search

materialsintelligence / mat2vec

Supplementary Materials for Tshitoyan et al. "Unsupervised word embeddings capture latent knowledge from materials science literature", Nature (2019).
MIT License
616 stars 180 forks source link

Code used to obtain the training data and for abstract classification #14

Closed Riksi closed 4 years ago

Riksi commented 4 years ago

Could you please share the code you used to query the APIs and filter the abstracts and for classifying them for relevance, as described in the Methods sections of the paper? Thanks.

vtshitoyan commented 4 years ago

Hi @Riksi, the code for download is available at https://www.github.com/materialsintelligence/matscholar, you have to configure a mongo dB. As for the classification model I am going to defer this to @LeighWeston86 since he trained the model.

Riksi commented 4 years ago

Thank you!