SQuAD: 100,000+ Questions for Machine Comprehension of Text
Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, Percy Liang
- Anthology ID:
- D16-1264
- Volume:
- Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2016
- Address:
- Austin, Texas
- Editors:
- Jian Su, Kevin Duh, Xavier Carreras
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2383–2392
- Language:
- URL:
- https://preview.aclanthology.org/acl-awards-reasoning/D16-1264/
- DOI:
- 10.18653/v1/D16-1264
- Award:
- ACL 2026 Test of Time AwardThis paper transformed how question answering is evaluated, and triggered a wide range of follow-up research into new evaluation datasets and methodologies. Its large-scale span-extraction setting established a new evaluation paradigm that shaped research for years. Nearly every major model, from RNNs and attention networks to transformers and today’s LLMs, has been benchmarked against SQuAD or its successors.
- Cite (ACL):
- Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. SQuAD: 100,000+ Questions for Machine Comprehension of Text. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2383–2392, Austin, Texas. Association for Computational Linguistics.
- Cite (Informal):
- SQuAD: 100,000+ Questions for Machine Comprehension of Text (Rajpurkar et al., EMNLP 2016)
- PDF:
- https://preview.aclanthology.org/acl-awards-reasoning/D16-1264.pdf