BioVAE: a pre-trained latent variable language model for biomedical text mining

We release BioVAE, the first large-scale pre-trained latent variable language model for the biomedical domain, which uses the OPTIMUS framework to train on large volumes of biomedical text.

This version contains the encoder parts of the pre-trained models for text mining tasks such as named entity recognition or relation extraction.

Explanation of each file:

• pm-full-lt32-beta00: latent_size = 32, beta=0.0
• pm-full-lt32-beta05: latent_size = 32, beta=0.5
• pm-full-lt768-beta00: latent_size = 768, beta=0.0
• pm-full-lt768-beta05: latent_size = 768, beta=0.5