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.
@article{arxiv.1702.02171,
title = {Question Answering through Transfer Learning from Large Fine-grained Supervision Data},
author = {Sewon Min and Minjoon Seo and Hannaneh Hajishirzi},
journal= {arXiv preprint arXiv:1702.02171},
year = {2018}
}
Comments
Published as a conference paper at ACL 2017 (short paper). Code available at https://github.com/shmsw25/qa-transfer