Generative Adversarial Networks
Related Papers
Evaluating Text GANs as Language Models
AbstractGenerative Adversarial Networks (GANs) are a promising approach for text generation that, unlike traditional language models (LM), does not suffer from the problem of “exposure bias”. However, A major hurdle …...
A Preliminary Exploration of GANs for Keyphrase Generation
AbstractWe introduce a new keyphrase generation approach using Generative Adversarial Networks (GANs). For a given document, the generator produces a sequence of keyphrases, and the discriminator distinguishes between human-curated and …...
Adversarial Grammatical Error Correction
AbstractRecent works in Grammatical Error Correction (GEC) have leveraged the progress in Neural Machine Translation (NMT), to learn rewrites from parallel corpora of grammatically incorrect and corrected sentences, achieving state-of-the-art …...
From Disjoint Sets to Parallel Data to Train Seq2Seq Models for Sentiment Transfer
AbstractWe present a method for creating parallel data to train Seq2Seq neural networks for sentiment transfer. Most systems for this task, which can be viewed as monolingual machine translation (MT), …...
Improving Adversarial Text Generation with n-Gram Matching
In the past few years, generative adversarial networks (GANs) have become increasingly important in natural language generation. How- ever, their performance seems to still have a sig- nificant margin for …...
PS-GAN: Feature augmented text generation in Telugu
Since the inception of Generative Adver- sarial Networks (GANs), synthetic im- age generation has taken a giant leap because of the ability of these networks to generate high-quality images, however, …...
TILGAN: Transformer-based Implicit Latent GAN for Diverse and Coherent Text Generation
Conventional autoregressive models have achieved great success in text generation but suffer from the exposure bias problem in that token sequences in the training and in the gen- eration stages …...
Exploring How Generative Adversarial Networks Learn Phonological Representations
AbstractThis paper explores how Generative Adversarial Networks (GANs) learn representations of phonological phenomena. We analyze how GANs encode contrastive and non-contrastive nasality in French and English vowels by applying the …...
GanLM: Encoder-Decoder Pre-training with an Auxiliary Discriminator
AbstractPre-trained models have achieved remarkable success in natural language processing (NLP). However, existing pre-training methods underutilize the benefits of language understanding for generation. Inspired by the idea of Generative Adversarial …...