Corpus ID: 4482119

SQuAD Reading Comprehension

@inproceedings{Jiang2018SQuADRC,
  title={SQuAD Reading Comprehension},
  author={Xinyi Jiang},
  year={2018}
}
One important task in Natural Language Understanding is Reading Comprehension. Given a piece of text, we want to be able to answer any relevant questions. Using Stanford Question Answering Dataset(SQuAD), which is a new reading comprehension dataset consisting of 100,000+ questions posed by crowdworkers on a set of Wikipedia articles, we built a reading comprehension model that attains 75.2% F1 score and 65.0% Exact Match (EM) on the test set. 

Figures from this paper

References

SHOWING 1-10 OF 11 REFERENCES
SQuAD: 100, 000+ Questions for Machine Comprehension of Text
  • 2,752
  • PDF
Teaching Machines to Read and Comprehend
  • 1,904
  • PDF
Modeling Biological Processes for Reading Comprehension
  • 137
  • PDF
Machine Comprehension Using Match-LSTM and Answer Pointer
  • 435
  • PDF
MCTest: A Challenge Dataset for the Open-Domain Machine Comprehension of Text
  • 490
  • PDF
Mnemonic Reader for Machine Comprehension
  • 39
  • Highly Influential
Bidirectional Attention Flow for Machine Comprehension
  • 1,329
  • Highly Influential
  • PDF
The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations
  • 459
  • PDF
Dynamic Coattention Networks For Question Answering
  • 495
  • PDF
Glove: Global Vectors for Word Representation
  • 17,484
  • PDF
...
1
2
...