Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

What is max_seq_length? #7

Closed
sbmaruf opened this issue May 15, 2019 · 2 comments
Closed

What is max_seq_length? #7

sbmaruf opened this issue May 15, 2019 · 2 comments

Comments

@sbmaruf
Copy link

sbmaruf commented May 15, 2019

Hi @kamalkraj !
Nice repo.
If a sentence has length more than 128 how do you predict NER tags for those sentences?
Especially for test data.

@kamalkraj
Copy link
Owner

Hi @sbmaruf
Currently model is trained to predict only NER tags for sequence length of 128 tokens, you can input sentence length more than 128, but output won't be good. The reason why i say it won't be good is ,BERT have positional embeddings, so after fine tuning only first 128 positions are fine tuned for NER task even though bert can accept maximum sequence length of 512.

In train set only 1 sentence has sequence length greater than 128 tokens. 2,4 in dev and test respectively .

@sbmaruf
Copy link
Author

sbmaruf commented May 16, 2019

Thanks for the reply.

@sbmaruf sbmaruf closed this as completed May 16, 2019
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants