QuASE: Question-Answer Driven Sentence Encoding

Hangfeng He, Qiang Ning, Dan Roth


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
Bibkey:
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)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.772.pdf
Video:
 http://slideslive.com/38929339
Code
 CogComp/QuASE
Data
GLUEMultiNLINewsQAOntoNotes 5.0QA-SRLQAMRSQuADTriviaQA