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.

Sign up for GitHub

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

Jump to bottom

Fixes for NER training with spaCy #136

Closed
honnibal opened this issue Feb 4, 2017 · 2 comments · Fixed by #171
Closed

Fixes for NER training with spaCy #136

honnibal opened this issue Feb 4, 2017 · 2 comments · Fixed by #171
Labels
type:bug 🐛 Inconsistencies or issues which will cause an issue or problem for users or implementors.

Comments

@honnibal
Copy link

honnibal commented Feb 4, 2017

tl;dr: Consider removing nlp.entity.end_training() in spaCy NER training.

Details here: explosion/spaCy#773

Have been working hard on the neural network model, to be launched with spaCy 2.0. This should give much improved performance for both NER and intent classification.
@amn41
Copy link
Contributor

amn41 commented Feb 9, 2017

Thanks! will give this a try

@honnibal
Copy link
Author

honnibal commented Feb 9, 2017

Relevant fix went up on Thinc master last night, and isn't up on PyPi yet.

@tmbo tmbo mentioned this issue Feb 23, 2017
Merged
@tmbo tmbo added the type:bug 🐛 Inconsistencies or issues which will cause an issue or problem for users or implementors. label Feb 23, 2017
taytzehao pushed a commit to taytzehao/rasa that referenced this issue Jul 14, 2023
@chenrui333
chore(deps): cleanup go.mod a little bit (RasaHQ#136)
ca648a3 
* Upgrade docker to v19.03.7

* go mod vendor

* golangci-lint 1.23.8
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
type:bug 🐛 Inconsistencies or issues which will cause an issue or problem for users or implementors.
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Provide option to fine tune spacy NER model instead of training from scratch RasaHQ/rasa
3 participants
@tmbo @amn41 @honnibal