Semi-supervised Text Regression with Conditional Generative Adversarial Networks
This addresses the challenge of predicting social and economic semantics from online text in real-world scenarios with limited labeled data, but it appears incremental as it adapts existing GAN methods to text regression.
The paper tackles the problem of associating textual data with social outcomes by proposing a semi-supervised text regression model using conditional GANs, which works with unbalanced datasets and limited labeled data in an end-to-end framework.
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.