jeniya/BERTOverflow

We pre-trained BERT-base model on 152 million sentences from StackOverflow's 10 year archive . We would like to thank Wuwei Lan for helping us in training this model . More details of this model can be found in our ACL 2020 paper: Code and Named Entity Recognition in StackOverflows . The model is based on a pre-training model on data from the StackOverFlow's 10-year archive . The paper is published by the Association for Computational Linguistics (ACL) and by the ACL 2020 conference on the subject of the conference of the same year as this year's conference . We are happy to provide a summary of the training and analysis of the,