English

Semi-supervised Text Regression with Conditional Generative Adversarial Networks

Computation and Language 2019-04-25 v2 Artificial Intelligence Computational Finance Machine Learning

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.

Keywords

Cite

@article{arxiv.1810.01165,
  title  = {Semi-supervised Text Regression with Conditional Generative Adversarial Networks},
  author = {Tao Li and Xudong Liu and Shihan Su},
  journal= {arXiv preprint arXiv:1810.01165},
  year   = {2019}
}
R2 v1 2026-06-23T04:25:39.603Z