Teaching Machines to Read and Comprehend

@inproceedings{Hermann2015TeachingMT,
  title={Teaching Machines to Read and Comprehend},
  author={Karl Moritz Hermann and Tom{\'a}s Kocisk{\'y} and Edward Grefenstette and Lasse Espeholt and Will Kay and Mustafa Suleyman and Phil Blunsom},
  booktitle={NIPS},
  year={2015}
}
Teaching machines to read natural language documents remains an elusive challenge. Machine reading systems can be tested on their ability to answer questions posed on the contents of documents that they have seen, but until now large scale training and test datasets have been missing for this type of evaluation. In this work we define a new methodology that resolves this bottleneck and provides large scale supervised reading comprehension data. This allows us to develop a class of attention… CONTINUE READING

Results and Topics from this paper.

Key Quantitative Results

  • : A Set of Prerequisite Toy Tasks achieve 100% accuracy.

Citations

Publications citing this paper.
SHOWING 1-10 OF 959 CITATIONS

Diversity-Promoting and Large-Scale Machine Learning for Healthcare

VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Machine Reading Comprehension: a Literature Review

Xin Zhang, An Yang, Sujian Li, Yizhong Wang
  • ArXiv
  • 2019
VIEW 9 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Modeling Task Effects in Human Reading with Neural Attention

VIEW 14 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Learning Latent Space Models with Angular Constraints

VIEW 5 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Machine Comprehension Based on Learning to Rank

VIEW 12 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Addressing Challenges of Modern News Agencies via Predictive Modeling, Deep Learning, and Transfer Learning

Yaser Keneshloo
  • 2019
VIEW 19 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2013
2019

CITATION STATISTICS

  • 193 Highly Influenced Citations

  • Averaged 259 Citations per year from 2017 through 2019