Question Answering through Transfer Learning from Large Fine-grained Supervision Data

February 07, 2017 · Entered Twilight · 🏛 Annual Meeting of the Association for Computational Linguistics

"Last commit was 8.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, README.md, basic, download.sh, evaluate.sh, my, prepro.sh, pretrain.sh, requirements.txt, run.md, semeval, squad, train.sh, wikiqa

Authors Sewon Min, Minjoon Seo, Hannaneh Hajishirzi arXiv ID 1702.02171 Category cs.CL: Computation & Language Citations 121 Venue Annual Meeting of the Association for Computational Linguistics Repository https://github.com/shmsw25/qa-transfer ⭐ 58 Last Checked 1 month ago

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.