mlsanityData to 14 Oct 2026

A Coarse to Fine Question Answering System based on Reinforcement Learning

arXiv 2106.00257 ↗First posted 1 Jun 2021cs.CL cs.AIcited by 2

Not on the map. Why?

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.

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

24 of 42 references.

References · 24

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  3. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
  4. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  5. 2015Teaching Machines to Read and Comprehendcited by 1,049
  6. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  7. 2016NewsQA: A Machine Comprehension Datasetcited by 331
  8. 2016Bidirectional Attention Flow for Machine Comprehensioncited by 278
  9. 2016Key-Value Memory Networks for Directly Reading Documentscited by 223
  10. 2015The Goldilocks Principle: Reading Children's Books with Explicit Memory Representationscited by 108
  11. 2016Learning to Compose Neural Networks for Question Answeringcited by 85
  12. 2016A Thorough Examination of the CNN/Daily Mail Reading Comprehension Taskcited by 72
12 more
  1. 2015Language Understanding for Text-based Games Using Deep Reinforcement Learningcited by 71
  2. 2016Deep Reinforcement Learning for Mention-Ranking Coreference Modelscited by 63
  3. 2018A Bi-model based RNN Semantic Frame Parsing Model for Intent Detection and Slot Fillingcited by 53
  4. 2016Dynamic Coattention Networks For Question Answeringcited by 49
  5. 2017Making Neural QA as Simple as Possible but not Simplercited by 33
  6. 2016WikiReading: A Novel Large-scale Language Understanding Task over Wikipediacited by 26
  7. 2016Who did What: A Large-Scale Person-Centered Cloze Datasetcited by 24
  8. 2016Hierarchical Question Answering for Long Documentscited by 21
  9. 2016Text Understanding with the Attention Sum Reader Networkcited by 18
  10. 2014Deep Learning for Answer Sentence Selectioncited by 17
  11. 2016Improving Information Extraction by Acquiring External Evidence with Reinforcement Learningcited by 16
  12. 2015Improving the Speed of Response of Learning Algorithms Using Multiple Modelscited by 1

Built on by

Cited by year

Citing papers per year: 2022: 2.

2 papers.

  1. 2022Hybrid Rule-Neural Coreference Resolution System based on Actor-Critic Learningcited by 1
  2. 2022Neural Coreference Resolution based on Reinforcement Learningcited by 0