search

VinAIResearch / PhoNLP

PhoNLP: A BERT-based multi-task learning model for part-of-speech tagging, named entity recognition and dependency parsing (NAACL 2021)
Apache License 2.0
137 stars 17 forks source link

About CRFLoss #6

Closed Quang-elec44 closed 2 years ago

Quang-elec44 commented 2 years ago

Hi, I am trying to write CRFLoss from scratch and I also read many other sources aside from your code. However, it seems that you omit the start and end tags in your code while other sources don't. I saw the comment TODO in your code which tells that you will change the code in the future, aren't you? If not, is there any difference between your code and others?. Below are some of the references, you can check them and make comparisons. I am a newbie so I hope that you will help me out. Thanks in advance. https://github.com/sgrvinod/a-PyTorch-Tutorial-to-Sequence-Labeling https://github.com/mtreviso/linear-chain-crf/tree/865bcf25fb33f73d59978426eb1c0f587e1f95f8 https://github.com/kmkurn/pytorch-crf/blob/8f3203a1f1d7984c87718bfe31853242670258db/torchcrf/__init__.py

thelinhbkhn2014 commented 2 years ago

I reused this function from Stanza of the Stanford NLP group. This function is another CRF version appropriate with languages built based on syllables level like Vietnamese. You can check them from Stanza Github https://github.com/stanfordnlp/stanza