English

A Coarse to Fine Question Answering System based on Reinforcement Learning

Computation and Language 2021-06-02 v1 Artificial Intelligence

Abstract

In this paper, we present a coarse to fine question answering (CFQA) system based on reinforcement learning 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 multi-step 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.

Keywords

Cite

@article{arxiv.2106.00257,
  title  = {A Coarse to Fine Question Answering System based on Reinforcement Learning},
  author = {Yu Wang and Hongxia Jin},
  journal= {arXiv preprint arXiv:2106.00257},
  year   = {2021}
}

Comments

9 pages, original work published in AAAI 2019

R2 v1 2026-06-24T02:41:39.133Z