Question Answering on Freebase via Relation Extraction and Textual Evidence

Abstract

Existing knowledge-based question answering systems often rely on small annotated training data. While shallow methods like relation extraction are robust to data scarcity, they are less expressive than the deep meaning representation methods like semantic parsing, thereby failing at answering questions involving multiple constraints. Here we alleviate this problem by empowering a relation extraction method with additional evidence from Wikipedia. We first present a neural network based relation extractor to retrieve the candidate answers from Freebase, and then infer over Wikipedia to validate these answers. Experiments on the WebQuestions question answering dataset show that our method achieves an F_1 of 53.3%, a substantial improvement over the state-of-the-art.

References in corpus (4)

• Teaching Machines to Read and Comprehend
• Large-scale Simple Question Answering with Memory Networks
• Deep Learning for Answer Sentence Selection
• Question Answering with Subgraph Embeddings

Cited by in corpus (7)

• Simple Question Answering by Attentive Convolutional Neural Network
• Review Conversational Reading Comprehension
• Towards Understanding and Answering Multi-Sentence Recommendation Questions on Tourism
• Infusing Finetuning with Semantic Dependencies
• Learning to Answer Ambiguous Questions with Knowledge Graph
• Representation Learning for Words and Entities
• Neural Architecture for Question Answering Using a Knowledge Graph and Web Corpus