-
-
Notifications
You must be signed in to change notification settings - Fork 2.1k
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
Pretrained Model for Keyphrase Extraction #1647
Labels
feature
A new feature
Comments
whoisjones
added a commit
that referenced
this issue
Jun 1, 2020
whoisjones
added a commit
that referenced
this issue
Jun 2, 2020
whoisjones
added a commit
that referenced
this issue
Jun 2, 2020
whoisjones
added a commit
that referenced
this issue
Jun 5, 2020
according to midas-research SciBert gives (almost) the best results among all three keyphrase datasets in flair (metric: f1-score):
|
What are the embeddings used in our model? |
whoisjones
added a commit
that referenced
this issue
Jun 5, 2020
whoisjones
added a commit
that referenced
this issue
Jun 5, 2020
whoisjones
added a commit
that referenced
this issue
Jun 5, 2020
whoisjones
added a commit
that referenced
this issue
Jun 5, 2020
whoisjones
added a commit
that referenced
this issue
Jun 5, 2020
whoisjones
added a commit
that referenced
this issue
Jun 11, 2020
whoisjones
added a commit
that referenced
this issue
Jun 11, 2020
whoisjones
added a commit
that referenced
this issue
Jun 11, 2020
…-keyphrase-tagger-model � Conflicts: � flair/datasets/sequence_labeling.py
whoisjones
added a commit
that referenced
this issue
Jun 11, 2020
alanakbik
added a commit
that referenced
this issue
Jun 11, 2020
gh-1647: pretrained keyphrase tagger model
Model added to Flair in #1689 |
@whoisjones How the model was trained? The scibert was finetuned in the process? What head is used (linear, rnn, crf)? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Since we've integrated Keyphrase Detection Datasets it might a cool to have pretrained model for this. As a foundation we can either use Datasets from #1621 or #1646.
I would train some models and post the results here to check if it makes sense to integrate it.
The text was updated successfully, but these errors were encountered: