Improved Neural Relation Detection for Knowledge Base Question Answering

Abstract

Relation detection is a core component for many NLP applications including Knowledge Base Question Answering (KBQA). In this paper, we propose a hierarchical recurrent neural network enhanced by residual learning that detects KB relations given an input question. Our method uses deep residual bidirectional LSTMs to compare questions and relation names via different hierarchies of abstraction. Additionally, we propose a simple KBQA system that integrates entity linking and our proposed relation detector to enable one enhance another. Experimental results evidence that our approach achieves not only outstanding relation detection performance, but more importantly, it helps our KBQA system to achieve state-of-the-art accuracy for both single-relation (SimpleQuestions) and multi-relation (WebQSP) QA benchmarks.

Accepted by ACL 2017 (updated for camera-ready)

References in corpus (5)

• Large-scale Simple Question Answering with Memory Networks
• Bilateral Multi-Perspective Matching for Natural Language Sentences
• Classifying Relations by Ranking with Convolutional Neural Networks
• Character-Level Question Answering with Attention
• Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision

Cited by in corpus (13)

• R${}^3$: Reinforced Reader-Ranker for Open-Domain Question Answering
• Formal Query Building with Query Structure Prediction for Complex Question Answering over Knowledge Base
• Efficient long-distance relation extraction with DG-SpanBERT
• Multi-Task Learning with Multi-View Attention for Answer Selection and Knowledge Base Question Answering
• Densely Connected Bidirectional LSTM with Applications to Sentence Classification
• Improving Knowledge-aware Dialogue Generation via Knowledge Base Question Answering
• Lattice CNNs for Matching Based Chinese Question Answering
• Knowledge Graph Question Answering via SPARQL Silhouette Generation
• Relation Adversarial Network for Low Resource Knowledge Graph Completion
• Learning to Answer Ambiguous Questions with Knowledge Graph
• Integrating Relation Constraints with Neural Relation Extractors
• Mention-centered Graph Neural Network for Document-level Relation Extraction
• Multi-view Inference for Relation Extraction with Uncertain Knowledge