You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
First of all, let's try this with the baseline approach - just using a simple linear layer approach. Performance is not what matters as of right now.
Could you use BART for this? Yes you could, but.. BART is an auto-regressive model - cannot refer to the future when processing the past. BERT would be a better choice than BART.
To-do's
delete tokenizer- related fetchers and paths
change the builders: InputsBuilder
we must make sure that the tokens are not split further than it is now..
explore_ inputs_builder
change the builders: LabelsBuilder
explore_labels_builder
rewrite Idiomifier to learn NER with BERT
The text was updated successfully, but these errors were encountered:
How?
First of all, let's try this with the baseline approach - just using a simple linear layer approach. Performance is not what matters as of right now.
Could you use BART for this? Yes you could, but.. BART is an auto-regressive model - cannot refer to the future when processing the past. BERT would be a better choice than BART.
To-do's
tokenizer
- related fetchers and pathsInputsBuilder
LabelsBuilder
Idiomifier
to learn NER with BERTThe text was updated successfully, but these errors were encountered: