Applying Deep Learning to Answer Selection: A Study and An Open Task

TL;DR

This paper explores a language-agnostic deep learning approach for non-factoid question answering, demonstrating superior performance and establishing a new insurance domain QA task with promising accuracy.

Contribution

It introduces a versatile deep learning framework for answer selection that does not depend on linguistic tools and applies it to a novel insurance domain QA dataset.

Findings

Top-1 accuracy reaches 65.3% on test set

Deep learning outperforms baseline methods

Framework applicable across languages and domains

Abstract

We apply a general deep learning framework to address the non-factoid question answering task. Our approach does not rely on any linguistic tools and can be applied to different languages or domains. Various architectures are presented and compared. We create and release a QA corpus and setup a new QA task in the insurance domain. Experimental results demonstrate superior performance compared to the baseline methods and various technologies give further improvements. For this highly challenging task, the top-1 accuracy can reach up to 65.3% on a test set, which indicates a great potential for practical use.