A Coarse to Fine Question Answering System based on Reinforcement Learning
This addresses the challenge of handling both short and long documents in QA systems, though it appears incremental as it builds on existing RL methods.
The paper tackles the problem of question answering on documents of varying lengths by developing a coarse-to-fine system using reinforcement learning, achieving 1.3%-1.7% accuracy improvements and 1.5x-3.4x training speed-ups compared to state-of-the-art baselines on four datasets.
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.