search

jiesutd / NCRFpp

NCRF++, a Neural Sequence Labeling Toolkit. Easy use to any sequence labeling tasks (e.g. NER, POS, Segmentation). It includes character LSTM/CNN, word LSTM/CNN and softmax/CRF components.
Apache License 2.0
1.89k stars 446 forks source link

Experimenting with Transformer models? #175

Open jd-coderepos opened 3 years ago

jd-coderepos commented 3 years ago

Greetings,

was wondering if there are plans to support Transformer models such as BERT, SciBERT, XLNet ... with this tool? This is not so much an issue, just a question.

Thank you :)

jiesutd commented 3 years ago

Hi @jd-coderepos I implemented a dev version that integrated the initial BERT model, but I didn't get enough time to finetune it. But the good news it that my student will continue my work. We plan to release the code and experiments reports with in near months (hopefully).