datistiquo

> You probably don't want to have _both_ `hs=1` and `negative=10` – both modes enabled – at once. Why not? Isnt it hs with negative sampling? > Also, growing the...

Thank you! > Yep, cosine similarity on plain BERT embeddings usually doesn't work very well. Yes, but I cannot imagine why stopwords or words like "Hallo" have such a high...

> We did that for English ;) I meant something like scraping all corona related text (in german). > If you just feed in one word like "hello" and most...

Hey, I want to get the embeddengs of BERT for BoW Model or just calculating the cosine distance. >Are you really extracting the token embeddings from BERT-as-a-service or are the...

I will check this. I also think that the margin plays a huge role with contrastive loss. Actually, have you normalized your word vectors before input? Maybe that is my...

Isn't it already implemented? In layers.losses there is a contrastive loss function. But I tried, but the loss is always 0. So, indeed it seems not working, although you can...

Hey @tlatkowski . Do you have an idea how I can use the loss other than MSE loss functions? I suppose I need to change the data set reader?

Hi @tlatkowski I already tried this, but I get for the loss zero. I think you also need to change the input dataset to get pairs for the postive and...