-
Notifications
You must be signed in to change notification settings - Fork 2
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
Sentence embedding field #158
base: master
Are you sure you want to change the base?
Conversation
…olt/takepod into missing-data-token � Conflicts: � takepod/datasets/iterator.py � takepod/storage/field.py � test/storage/test_iterator.py
…olt/takepod into missing-data-token
…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
…beddingField � Conflicts: � test/storage/test_field.py
This PR looks a bit outdated at this point.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) |
Adds a Sentence embedding field