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

ner.embed.pth #2

Closed
zhuzhikui opened this issue Dec 4, 2019 · 5 comments
Closed

ner.embed.pth #2

zhuzhikui opened this issue Dec 4, 2019 · 5 comments

Comments

@zhuzhikui
Copy link

What's the file: 'ner.embed.pth '. Is it generated by word2vec. The format of it is not like char + vec

@nooralahzadeh
Copy link
Owner

nooralahzadeh commented Dec 4, 2019

Hi,
It is created in first run to avoid the time of creating embedding for each words from pre_trained model in next runs. As you can see here :

emb_file = os.path.join(args.data, 'ner.embed.pth')

And yes, it is char+vec !

@zhuzhikui
Copy link
Author

Wow! Thanks for relying me. I get it. But when I run my dataset some error happen. And when I run part of my data, it works well. The error is as following:
image

@nooralahzadeh
Copy link
Owner

You'r Welcome.
Did you do preprocessing? It seems some of the tags in dataset are empty ''!

@zhuzhikui
Copy link
Author

I'll check it, thank you!

@nooralahzadeh
Copy link
Owner

I am closing this case, since you didn't update me. Please reopen it if you still have a problem with that!

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