Next Article in Journal
Efficient Algorithms for Computing the Inner Edit Distance of a Regular Language via Transducers
Next Article in Special Issue
Measuring the Impact of Financial News and Social Media on Stock Market Modeling Using Time Series Mining Techniques
Previous Article in Journal
Airfoil Optimization Design Based on the Pivot Element Weighting Iterative Method
Previous Article in Special Issue
LSTM Accelerator for Convolutional Object Identification
Article Menu

Export Article

Open AccessArticle
Algorithms 2018, 11(10), 164; https://doi.org/10.3390/a11100164

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

1
Intelligent Systems Content and Interaction Laboratory, National Technical University of Athens (NTUA), 15780 Athens, Greece
2
Department of Cultural Technology and Communication, University of the Aegean, 81100 Mytilene, Greece
3
Department of Informatics, Ionian University, 49100 Corfu, Greece
*
Author to whom correspondence should be addressed.
Received: 27 August 2018 / Revised: 30 September 2018 / Accepted: 19 October 2018 / Published: 22 October 2018
(This article belongs to the Special Issue Humanistic Data Mining: Tools and Applications)
Full-Text   |   PDF [1468 KB, uploaded 24 October 2018]   |  

Abstract

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. View Full-Text
Keywords: natural language texts; representation learning; deep learning; generative adversarial networks (GANs); adversarial training; document; sentence; aspect-level text analysis; information retrieval natural language texts; representation learning; deep learning; generative adversarial networks (GANs); adversarial training; document; sentence; aspect-level text analysis; information retrieval
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
SciFeed

Share & Cite This Article

MDPI and ACS Style

Vlachostergiou, A.; Caridakis, G.; Mylonas, P.; Stafylopatis, A. Learning Representations of Natural Language Texts with Generative Adversarial Networks at Document, Sentence, and Aspect Level. Algorithms 2018, 11, 164.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Algorithms EISSN 1999-4893 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top