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 pre-trained models for text mining tasks such as named entity recognition or relation extraction, and text generation task.

Explanation of each file: (lt32: latent_size = 32, beta05: beta=0.5)

• pm-full-lt32-beta00
• pm-full-lt32-beta05
• pm-full-lt768-beta00
• pm-full-lt768-beta05
• pm-full-generation