TransformersDocumentClassifier replacing FARMClassifier #1540
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
It would be great to allow zero shot classifier as well. Some cases user what to define their out label and interested in getting probabilities (both with multiclass and without multiclass) |
I thought so too. 👍 |
julian-risch
changed the title
tholor
approved these changes
Sep 30, 2021
| params={"Retriever": {"top_k": 10}, "Classifier": {"top_k": 5}} | ||
| ) | ||
| print(res["documents"][0].to_dict()["meta"]["classification"]["label"]) | ||
| __Note that print_documents() does not output the content of the classification field in the meta data__ |
There was a problem hiding this comment.
Seems quite complicated here to print the meta data. Shall we just add an arg print_meta=True/False to print_documents? Could be helpful in other occasions as well and would simplify this example
…ack into transformers_classifier
…ack into transformers_classifier
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Proposed changes:
closes #1508
Status (please check what you already did):
Limitation: I did not add multi-label classification but that would be easy to add in future.