Generative Adversarial Nets for Multiple Text Corpora (2017-12-25T00:00:00.000000Z)

TL;DR

This work demonstrates the GAN models on real-world text data sets from different corpora, and shows that embeddings from both models lead to improvements in supervised learning problems.

Abstract

Generative adversarial nets (GANs) have been successfully applied to the artificial generation of image data. In terms of text data, much has been done on the artificial generation of natural language from a single corpus. We consider multiple text corpora as the input data, for which there can be two applications of GANs: (1) the creation of consistent cross-corpus word embeddings given different word embeddings per corpus; (2) the generation of robust bag-of-words document embeddings for each corpora. We demonstrate our GAN models on real-world text data sets from different corpora, and show that embeddings from both models (weGAN and deGAN) lead to improvements in supervised learning problems.

Authors

Baiyang Wang

1 papers

D. Klabjan

1 papers

TL;DR

Abstract

Authors

References27 items

Generative Adversarial Networks

An End-to-End Generative Architecture for Paraphrase Generation

Conditional Generative Adversarial Networks for Commonsense Machine Comprehension

Language Generation with Recurrent Generative Adversarial Networks without Pre-training

Adversarial Generation of Natural Language

Wasserstein GAN

Adversarial Learning for Neural Dialogue Generation

Modeling documents with Generative Adversarial Networks

Least Squares Generative Adversarial Networks

SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient

Coupled Generative Adversarial Networks

Improved Techniques for Training GANs

Semi-Supervised Learning with Generative Adversarial Networks

Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks

Conditional Generative Adversarial Nets

GloVe: Global Vectors for Word Representation

Convolutional Neural Networks for Sentence Classification

Distributed Representations of Sentences and Documents

Distributed Representations of Words and Phrases and their Compositionality

Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank

Efficient Estimation of Word Representations in Vector Space

Natural Language Processing (Almost) from Scratch

Long Short-Term Memory

Natural Scales in Geographical Patterns

Generating Text via Adversarial Training

Latent Dirichlet Allocation

Visualizing Data using t-SNE

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names