Coarse-to-Fine Question Answering for Long Documents

@inproceedings{Choi2017CoarsetoFineQA,
  title={Coarse-to-Fine Question Answering for Long Documents},
  author={Eunsol Choi and D. Hewlett and Jakob Uszkoreit and Illia Polosukhin and Alexandre Lacoste and Jonathan Berant},
  booktitle={ACL},
  year={2017}
}
We present a framework for question answering that can efficiently scale to longer documents while maintaining or even improving performance of state-of-the-art models. While most successful approaches for reading comprehension rely on recurrent neural networks (RNNs), running them over long documents is prohibitively slow because it is difficult to parallelize over sequences. Inspired by how people first skim the document, identify relevant parts, and carefully read these parts to produce an… Expand
116 Citations
Learning to Search in Long Documents Using Document Structure
R3: Reinforced Reader-Ranker for Open-Domain Question Answering
R3: Reinforced Ranker-Reader for Open-Domain Question Answering
Multi-Mention Learning for Reading Comprehension with Neural Cascades
A Deep Reinforcement Learning Based Multi-Step Coarse to Fine Question Answering (MSCQA) System
Multi-hop Reading Comprehension via Deep Reinforcement Learning based Document Traversal
Accurate Supervised and Semi-Supervised Machine Reading for Long Documents
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 48 REFERENCES
Deep Learning for Answer Sentence Selection
Query-Reduction Networks for Question Answering
Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks
Dynamic Coattention Networks For Question Answering
Learning to Compose Neural Networks for Question Answering
SQuAD: 100, 000+ Questions for Machine Comprehension of Text
WikiReading: A Novel Large-scale Language Understanding Task over Wikipedia
...
1
2
3
4
5
...