Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension

David Golub, Po-Sen Huang, Xiaodong He, Li Deng


Abstract
We develop a technique for transfer learning in machine comprehension (MC) using a novel two-stage synthesis network. Given a high performing MC model in one domain, our technique aims to answer questions about documents in another domain, where we use no labeled data of question-answer pairs. Using the proposed synthesis network with a pretrained model on the SQuAD dataset, we achieve an F1 measure of 46.6% on the challenging NewsQA dataset, approaching performance of in-domain models (F1 measure of 50.0%) and outperforming the out-of-domain baseline by 7.6%, without use of provided annotations.
Anthology ID:
D17-1087
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
835–844
Language:
URL:
https://www.aclweb.org/anthology/D17-1087
DOI:
10.18653/v1/D17-1087
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D17-1087.pdf