A Deep Reinforcement Learning Based Multi-Step Coarse to Fine Question Answering (MSCQA) System

Authors

  • Yu Wang Samsung Research America
  • Hongxia Jin Samsung Research America

DOI:

https://doi.org/10.1609/aaai.v33i01.33017224

Abstract

In this paper, we present a multi-step coarse to fine question answering (MSCQA) system which can efficiently processes documents with different lengths by choosing appropriate actions. The system is designed using an actor-critic based deep reinforcement learning model to achieve multistep question answering. Compared to previous QA models targeting on datasets mainly containing either short or long documents, our multi-step coarse to fine model takes the merits from multiple system modules, which can handle both short and long documents. The system hence obtains a much better accuracy and faster trainings speed compared to the current state-of-the-art models. We test our model on four QA datasets, WIKEREADING, WIKIREADING LONG, CNN and SQuAD, and demonstrate 1.3%-1.7% accuracy improvements with 1.5x-3.4x training speed-ups in comparison to the baselines using state-of-the-art models.

Downloads

Published

2019-07-17

How to Cite

Wang, Y., & Jin, H. (2019). A Deep Reinforcement Learning Based Multi-Step Coarse to Fine Question Answering (MSCQA) System. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 7224-7232. https://doi.org/10.1609/aaai.v33i01.33017224

Issue

Section

AAAI Technical Track: Natural Language Processing