This causes a mismatch between inference and training input features (doc embeddings during training are correctly calculated in document.py). Is it a bug or is it intentional? There is a call to a method get_average_embedding as a comment but it does not exist.
Document embeddings are not calculated during inference in neuralcoref.pyx, but they are left at zeros.
https://github.com/huggingface/neuralcoref/blob/60338df6f9b0a44a6728b442193b7c66653b0731/neuralcoref/neuralcoref.pyx#L717
This causes a mismatch between inference and training input features (doc embeddings during training are correctly calculated in document.py). Is it a bug or is it intentional? There is a call to a method
get_average_embedding
as a comment but it does not exist.