Aspect-augmented Adversarial Networks for Domain Adaptation

Aspect-augmented Adversarial Networks for Domain Adaptation

<jats:p> 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 docume...

Full description

Bibliographic Details
Main Authors: Zhang, Yuan, Barzilay, Regina, Jaakkola, Tommi
Other Authors: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Format: Article
Language:English
Published: MIT Press - Journals 2021
Online Access:https://hdl.handle.net/1721.1/135065

Internet

https://hdl.handle.net/1721.1/135065

Similar Items