CFO: Conditional Focused Neural Question Answering with Large-scale Knowledge Bases
This addresses the problem of improving question-answering accuracy for factoid queries using large-scale knowledge bases, representing a strong specific gain in this domain.
The paper tackles the challenge of answering factoid questions from natural language using knowledge bases by proposing CFO, a neural-network-based approach that achieves 75.7% accuracy on a dataset of 108k questions, outperforming the state of the art by 11.8%.
How can we enable computers to automatically answer questions like "Who created the character Harry Potter"? Carefully built knowledge bases provide rich sources of facts. However, it remains a challenge to answer factoid questions raised in natural language due to numerous expressions of one question. In particular, we focus on the most common questions --- ones that can be answered with a single fact in the knowledge base. We propose CFO, a Conditional Focused neural-network-based approach to answering factoid questions with knowledge bases. Our approach first zooms in a question to find more probable candidate subject mentions, and infers the final answers with a unified conditional probabilistic framework. Powered by deep recurrent neural networks and neural embeddings, our proposed CFO achieves an accuracy of 75.7% on a dataset of 108k questions - the largest public one to date. It outperforms the current state of the art by an absolute margin of 11.8%.