-
Hi! I hope you are doing well!
I am a newbie and here I am doing a prediction task using cosine similarity, in CosineSimilarityLoss
(https://github.com/UKPLab/sentence-transformers/blob/master/se…
-
I've been getting some errors when computing/loading extensions from a `SortingAnalyzer` containig a `template_metrics` extension. I calculate extensions from a dict as follows:
```py
phy_exts = {…
-
Hi, thank you for this excellent work, I am already using it in my project which shows impressive results.
I just want to ask about the training objective:
https://github.com/facebookresearch/Q…
-
Hi, I have a question about the loss function choice. As I see, you have used dot product for similarity of features. Did you experiment using L1, L2 MSE, others or their combination. I am asking beca…
-
I was wondering what is the similarity metric used in the paper. It doesn't seem to be defined anywhere. It looks like cosine similarity. Can someone please confirm?
-
The calculation of cosine similarity in your code is as follows,
dist_i = F.conv2d(featureI_i, featureT_patch)
But I do not understand why conv2d can implement it, can you explain it? Th…
-
Title is fairly self explanatory, I've found the need for cosine distance at various times (and other distance metrics) that probably fit well in ndarray-stats. Maybe here we can decided on a few diff…
-
In _Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks_ Section 4:Evaluation - Semantic Textual Similarity, you include the Spearman rank correlation between the cosine similarity of the e…
-
-
We calculate a topic distribution for each document**(1)** and calculate topic distribution for the given input text (2) with keywords. We need to find similar documents in the matrix of topic/documen…