Aspect-augmented Adversarial Networks for Domain Adaptation
Name
tacl_a_00077.pdf
Description
Published version
Size
2.63 MB
Format
Adobe PDF
Checksum (MD5)
9dcac1bd9e49261f0512cd6322a4e4cf
Author(s)
Zhang, Yuan
Barzilay, Regina
Jaakkola, Tommi
Date Issued
2017
Journal
Transactions of the Association for Computational Linguistics
Publisher
MIT Press - Journals
Version
Final published version
Abstract
We introduce a neural method for transfer learning between two (source and target) classification tasks or aspects over the same domain. Rather than training on target labels, we use a few keywords pertaining to source and target aspects indicating sentence relevance instead of document class labels. Documents are encoded by learning to embed and softly select relevant sentences in an aspect-dependent manner. A shared classifier is trained on the source encoded documents and labels, and applied to target encoded documents. We ensure transfer through aspect-adversarial training so that encoded documents are, as sets, aspect-invariant. Experimental results demonstrate that our approach outperforms different baselines and model variants on two datasets, yielding an improvement of 27% on a pathology dataset and 5% on a review dataset.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution 4.0 International license
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1162/TACL_A_00077
