Sentence-similarity-classifier-for-pyTorch
Sentence-similarity-classifier-for-pyTorch copied to clipboard
demelin
Re-implementation of Mueller's et al., "Siamese Recurrent Architectures for Learning Sentence Similarity." (AAAI, 2016)
I think the code has a little issue in loss calculation: when " # Obtain similarity score predictions by calculating the Manhattan distance between sentence encoding" self.prediction = torch.exp(-torch.norm((self.encoding_a -...
If there is a word in testing set but not in training set, it will raise a 'keyerror'. But there are some situations that cannot avoid this. What can I...
Hi, I am not really sure how are you handling variable length sequences. It would be really helpful if you could help with this!
