Generating Text through Adversarial Training using Skip-Thought Vectors

NAACL 2019 Afroz Ahamad

GANs have been shown to perform exceedingly well on tasks pertaining to image generation and style transfer. In the field of language modelling, word embeddings such as GLoVe and word2vec are state-of-the-art methods for applying neural network models on textual data... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Text Generation CMU-SE STWGAN-GP BLEU-3 0.617 # 1

Methods used in the Paper