# A Coarse to Fine Question Answering System based on Reinforcement Learning

arXiv: https://arxiv.org/abs/2106.00257 · HTML: https://mlsanity.com/paper/2106.00257/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 42 references that are in the map.
- First posted on arXiv 1 Jun 2021.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [NewsQA: A Machine Comprehension Dataset](https://mlsanity.com/paper/1611.09830/) (2016)
- [Bidirectional Attention Flow for Machine Comprehension](https://mlsanity.com/paper/1611.01603/) (2016)
- [Key-Value Memory Networks for Directly Reading Documents](https://mlsanity.com/paper/1606.03126/) (2016)
- [The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations](https://mlsanity.com/paper/1511.02301/) (2015)
- [Learning to Compose Neural Networks for Question Answering](https://mlsanity.com/paper/1601.01705/) (2016)
- [A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task](https://mlsanity.com/paper/1606.02858/) (2016)
- [Language Understanding for Text-based Games Using Deep Reinforcement Learning](https://mlsanity.com/paper/1506.08941/) (2015)
- [Deep Reinforcement Learning for Mention-Ranking Coreference Models](https://mlsanity.com/paper/1609.08667/) (2016)
- [A Bi-model based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling](https://mlsanity.com/paper/1812.10235/) (2018)
- [Dynamic Coattention Networks For Question Answering](https://mlsanity.com/paper/1611.01604/) (2016)
- [Making Neural QA as Simple as Possible but not Simpler](https://mlsanity.com/paper/1703.04816/) (2017)
- [WikiReading: A Novel Large-scale Language Understanding Task over Wikipedia](https://mlsanity.com/paper/1608.03542/) (2016)
- [Who did What: A Large-Scale Person-Centered Cloze Dataset](https://mlsanity.com/paper/1608.05457/) (2016)
- [Hierarchical Question Answering for Long Documents](https://mlsanity.com/paper/1611.01839/) (2016)
- [Text Understanding with the Attention Sum Reader Network](https://mlsanity.com/paper/1603.01547/) (2016)
- [Deep Learning for Answer Sentence Selection](https://mlsanity.com/paper/1412.1632/) (2014)
- [Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning](https://mlsanity.com/paper/1603.07954/) (2016)
- [Improving the Speed of Response of Learning Algorithms Using Multiple Models](https://mlsanity.com/paper/1510.05034/) (2015)

## Built on by (most cited first, 2 of 2)

- [Hybrid Rule-Neural Coreference Resolution System based on Actor-Critic Learning](https://mlsanity.com/paper/2212.10087/) (2022)
- [Neural Coreference Resolution based on Reinforcement Learning](https://mlsanity.com/paper/2212.09028/) (2022)

## Abstract (arXiv)

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.