AgaMiko commited on
Commit
e2179e3
·
1 Parent(s): 592e94a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -1
README.md CHANGED
@@ -4,9 +4,20 @@ language:
4
  - pl
5
  datasets:
6
  - Wikipedia
 
7
  tags:
8
- - sentence similarity
 
 
 
 
 
 
 
 
 
9
  ---
 
10
  # SHerbert large - Polish SentenceBERT
11
  SentenceBERT is a modification of the pretrained BERT network that use siamese and triplet network structures to derive semantically meaningful sentence embeddings that can be compared using cosine-similarity. Training was based on the original paper [Siamese BERT models for the task of semantic textual similarity (STS)](https://arxiv.org/abs/1908.10084) with a slight modification of how the training data was used. The goal of the model is to generate different embeddings based on the semantic and topic similarity of the given text.
12
 
 
4
  - pl
5
  datasets:
6
  - Wikipedia
7
+ pipeline_tag: sentence-similarity
8
  tags:
9
+ - sentence-transformers
10
+ - feature-extraction
11
+ - sentence-similarity
12
+ widget:
13
+ - source_sentence: "Uczenie maszynowe jest konsekwencją rozwoju idei sztucznej inteligencji i metod jej wdrażania praktycznego."
14
+ sentences:
15
+ - "Głębokie uczenie maszynowe jest sktukiem wdrażania praktycznego metod sztucznej inteligencji oraz jej rozwoju."
16
+ - "Kasparow zarzucił firmie IBM oszustwo, kiedy odmówiła mu dostępu do historii wcześniejszych gier Deep Blue. "
17
+ - "Samica o długości ciała 10–11 mm, szczoteczki na tylnych nogach służące do zbierania pyłku oraz włoski na końcu odwłoka jaskrawo pomarańczowoczerwone. "
18
+ example_title: "Uczenie maszynowe"
19
  ---
20
+
21
  # SHerbert large - Polish SentenceBERT
22
  SentenceBERT is a modification of the pretrained BERT network that use siamese and triplet network structures to derive semantically meaningful sentence embeddings that can be compared using cosine-similarity. Training was based on the original paper [Siamese BERT models for the task of semantic textual similarity (STS)](https://arxiv.org/abs/1908.10084) with a slight modification of how the training data was used. The goal of the model is to generate different embeddings based on the semantic and topic similarity of the given text.
23