0.9.2

Changes

Fixed loading models without vocabularies from ZIP archives

0.9.1

Changes

Simple_elmo is now compatible with the up-to-date versions of the smart_open library.

0.9.0

Changes

• The get_elmo_vectors() and get_elmo_vector_average() methods can now re-use existing TensorFlow sessions. This is extremely useful, for example, when using ELMo models as embedding generators for downstream models. See an example in the README.
• Further speed improvements for the new experimental get_elmo_substitutes() method for language modeling

0.8.0

Changes

• The new get_elmo_substitutes() method for language modeling now uses batching and is significantly faster.
• Language mode predictions yield lists instead of numpy arrays, for easier serializing.
• Language model predictions yield raw logit scores instead of probabilities.

0.7.0

Changes

• A new get_elmo_substitutes() method for language modeling. Requires full model checkpoint with the softmax weights (should be loaded with full=True). Still experimental.
• The number of deprecation warnings is reduced.

0.6.0

Changes

• Whether to use the top layer or the average of all layers is now the layers argument of the get_elmo_vectors() and get_elmo_vectors_average() methods. It is no longer necessary to state this when loading a model.
• The layers argument can take the all value. In this case, raw weights from all 3 ELMo layers are returned.
• Small fixes

0.5.1

Changes

• Code cleanup
• Word sense disambiguation example

0.5.0

Changes

• The file with model weights to load no longer has to be named model.hdf5: can be anything with the .hdf5 extension.
• Default batch size reduced to 32 (should ease the usage on low-resource machines).
• Warming on the first batch is performed by default (as a rule, slightly improves the performance).
• FAQ added to the Github page.

0.4.1

Changes

• Scikit-learn is no longer required.
• Example scripts moved to the examples directory.

0.4.0

Changes

• Vocabulary file is no longer obligatory when loading a pre-trained model.
• The module name is now officially simple_elmo (with the underscore).