search

yzhangcs / parser

:rocket: State-of-the-art parsers for natural language.
https://parser.yzhang.site/
MIT License
827 stars 139 forks source link

Question about fine-tuning #53

Closed zerogerc closed 3 years ago

zerogerc commented 3 years ago

Hi, thanks for the awesome library. I wonder if it is possible to pretrain the model on one dataset and then fine-tune on another?

yzhangcs commented 3 years ago

@zerogerc you can achieve this by passing 'requires_grad=True' when initializing the BertEmbedding. However, the code for a model without LSTM layers/word embeddings is not integrated into the repo yet. I'm working on this, and it can be available in the next release.

zerogerc commented 3 years ago

Thanks!