bert-sense
bert-sense copied to clipboard
Source code accompanying the KONVENS 2019 paper "Does BERT Make Any Sense? Interpretable Word Sense Disambiguation with Contextualized Embeddings"
The word senses clustering shown in the paper is very nice. Is the code been provided in this repo?
Huggingface transformers has been upgraded from pytorch-pretrained-BERT and BERT_model.py doesn't run
Current code doesn't work with latest `transformers` code. See issue https://github.com/uhh-lt/bert-sense/issues/2 This PR updates `BERT_Model.py` from using deprecated `pytorch-pretrained-bert` version, to using latest `transformers` code.
With current argument, `use_cuda=False` has no effect. Changed `use_cuda` argument to `no_cuda`, so that CUDA can be disabled. Affects both BERT_Model.py and Flair_Model.py Changed README accordingly.