Question Answering on Freebase via Relation Extraction and Textual Evidence
This work addresses the challenge of answering complex questions with multiple constraints for users of knowledge-based systems, representing an incremental improvement over existing methods.
The paper tackled the problem of knowledge-based question answering with limited training data by enhancing a relation extraction method with Wikipedia evidence, achieving an F1 score of 53.3% on the WebQuestions dataset, a substantial improvement over the state-of-the-art.
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.