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 does "1sent+1sur" mean? #3

Open
huidemie opened this issue Dec 28, 2020 · 3 comments
Open

what does "1sent+1sur" mean? #3

huidemie opened this issue Dec 28, 2020 · 3 comments

Comments

@huidemie
Copy link

hello, I don't understand "1sent+1sur" in the paper,and I didn't find it in the code. Can you tell me what is the "surrounding"?

@chrhad
Copy link
Collaborator

chrhad commented Dec 28, 2020

Hi, 1sent+1sur means that the input consists of the sentence that contains the ambiguous word to disambiguate. It is activated by adding the parameter --num-context 1. Please refer to the example running script. The surrounding sentence refers to the sentence before and after the sentence that contains the word to disambiguate.

@huidemie
Copy link
Author

huidemie commented Dec 28, 2020

Hi, 1sent+1sur means that the input consists of the sentence that contains the ambiguous word to disambiguate. It is activated by adding the parameter --num-context 1. Please refer to the example running script. The surrounding sentence refers to the sentence before and after the sentence that contains the word to disambiguate.

Thank you for your reply! Another question : you got the state-of-the-art F1 using BERT without finetune?

@chrhad
Copy link
Collaborator

chrhad commented Dec 30, 2020

Thank you for your reply! Another question : you got the state-of-the-art F1 using BERT without finetune?

Yes, we did not fine-tune the BERT model and got the reported state-of-the-art results. However, the sense output layer parameters, which are randomly initialized, are updated during training.

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