Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension

06/29/2017

∙

by   David Golub, et al.

∙

0

∙

share

We develop a technique for transfer learning in machine comprehension (MC) using a novel two-stage synthesis network (SynNet). 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 SynNet with a pretrained model from the SQuAD dataset on the challenging NewsQA dataset, we achieve an F1 measure of 44.3 model and 46.6 (F1 measure of 50.0 without use of provided annotations.