Algorithms (Oct 2018)

Learning Representations of Natural Language Texts with Generative Adversarial Networks at Document, Sentence, and Aspect Level

  • Aggeliki Vlachostergiou,
  • George Caridakis,
  • Phivos Mylonas,
  • Andreas Stafylopatis

DOI
https://doi.org/10.3390/a11100164
Journal volume & issue
Vol. 11, no. 10
p. 164

Abstract

Read online

The ability to learn robust, resizable feature representations from unlabeled data has potential applications in a wide variety of machine learning tasks. One way to create such representations is to train deep generative models that can learn to capture the complex distribution of real-world data. Generative adversarial network (GAN) approaches have shown impressive results in producing generative models of images, but relatively little work has been done on evaluating the performance of these methods for the learning representation of natural language, both in supervised and unsupervised settings at the document, sentence, and aspect level. Extensive research validation experiments were performed by leveraging the 20 Newsgroups corpus, the Movie Review (MR) Dataset, and the Finegrained Sentiment Dataset (FSD). Our experimental analysis suggests that GANs can successfully learn representations of natural language texts at all three aforementioned levels.

Keywords