CFO: Conditional Focused Neural Question Answering with Large-scale Knowledge Bases

TL;DR

This paper introduces CFO, a neural network approach that improves factoid question answering over large knowledge bases by focusing on candidate mentions and using a probabilistic framework, achieving state-of-the-art accuracy.

Contribution

The paper presents CFO, a novel neural question answering method that enhances candidate mention detection and answer inference using a unified probabilistic model.

Findings

Achieves 75.7% accuracy on a large dataset of 108k questions.

Outperforms previous state-of-the-art by 11.8%.

Demonstrates effectiveness of focused neural networks in knowledge base question answering.

Abstract

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%.