POS-tagging only

README.md

@@ -6,7 +6,6 @@ tags:
 - "token-classification"
 - "pos"
 - "wikipedia"
-- "dependency-parsing"
 datasets:
 - "universal_dependencies"
 license: "apache-2.0"
@@ -19,7 +18,7 @@ widget:
 
 ## Model Description
 
-This is a BERT model pre-trained on Thai Wikipedia texts for POS-tagging and dependency-parsing, derived from [bert-base-th-cased](https://huggingface.co/Geotrend/bert-base-th-cased). Every word is tagged by [UPOS](https://universaldependencies.org/u/pos/) (Universal Part-Of-Speech).
+This is a BERT model pre-trained on Thai Wikipedia texts for POS-tagging, derived from [bert-base-th-cased](https://huggingface.co/Geotrend/bert-base-th-cased). Every word is tagged by [UPOS](https://universaldependencies.org/u/pos/) (Universal Part-Of-Speech).
 
 ## How to Use
 
@@ -28,21 +27,5 @@ import torch
 from transformers import AutoTokenizer,AutoModelForTokenClassification
 tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/bert-base-thai-upos")
 model=AutoModelForTokenClassification.from_pretrained("KoichiYasuoka/bert-base-thai-upos")
-s="หลายหัวดีกว่าหัวเดียว"
-t=tokenizer.tokenize(s)
-p=[model.config.id2label[q] for q in torch.argmax(model(tokenizer.encode(s,return_tensors="pt"))["logits"],dim=2)[0].tolist()[1:-1]]
-print(list(zip(t,p)))
 ```
 
-or
-
-```py
-import esupar
-nlp=esupar.load("KoichiYasuoka/bert-base-thai-upos")
-print(nlp("หลายหัวดีกว่าหัวเดียว"))
-```
-
-## See Also
-
-[esupar](https://github.com/KoichiYasuoka/esupar): Tokenizer POS-tagger and Dependency-parser with BERT/RoBERTa models
-