Update README.md

README.md

@@ -5,12 +5,14 @@ tags:
 - sentence-transformers
 - feature-extraction
 - sentence-similarity
-
+license: cc-by-nc-sa-4.0
+language:
+- krc
 ---
 
-# {MODEL_NAME}
+# TSjB/labse-krc
 
-This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
 
 <!--- Describe your model here -->
 
@@ -26,13 +28,59 @@ Then you can use the model like this:
 
 ```python
 from sentence_transformers import SentenceTransformer
-sentences = ["This is an example sentence", "Each sentence is converted"]
+sentences = ["This is an example sentence", "Бу айтым юлгюдю"]
 
-model = SentenceTransformer('{MODEL_NAME}')
+model = SentenceTransformer('TSjB/labse-krc')
 embeddings = model.encode(sentences)
 print(embeddings)
 ```
 
+```r
+library(data.table)
+library(reticulate)
+library(ggplot2)
+library(ggrepel)
+library(Rtsne)
+
+py_install("sentence-transformers", pip = TRUE)
+st <- import("sentence_transformers")
+
+english_sentences = base::c("dog", "Puppies are nice.", "I enjoy taking long walks along the beach with my dog.")
+italian_sentences = base::c("cane", "I cuccioli sono carini.", "Mi piace fare lunghe passeggiate lungo la spiaggia con il mio cane.")
+qarachay_sentences = base::c("ит", "Итле джагъымлыдыла.", "Джагъа юсю бла итим бла айланыргъа сюеме.")
+
+model = st$SentenceTransformer('TSjB/labse-krc')
+
+english_embeddings = model$encode(english_sentences)
+italian_embeddings = model$encode(italian_sentences)
+qarachay_embeddings = model$encode(qarachay_sentences)
+
+m <- rbind(english_embeddings,
+           italian_embeddings,
+           qarachay_embeddings) %>% as.matrix
+
+tsne <- Rtsne(m, perplexity = floor((nrow(m) - 1) / 3))
+
+
+tSNE_df <- tsne$Y %>% 
+  as.data.table() %>% 
+  setnames(old = c("V1", "V2"), new = c("tSNE1", "tSNE2")) %>% 
+  .[, `:=`(sentence = c(english_sentences, italian_sentences, qarachay_sentences),
+           language = c(rep("english", length(english_sentences)),
+                        rep("italian", length(italian_sentences)),
+                        rep("qarachay", length(qarachay_sentences))))]
+
+
+tSNE_df %>%
+ ggplot(aes(x = tSNE1, 
+            y = tSNE2,
+            color = language,
+            label = sentence             
+             )
+         )  + 
+    geom_label_repel() +    
+  geom_point()
+```
 
 
 ## Evaluation Results
@@ -90,4 +138,4 @@ SentenceTransformer(
 
 ## Citing & Authors
 
-<!--- Describe where people can find more information -->
+[Bogdan Tewunalany](https://t.me/bogdan_tewunalany), [Ali Berberov](https://t.me/ali_bulat1990)