Representation-Learning-for-Information-Extraction
Representation-Learning-for-Information-Extraction copied to clipboard
Praneet9
Pytorch implementation of Paper by Google Research - Representation Learning for Information Extraction from Form-like Documents.
The linear projection after the self attention: `bs = self_attention.size(0)` `self_attention = self_attention.view(bs, -1)` `linear_proj = F.relu(self.linear_projection(self_attention))` From the paper, they said "We project the self-attended neighbor encodings to a...
Have you experimented with altering the candidate selection process? I am interested in what occurs when the candidate selection process is simplified or removed entirely so that every possible candidate...
why files not found in candidates directory when training is started?
The whole system can be dockerized for an easier setup procedure for training or inferencing.
 My candidate recall is already as high as 0.95, but as you can see during training, the recall on the validation set is very low.
@Praneet9 The NER to extract address candidates is having accuracy issue and difficult to separate multiple address. Do you know any way , how to train model , example bert...
I have noticed that in train.py and eval.py you have import a FocalLoss class which is then used as criterion for both training and evaluating. But I couldn't find relevant...
