Semi-supervised Text Regression with Conditional Generative Adversarial Networks
- Creators
- Li, Tao
- Liu, Xudong
- Su, Shihan
Abstract
Enormous online textual information provides intriguing opportunities for understandings of social and economic semantics. In this paper, we propose a novel text regression model based on a conditional generative adversarial network (GAN), with an attempt to associate textual data and social outcomes in a semi-supervised manner. Besides promising potential of predicting capabilities, our superiorities are twofold: (i) the model works with unbalanced datasets of limited labelled data, which align with real-world scenarios; and (ii) predictions are obtained by an end-to-end framework, without explicitly selecting high-level representations. Finally we point out related datasets for experiments and future research directions.
Additional Information
© 2018 IEEE. We thank Hao Peng and Kantapon Kaewtip for insightful discussions. The idea of this work originally came out during discussions of [29] and [30].Attached Files
Published - 08622140.pdf
Accepted Version - 1810.01165.pdf
Files
Name | Size | Download all |
---|---|---|
md5:fa23dd73c93dca6f96df072ff671439b
|
187.7 kB | Preview Download |
md5:0ad2a61081552eec633786d8e0bde54d
|
154.9 kB | Preview Download |
Additional details
- Eprint ID
- 92549
- Resolver ID
- CaltechAUTHORS:20190131-131445365
- Created
-
2019-01-31Created from EPrint's datestamp field
- Updated
-
2021-11-16Created from EPrint's last_modified field