Hot answers tagged

4

That layer isn't required indeed as it also encodes the sequence, albeit in a different way than BERT. What I assume is that in a BERT-BiLSTM-CRF, setup, the BERT layer is either frozen or difficult to fine-tune due to its sheer size. Which is likely why the BiLSTM layer has been added there.


1

This is likely due to overfitting, and it won't be easy to combat. If you would ask a skilled technical analyst you would notice that he is not using the same features you are inputting into the LSTM. Also, he has the capability of generalizing. If you would be able to feed the same input into an LSTM then maybe you could have similar results, but I would ...


1

The issue was resolved once I used Tensor View to reshape the mini-batches for the features in the training and in the validation set. As a side note, view() enable fast and memory-efficient reshaping, slicing, and element-wise operations, by avoiding an explicit data copy. It turned out that in the earlier implementation torch.unsqueeze() did not reshape ...


1

What you would typically do in your case is to apply a sentence alignment tool. Some popular options for that are: hunalign: a classical tool that relies on a bilingual dictionary. bleualign: it aligns based on the BLEU score similarity vecalign: it is based on sentence embeddings, like LASER's. I suggest you take a look at the preprocessing applied for ...


1

You answered yourself [sequence length, 1] is correct assuming you work with a single sentence. (Or actually, the 1 dimension depends on implementation.) In practice, the data is typically batched, so it will be [batch, sequence length 1]. This can be element-wise multiplied with the encoder states of dimension [batch, sequence length, hidden size] and ...


1

I'm not particularly expert in this but I'm quite sure that the variations in the price of anything depend mostly on external factors: news of the day, economic indicators, stockmarket movements, etc. As a rule of thumb, if a human with a lot of time can't do it, usually a ML model can't do it either. In this case if an expert in finance is given the history ...


1

The tough part about this problem is evaluating what moves are "correct" per se. In a fighting game sequence, there may be 2 or more moves which both work in theory in the current frame. If you are optimizing for knocking the other character out of frame, it would be useful to build a reward set which optimizes for this. It may be worthwhile to ...


Only top voted, non community-wiki answers of a minimum length are eligible