Abstract
Question-answering (QA) data often encodes essential information in many facets. This paper studies a natural question: Can we get supervision from QA data for other tasks (typically, non-QA ones)? For example, can we use QAMR (Michael et al., 2017) to improve named entity recognition? We suggest that simply further pre-training BERT is often not the best option, and propose the question-answer driven sentence encoding (QuASE) framework. QuASE learns representations from QA data, using BERT or other state-of-the-art contextual language models. In particular, we observe the need to distinguish between two types of sentence encodings, depending on whether the target task is a single- or multi-sentence input; in both cases, the resulting encoding is shown to be an easy-to-use plugin for many downstream tasks. This work may point out an alternative way to supervise NLP tasks.- Anthology ID:
- 2020.acl-main.772
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 8743–8758
- Language:
- URL:
- https://aclanthology.org/2020.acl-main.772
- DOI:
- 10.18653/v1/2020.acl-main.772
- Cite (ACL):
- Hangfeng He, Qiang Ning, and Dan Roth. 2020. QuASE: Question-Answer Driven Sentence Encoding. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8743–8758, Online. Association for Computational Linguistics.
- Cite (Informal):
- QuASE: Question-Answer Driven Sentence Encoding (He et al., ACL 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2020.acl-main.772.pdf
- Code
- CogComp/QuASE
- Data
- GLUE, MultiNLI, NewsQA, OntoNotes 5.0, QA-SRL, QAMR, SQuAD, TriviaQA