Corpus ID: 231924957

PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them

@article{Lewis2021PAQ6M,
  title={PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them},
  author={Patrick Lewis and Yuxiang Wu and L. Liu and Pasquale Minervini and Heinrich Kuttler and Aleksandra Piktus and Pontus Stenetorp and Sebastian Riedel},
  journal={ArXiv},
  year={2021},
  volume={abs/2102.07033}
}
Open-domain Question Answering models which directly leverage question-answer (QA) pairs, such as closed-book QA (CBQA) models and QA-pair retrievers, show promise in terms of speed and memory compared to conventional models which retrieve and read from text corpora. QA-pair retrievers also offer interpretable answers, a high degree of control, and are trivial to update at test time with new knowledge. However, these models lack the accuracy of retrieve-and-read systems, as substantially less… Expand
5 Citations
Designing a Minimal Retrieve-and-Read System for Open-Domain Question Answering
  • Highly Influenced
  • PDF
Multilingual Autoregressive Entity Linking
  • PDF
GooAQ: Open Question Answering with Diverse Answer Types
  • Highly Influenced
  • PDF
Case-based Reasoning for Natural Language Queries over Knowledge Bases
  • PDF

References

SHOWING 1-10 OF 61 REFERENCES
Open-domain question answering
  • 48
Large-Scale QA-SRL Parsing
  • 40
  • PDF
Natural Questions: A Benchmark for Question Answering Research
  • 358
  • PDF
AmbigQA: Answering Ambiguous Open-domain Questions
  • 20
  • Highly Influential
  • PDF
...
1
2
3
4
5
...