Skip to content

issues Search Results · repo:BinWang28/SBERT-WK-Sentence-Embedding language:Python

Filter by

11 results
 (56 ms)

11 results

inBinWang28/SBERT-WK-Sentence-Embedding (press backspace or delete to remove)

BinWang28/SBERT-WK-Sentence-Embedding
Computing embedding for train is extremely slow

Is it normal to cost more than 1 hour to computing embedding?
  • anaivebird
  • 1
  • Opened 
    on Jul 9, 2021
  • #14

BinWang28/SBERT-WK-Sentence-Embedding
How can i get the sentence representations from SBERT-WK

I would like to use the representations for a custom data in downstream clustering. But i don t see how i can obtain the sentence representations using your method. Any help will be appreciated. Thanks ...
  • boscoj2008
  • 3
  • Opened 
    on Apr 16, 2021
  • #13

BinWang28/SBERT-WK-Sentence-Embedding
Biasing Attention

Hello! I had a few questions: 1. I was wondering if you could bias SBERT s attention on certain words, for example if I have a sentence like a brown dog and a cat , I would like to bias towards sentences ...
  • g-luo
  • 4
  • Opened 
    on Feb 14, 2021
  • #12

BinWang28/SBERT-WK-Sentence-Embedding
If I want to use Chinese dataset, what can I do?

  • SomeoneNotLikeYou
  • 1
  • Opened 
    on Dec 14, 2020
  • #11

BinWang28/SBERT-WK-Sentence-Embedding
Is `q` ever used?

Hi, I am very interested in using this method with my own sentence encoder, so I have been going through the code/paper line-by-line to understand it. I noticed that this variable is computed but never ...
  • JohnGiorgi
  • 1
  • Opened 
    on Jun 13, 2020
  • #9

BinWang28/SBERT-WK-Sentence-Embedding
Why not use this methond to finetune Bert?

Hi~ I am a beginner, I have a question. Why not use this method to obtain wk-sentence-embedding and then based on sentence-bert model fintune NLI data to get finetuned model? I see you only based on pre-train ...
  • hlang8160
  • 2
  • Opened 
    on Apr 8, 2020
  • #6

BinWang28/SBERT-WK-Sentence-Embedding
Comparison with sentence-transformers

Hi, any comparison with sentence-transformers form https://github.com/UKPLab/sentence-transformers ? That would be really interesting indeed. 😃
  • MastafaF
  • 6
  • Opened 
    on Apr 7, 2020
  • #5

BinWang28/SBERT-WK-Sentence-Embedding
Whether or not the BERT listed in experimental results of STS tasks (p8, table 3) be fine-tuned?

@BinWang28 Thanks for your great work, it s very inspiring for me. However, for the BERT s poor performance on STS tasks (listed in table III of the SBERT-WK paper), I wonder: if the BERT-[CLS] and Avg. ...
  • slvher
  • 2
  • Opened 
    on Apr 5, 2020
  • #4

BinWang28/SBERT-WK-Sentence-Embedding
Time and Memory consumption

Hi ! I m trying to generate some sequence embeddings using your code almost directly: for b in tqdm(range(0,n,self.params[ batch_size ])): for sent_ids in sentences_index[b:min(b+self.params[ ...
  • Thomzoy
  • 8
  • Opened 
    on Mar 23, 2020
  • #3

BinWang28/SBERT-WK-Sentence-Embedding
Missing file problem

Hello, when I was running, it was suggested that three files could not be found. Could you please provide the download link? The three documents are as follows : added_tokens.json、special_tokens_map.json、tokenizer_config.json ...
  • None403
  • 6
  • Opened 
    on Mar 4, 2020
  • #2
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Restrict your search to the title by using the in:title qualifier.
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Restrict your search to the title by using the in:title qualifier.
Issue search results · GitHub