Abstract
We show that the task of question answering (QA) can significantly benefit from the transfer learning of models trained on a different large, fine-grained QA dataset. We achieve the state of the art in two well-studied QA datasets, WikiQA and SemEval-2016 (Task 3A), through a basic transfer learning technique from SQuAD. For WikiQA, our model outperforms the previous best model by more than 8%. We demonstrate that finer supervision provides better guidance for learning lexical and syntactic information than coarser supervision, through quantitative results and visual analysis. We also show that a similar transfer learning procedure achieves the state of the art on an entailment task.- Anthology ID:
- P17-2081
- Volume:
- Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
- Month:
- July
- Year:
- 2017
- Address:
- Vancouver, Canada
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 510–517
- Language:
- URL:
- https://aclanthology.org/P17-2081
- DOI:
- 10.18653/v1/P17-2081
- Cite (ACL):
- Sewon Min, Minjoon Seo, and Hannaneh Hajishirzi. 2017. Question Answering through Transfer Learning from Large Fine-grained Supervision Data. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 510–517, Vancouver, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Question Answering through Transfer Learning from Large Fine-grained Supervision Data (Min et al., ACL 2017)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/P17-2081.pdf
- Data
- SICK, SNLI, SQuAD, WikiQA