This is a Named Entity Recognition model that trained with Thai NER v2.0 Corpus
Training script and split data: https://zenodo.org/record/7761354
The model was trained by WangchanBERTa base model.
Validation from the Validation set
- Precision: 0.830336794125095
- Recall: 0.873701039168665
- F1: 0.8514671513892494
- Accuracy: 0.9736483416628805
Test from the Test set
- Precision: 0.8199168093956447
- Recall: 0.8781446540880503
- F1: 0.8480323927622422
- Accuracy: 0.9724346779516247
Download: HuggingFace Hub
Read more: Thai NER v2.0
Inference
Huggingface doesn't support inference token classification for Thai and It will give wrong tag. You must using this code.
from transformers import AutoTokenizer
from transformers import AutoModelForTokenClassification
from pythainlp.tokenize import word_tokenize # pip install pythainlp
import torch
name="pythainlp/thainer-corpus-v2-base-model"
tokenizer = AutoTokenizer.from_pretrained(name)
model = AutoModelForTokenClassification.from_pretrained(name)
sentence="ฉันชื่อ นางสาวมะลิวา บุญสระดี อาศัยอยู่ที่อำเภอนางรอง จังหวัดบุรีรัมย์ อายุ 23 ปี เพิ่งเรียนจบจาก มหาวิทยาลัยขอนแก่น และนี่คือข้อมูลปลอมชื่อคนไม่มีอยู่จริง อายุ 23 ปี"
cut=word_tokenize(sentence.replace(" ", "<_>"))
inputs=tokenizer(cut,is_split_into_words=True,return_tensors="pt")
ids = inputs["input_ids"]
mask = inputs["attention_mask"]
# forward pass
outputs = model(ids, attention_mask=mask)
logits = outputs[0]
predictions = torch.argmax(logits, dim=2)
predicted_token_class = [model.config.id2label[t.item()] for t in predictions[0]]
def fix_span_error(words,ner):
_ner = []
_ner=ner
_new_tag=[]
for i,j in zip(words,_ner):
#print(i,j)
i=tokenizer.decode(i)
if i.isspace() and j.startswith("B-"):
j="O"
if i=='' or i=='<s>' or i=='</s>':
continue
if i=="<_>":
i=" "
_new_tag.append((i,j))
return _new_tag
ner_tag=fix_span_error(inputs['input_ids'][0],predicted_token_class)
print(ner_tag)
output:
[('ฉัน', 'O'),
('ชื่อ', 'O'),
(' ', 'O'),
('นางสาว', 'B-PERSON'),
('มะลิ', 'I-PERSON'),
('วา', 'I-PERSON'),
(' ', 'I-PERSON'),
('บุญ', 'I-PERSON'),
('สระ', 'I-PERSON'),
('ดี', 'I-PERSON'),
(' ', 'O'),
('อาศัย', 'O'),
('อยู่', 'O'),
('ที่', 'O'),
('อําเภอ', 'B-LOCATION'),
('นาง', 'I-LOCATION'),
('รอง', 'I-LOCATION'),
(' ', 'O'),
('จังหวัด', 'B-LOCATION'),
('บุรีรัมย์', 'I-LOCATION'),
(' ', 'O'),
('อายุ', 'O'),
(' ', 'O'),
('23', 'B-AGO'),
(' ', 'I-AGO'),
('ปี', 'I-AGO'),
(' ', 'O'),
('เพิ่ง', 'O'),
('เรียนจบ', 'O'),
('จาก', 'O'),
(' ', 'O'),
('มหาวิทยาลั', 'B-ORGANIZATION'),
('ยขอนแก่น', 'I-ORGANIZATION'),
(' ', 'O'),
('และ', 'O'),
('นี่', 'O'),
('คือ', 'O'),
('ข้อมูล', 'O'),
('ปลอม', 'O'),
('ชื่อ', 'O'),
('คน', 'O'),
('ไม่', 'O'),
('มี', 'O'),
('อยู่', 'O'),
('จริง', 'O'),
(' ', 'O'),
('อายุ', 'O'),
(' ', 'O'),
('23', 'B-AGO'),
(' ', 'O'),
('ปี', 'I-AGO')]
Cite
Wannaphong Phatthiyaphaibun. (2022). Thai NER 2.0 (2.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.7761354
or BibTeX
@dataset{wannaphong_phatthiyaphaibun_2022_7761354,
author = {Wannaphong Phatthiyaphaibun},
title = {Thai NER 2.0},
month = sep,
year = 2022,
publisher = {Zenodo},
version = {2.0},
doi = {10.5281/zenodo.7761354},
url = {https://doi.org/10.5281/zenodo.7761354}
}
- Downloads last month
- 8,315
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.