Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension

David Golub, Po-Sen Huang, Xiaodong He, Li Deng
6/29/2017
cs.CL

Official code: davidgolub/QuestionGeneration (108 stars, last commit 2018-08-28).

Abstract

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% with a single model and 46.6% with an ensemble, approaching performance of in-domain models (F1 measure of 50.0%) and outperforming the out-of-domain baseline of 7.6%, without use of provided annotations.

View on arXivView PDF

Code Implementations(1)

davidgolub/QuestionGenerationOfficial100%
10830HTML, ShellSep 4, 20178 years agoNOASSERTION

Similar Papers

A Comprehensive Survey on Transfer Learning

81% match1 repo1092019

Scalable Weight Reparametrization for Efficient Transfer Learning

81% match2023

Reason Analogically via Cross-domain Prior Knowledge: An Empirical Study of Cross-domain Knowledge Transfer for In-Context Learning

81% match1 repo12026

Go From the General to the Particular: Multi-Domain Translation with Domain Transformation Networks

80% match1 repo72019

Improving Polish to English Neural Machine Translation with Transfer Learning: Effects of Data Volume and Language Similarity

80% match2023

Document Flattening: Beyond Concatenating Context for Document-Level Neural Machine Translation

80% match2023

Cite this paper

@article{golub2017twostage,
  title  = {Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension},
  author = {David Golub and Po-Sen Huang and Xiaodong He and Li Deng},
  year   = {2017},
  eprint = {1706.09789},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1706.09789}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1706.09789.svg)](https://codeofpaper.com/paper/1706.09789)

Discussion