roberta-base-thai-char-upos

Model Description

This is a RoBERTa model pre-trained on Thai Wikipedia texts for POS-tagging and dependency-parsing, derived from roberta-base-thai-char. Every word is tagged by UPOS (Universal Part-Of-Speech).

How to Use

import torch
from transformers import AutoTokenizer,AutoModelForTokenClassification
tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/roberta-base-thai-char-upos")
model=AutoModelForTokenClassification.from_pretrained("KoichiYasuoka/roberta-base-thai-char-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

import esupar
nlp=esupar.load("KoichiYasuoka/roberta-base-thai-char-upos")
print(nlp("หลายหัวดีกว่าหัวเดียว"))

See Also

esupar: Tokenizer POS-tagger and Dependency-parser with BERT/RoBERTa/DeBERTa models