Named Entity Recognition on Bangla Language
Fine Tuning BERT for NER on Bengali Language Tagging using HuggingFace
Correspondence Label ID and Label Name
Label ID |
Label Name |
0 |
O |
1 |
B-PER |
2 |
I-PER |
3 |
B-ORG |
4 |
I-ORG |
5 |
B-LOC |
6 |
I-LOC |
Evaluation and Validation
Name |
Precision |
Recall |
F1 |
Accuracy |
Train/Val set |
0.963899 |
0.964770 |
0.964334 |
0.981252 |
Test set |
0.952855 |
0.965105 |
0.958941 |
0.981349 |
Transformers AutoModelForTokenClassification
from transformers import AutoTokenizer, AutoModelForTokenClassification
from transformers import pipeline
tokenizer = AutoTokenizer.from_pretrained("engineersakibcse47/NER_on_Bangla_Language")
model_ner = AutoModelForTokenClassification.from_pretrained("engineersakibcse47/NER_on_Bangla_Language")
pipe = pipeline("ner", model=model_ner, tokenizer=tokenizer, aggregation_strategy="simple")
sample = "বসনিয়া ও হার্জেগোভিনা"
result = pipe(sample)
result