Variational Reasoning for Question Answering with Knowledge Graph

Abstract

Knowledge graph (KG) is known to be helpful for the task of question answering (QA), since it provides well-structured relational information between entities, and allows one to further infer indirect facts. However, it is challenging to build QA systems which can learn to reason over knowledge graphs based on question-answer pairs alone. First, when people ask questions, their expressions are noisy (for example, typos in texts, or variations in pronunciations), which is non-trivial for the QA system to match those mentioned entities to the knowledge graph. Second, many questions require multi-hop logic reasoning over the knowledge graph to retrieve the answers. To address these challenges, we propose a novel and unified deep learning architecture, and an end-to-end variational learning algorithm which can handle noise in questions, and learn multi-hop reasoning simultaneously. Our method achieves state-of-the-art performance on a recent benchmark dataset in the literature. We also derive a series of new benchmark datasets, including questions for multi-hop reasoning, questions paraphrased by neural translation model, and questions in human voice. Our method yields very promising results on all these challenging datasets.

Cited by in corpus (58)

• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals
• Knowledge Graphs in Manufacturing and Production: A Systematic Literature Review
• Graph Neural Networks for Natural Language Processing: A Survey
• Measuring Compositional Generalization: A Comprehensive Method on Realistic Data
• UHop: An Unrestricted-Hop Relation Extraction Framework for Knowledge-Based Question Answering
• Reinforcement Learning from Reformulations in Conversational Question Answering over Knowledge Graphs
• PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text
• Faithful Embeddings for Knowledge Base Queries
• Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games
• Variational Attention for Sequence-to-Sequence Models
• Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval
• A Variational Dirichlet Framework for Out-of-Distribution Detection
• A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutions
• GNN is a Counter? Revisiting GNN for Question Answering
• HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data
• T-GAP: Learning to Walk across Time for Temporal Knowledge Graph Completion
• Graph-based Multi-hop Reasoning for Long Text Generation
• Jointly Learning Entity and Relation Representations for Entity Alignment
• Towards Learning Instantiated Logical Rules from Knowledge Graphs
• Path-Enhanced Multi-Relational Question Answering with Knowledge Graph Embeddings
• Reasoning Over Virtual Knowledge Bases With Open Predicate Relations
• Querying Knowledge via Multi-Hop English Questions
• Relational Graph Representation Learning for Open-Domain Question Answering
• Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval
• Self-Supervised Learning of Contextual Embeddings for Link Prediction in Heterogeneous Networks
• Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps
• A Variational Approach to Weakly Supervised Document-Level Multi-Aspect Sentiment Classification
• DyERNIE: Dynamic Evolution of Riemannian Manifold Embeddings for Temporal Knowledge Graph Completion
• AutoKG: Constructing Virtual Knowledge Graphs from Unstructured Documents for Question Answering
• Neural, Symbolic and Neural-Symbolic Reasoning on Knowledge Graphs
• Clustering-based Unsupervised Generative Relation Extraction
• FAQ-based Question Answering via Knowledge Anchors
• Question-Aware Memory Network for Multi-hop Question Answering in Human-Robot Interaction
• Answering Any-hop Open-domain Questions with Iterative Document Reranking
• Textbook to triples: Creating knowledge graph in the form of triples from AI TextBook
• Towards a Universal Continuous Knowledge Base
• A Variational Approach to Unsupervised Sentiment Analysis
• TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph
• MCMH: Learning Multi-Chain Multi-Hop Rules for Knowledge Graph Reasoning
• A Data-Driven Study of Commonsense Knowledge using the ConceptNet Knowledge Base
• TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting
• Knowledge Authoring with Factual English
• Recent Advances in Automated Question Answering In Biomedical Domain
• TIE: A Framework for Embedding-based Incremental Temporal Knowledge Graph Completion
• Stronger Transformers for Neural Multi-Hop Question Generation
• Text Modeling with Syntax-Aware Variational Autoencoders
• Differentiable Representations For Multihop Inference Rules
• SemCo: Toward Semantic Coherent Visual Relationship Forecasting
• Complex Knowledge Base Question Answering: A Survey
• Audio-Oriented Multimodal Machine Comprehension: Task, Dataset and Model
• SQALER: Scaling Question Answering by Decoupling Multi-Hop and Logical Reasoning
• Incremental Knowledge Based Question Answering
• Integrating Subgraph-aware Relation and DirectionReasoning for Question Answering
• Multi-hop Reading Comprehension via Deep Reinforcement Learning based Document Traversal
• NePTuNe: Neural Powered Tucker Network for Knowledge Graph Completion
• Learning When Not to Answer: A Ternary Reward Structure for Reinforcement Learning based Question Answering
• Building Rule Hierarchies for Efficient Logical Rule Learning from Knowledge Graphs