Skip to content

Conversation

@ivansmokovic
Copy link
Collaborator

Adds a Sentence embedding field

…olt/takepod into missing-data-token

� Conflicts:
�	takepod/datasets/iterator.py
�	takepod/storage/field.py
�	test/storage/test_iterator.py
…tenceEmbeddingField

# Conflicts:
#	takepod/datasets/iterator.py
#	takepod/examples/ner_example.py
#	takepod/storage/field.py
#	takepod/storage/vocab.py
#	test/storage/test_field.py
#	test/storage/test_iterator.py
#	test/storage/test_vocab.py
@ivansmokovic ivansmokovic self-assigned this Apr 2, 2020
@ivansmokovic ivansmokovic requested a review from FilipBolt April 17, 2020 13:00
@FilipBolt
Copy link
Collaborator

FilipBolt commented Dec 18, 2020

This PR looks a bit outdated at this point. However, I'd like to have this functionality easily integrated in the NumericalizerABC interface. @ivansmokovic Would you be comfortable with discarding this? I don't see SentenceEmbedding in this form long term, as I believe we need some general free-form input-output contract such that we can transform a single token to a single number, multiple tokens to a single number and multiple tokens to a single number (vector) (SentenceEmbedding case)

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

Successfully merging this pull request may close these issues.

4 participants