See Also

README.md

@@ -15,7 +15,7 @@ pipeline_tag: "token-classification"
 
 ## Model Description
 
-This is a XLM-RoBERTa model pre-trained on English corpus for POS-tagging, derived from [xlm-roberta-base](https://huggingface.co/xlm-roberta-base). Every word is tagged by [UPOS](https://universaldependencies.org/u/pos/) (Universal Part-Of-Speech).
+This is a XLM-RoBERTa model pre-trained with [UD_English-EWT](https://github.com/UniversalDependencies/UD_English-EWT) for POS-tagging and dependency-parsing, derived from [xlm-roberta-base](https://huggingface.co/xlm-roberta-base). Every word is tagged by [UPOS](https://universaldependencies.org/u/pos/) (Universal Part-Of-Speech).
 
 ## How to Use
 
@@ -25,3 +25,14 @@ tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/xlm-roberta-base-english-
 model=AutoModelForTokenClassification.from_pretrained("KoichiYasuoka/xlm-roberta-base-english-upos")
 ```
 
+or
+
+```py
+import esupar
+nlp=esupar.load("KoichiYasuoka/xlm-roberta-base-english-upos")
+```
+
+## See Also
+
+[esupar](https://github.com/KoichiYasuoka/esupar): Tokenizer POS-tagger and Dependency-parser with BERT/RoBERTa models
+