Improved Neural Relation Detection for Knowledge Base Question Answering
This improves knowledge base question answering systems, which is important for NLP applications, though it appears incremental as it builds on existing neural methods.
The paper tackles relation detection for knowledge base question answering by proposing a hierarchical recurrent neural network with residual learning, achieving state-of-the-art accuracy on SimpleQuestions and WebQSP benchmarks.
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.