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 (28)

• Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals
• UHop: An Unrestricted-Hop Relation Extraction Framework for Knowledge-Based Question Answering
• PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text
• A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutions
• GNN is a Counter? Revisiting GNN for Question Answering
• T-GAP: Learning to Walk across Time for Temporal Knowledge Graph Completion
• Graph-based Multi-hop Reasoning for Long Text Generation
• Path-Enhanced Multi-Relational Question Answering with Knowledge Graph Embeddings
• Relational Graph Representation Learning for Open-Domain Question Answering
• Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval
• Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps
• DyERNIE: Dynamic Evolution of Riemannian Manifold Embeddings for Temporal Knowledge Graph Completion
• A Variational Approach to Weakly Supervised Document-Level Multi-Aspect Sentiment Classification
• A Variational Approach to Unsupervised Sentiment Analysis
• Clustering-based Unsupervised Generative Relation Extraction
• Towards a Universal Continuous Knowledge Base
• Knowledge Authoring with Factual English
• MCMH: Learning Multi-Chain Multi-Hop Rules for Knowledge Graph Reasoning
• TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting
• A Data-Driven Study of Commonsense Knowledge using the ConceptNet Knowledge Base
• Incremental Knowledge Based Question Answering
• Multi-hop Reading Comprehension via Deep Reinforcement Learning based Document Traversal
• Learning When Not to Answer: A Ternary Reward Structure for Reinforcement Learning based Question Answering
• NePTuNe: Neural Powered Tucker Network for Knowledge Graph Completion
• Integrating Subgraph-aware Relation and DirectionReasoning for Question Answering
• Differentiable Representations For Multihop Inference Rules
• SQALER: Scaling Question Answering by Decoupling Multi-Hop and Logical Reasoning
• Audio-Oriented Multimodal Machine Comprehension: Task, Dataset and Model