Neural Generative Question Answering

TL;DR

This paper introduces Neural Generative Question Answering (GENQA), a neural network model that generates fact-based answers to questions by integrating sequence-to-sequence learning with knowledge-base querying.

Contribution

It presents a novel end-to-end neural model that combines question answering with knowledge-base access, improving answer accuracy and naturalness.

Findings

Outperforms embedding-based QA models

Effectively handles question and answer variations

Generates accurate, natural answers based on knowledge-base facts

Abstract

This paper presents an end-to-end neural network model, named Neural Generative Question Answering (GENQA), that can generate answers to simple factoid questions, based on the facts in a knowledge-base. More specifically, the model is built on the encoder-decoder framework for sequence-to-sequence learning, while equipped with the ability to enquire the knowledge-base, and is trained on a corpus of question-answer pairs, with their associated triples in the knowledge-base. Empirical study shows the proposed model can effectively deal with the variations of questions and answers, and generate right and natural answers by referring to the facts in the knowledge-base. The experiment on question answering demonstrates that the proposed model can outperform an embedding-based QA model as well as a neural dialogue model trained on the same data.