Generative Adversarial Nets for Multiple Text Corpora [article]

Baiyang Wang, Diego Klabjan
2017 arXiv   pre-print
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
more » ... corpora. We demonstrate our GAN models on real-world text data sets from different corpora, and show that embeddings from both models lead to improvements in supervised learning problems.
arXiv:1712.09127v1 fatcat:fhur7ebflnhuplyc4wcfeeueae