Sepehr Sameni
Sepehr Sameni
No, they are not, the blank can be used to separate repeated characters ("aa" vs "a a" => "a/blank/a" and "a/space/a")
Great question; I can't remember where but there was a guy experimenting with the text encoder for sentence embedding and he was not satisfied with the results (I think (I'm...
Hi @gaphex I didn't write the TPU code and don't have a clue on what's going on. HighCWu wrote it so I'll mention him. @HighCWu can you help us?
Hi, There are some special tokens in the vocabulary(for example BOS stands for Beginning Of Sentence) and we can either put them at the beginning of a lookup table(embedding) or...
Ah, you might be confused by their usage, right? Let's say you want to feed a sentence into your network, so you should add the BOS and EOS tokens to...
@ChiuHsin I guess you are right, and it seems that you were able to solve it(based on the other issue you posted) can you please send a pull request to...
Hi @ChiuHsin, Sorry for the super late reply, well your code seems alright and I think something is wrong in my code. I will look into it as soon as...
Hmm, 9 hours compared to 10 minutes? wow, that is horrible, sadly though I'm swamped with work and can't figure out what's wrong (I checked your code and it seems...
Thanks @MrKamiZhou, so I'm guessing that something is wrong here because Keras shouldn't be this slow. I will try to figure it out as soon as I have some free...
Hi, I'm not entirely sure, but maybe it's because of the subword embeddings? most of the time people don't count input embeddings in their model parameters.