDD.

[10]  Liang Wang,et al.  Deep Graph Contrastive Representation Learning , 2020, ArXiv.

[11]  Kaveh Hassani,et al.  Contrastive Multi-View Representation Learning on Graphs , 2020, ICML.

[12]  Eunsol Choi,et al.  Entities as Experts: Sparse Memory Access with Entity Supervision , 2020, EMNLP.

[13]  Danqi Chen,et al.  Dense Passage Retrieval for Open-Domain Question Answering , 2020, EMNLP.

[14]  William W. Cohen,et al.  Scalable Neural Methods for Reasoning With a Symbolic Knowledge Base , 2020, ICLR.

[15]  Manzil Zaheer,et al.  A Simple Approach to Case-Based Reasoning in Knowledge Bases , 2020, AKBC.

[16]  Jure Leskovec,et al.  Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings , 2020, ICLR.

[17]  Geoffrey E. Hinton,et al.  A Simple Framework for Contrastive Learning of Visual Representations , 2020, ICML.

[18]  Xiaolong Jin,et al.  Stepwise Reasoning for Multi-Relation Question Answering over Knowledge Graph with Weak Supervision , 2020, WSDM.

[19]  William L. Hamilton,et al.  Inductive Relation Prediction by Subgraph Reasoning , 2019, ICML.

[20]  Omer Levy,et al.  Generalization through Memorization: Nearest Neighbor Language Models , 2019, ICLR.

[21]  Jian Tang,et al.  InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization , 2019, ICLR.

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

[23]  Peng Wu,et al.  Learning Representation Mapping for Relation Detection in Knowledge Base Question Answering , 2019, ACL.

[24]  Jeffrey Ling,et al.  Matching the Blanks: Distributional Similarity for Relation Learning , 2019, ACL.

[25]  Hui Jiang,et al.  FreebaseQA: A New Factoid QA Data Set Matching Trivia-Style Question-Answer Pairs with Freebase , 2019, NAACL.

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

[27]  Jingyuan Zhang,et al.  Knowledge Graph Embedding Based Question Answering , 2019, WSDM.

[28]  Jure Leskovec,et al.  How Powerful are Graph Neural Networks? , 2018, ICLR.

[29]  Jian-Yun Nie,et al.  RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space , 2018, ICLR.

[30]  Percy Liang,et al.  A Retrieve-and-Edit Framework for Predicting Structured Outputs , 2018, NeurIPS.

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

[32]  Yong Wang,et al.  Search Engine Guided Neural Machine Translation , 2018, AAAI.

[33]  Yixin Chen,et al.  Link Prediction Based on Graph Neural Networks , 2018, NeurIPS.

[34]  Jimmy J. Lin,et al.  Strong Baselines for Simple Question Answering over Knowledge Graphs with and without Neural Networks , 2017, NAACL.

[35]  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.

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

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

[38]  Max Welling,et al.  Modeling Relational Data with Graph Convolutional Networks , 2017, ESWC.

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

[40]  Samuel S. Schoenholz,et al.  Neural Message Passing for Quantum Chemistry , 2017, ICML.

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

[42]  Jason Weston,et al.  Reading Wikipedia to Answer Open-Domain Questions , 2017, ACL.

[43]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

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

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

[46]  Alán Aspuru-Guzik,et al.  Convolutional Networks on Graphs for Learning Molecular Fingerprints , 2015, NIPS.

[47]  Andrew McCallum,et al.  Compositional Vector Space Models for Knowledge Base Completion , 2015, ACL.

[48]  Jianfeng Gao,et al.  Embedding Entities and Relations for Learning and Inference in Knowledge Bases , 2014, ICLR.

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

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

[51]  Eunsol Choi,et al.  Scaling Semantic Parsers with On-the-Fly Ontology Matching , 2013, EMNLP.

[52]  Aapo Hyvärinen,et al.  Noise-contrastive estimation: A new estimation principle for unnormalized statistical models , 2010, AISTATS.

[53]  Ah Chung Tsoi,et al.  The Graph Neural Network Model , 2009, IEEE Transactions on Neural Networks.

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

[55]  Luke S. Zettlemoyer,et al.  Online Learning of Relaxed CCG Grammars for Parsing to Logical Form , 2007, EMNLP.

[56]  Luke S. Zettlemoyer,et al.  Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars , 2005, UAI.

[57]  Yann LeCun,et al.  Learning a similarity metric discriminatively, with application to face verification , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[58]  Raymond J. Mooney,et al.  Learning to Parse Database Queries Using Inductive Logic Programming , 1996, AAAI/IAAI, Vol. 2.

[59]  P. Erdos,et al.  On the evolution of random graphs , 1984 .

[60]  Roger C. Schank,et al.  Dynamic memory - a theory of reminding and learning in computers and people , 1983 .