Coarse-to-Fine Question Answering for Long Documents

@inproceedings{Choi2017CoarsetoFineQA,
  title={Coarse-to-Fine Question Answering for Long Documents},
  author={Eunsol Choi and Daniel 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-ofthe-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… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 69 CITATIONS

Question Answering on SQuAD 2 . 0

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

A Deep Reinforcement Learning Based Multi-Step Coarse to Fine Question Answering (MSCQA) System

VIEW 10 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Integrated Triaging for Fast Reading Comprehension

VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Multi-hop Reading Comprehension via Deep Reinforcement Learning based Document Traversal

VIEW 3 EXCERPTS
CITES BACKGROUND & RESULTS
HIGHLY INFLUENCED

Reading Turn by Turn: Hierarchical Attention Architecture for Spoken Dialogue Comprehension

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

DSDR: Dynamic Semantic Discard Reader for Open-Domain Question Answering

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

3R: Reading - Ranking - Recognizing for Multi- Passage Reading Comprehension

  • Jin Wang, Yan Gao, Jie Li, Yanhua Yu, Binyang Li
  • Computer Science
  • 2019 IEEE 8th Joint International Information Technology and Artificial Intelligence Conference (ITAIC)
  • 2019
VIEW 2 EXCERPTS
CITES BACKGROUND

FILTER CITATIONS BY YEAR

2017
2019

CITATION STATISTICS

  • 7 Highly Influenced Citations

  • Averaged 23 Citations per year from 2017 through 2019

  • 17% Increase in citations per year in 2019 over 2018

References

Publications referenced by this paper.
SHOWING 1-10 OF 45 REFERENCES

Hierarchical Attention Networks for Document Classification

VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

NewsQA: A Machine Comprehension Dataset

VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Teaching Machines to Read and Comprehend

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

A Joint Model for Answer Sentence Ranking and Answer Extraction

VIEW 1 EXCERPT