Tutorial for KLUE Relation Extraction.

Fine-tuning klue/bert-base using KLUE RE dataset.

• KLUE Benchmark Official Webpage
• KLUE Official Github
• Model on Huggingface
• Run KLUE RE on free GPU : Ainize Workspace

Usage

• KLUE Relation List

from transformers import AutoTokenizer, AutoModelForSequenceClassification

tokenizer = AutoTokenizer.from_pretrained("ainize/klue-bert-base-re")
model = AutoModelForSequenceClassification.from_pretrained("ainize/klue-bert-base-re")

# Add "<subj>", "</subj>" to both ends of the subject object and "<obj>", "</obj>" to both ends of the object object.
sentence = "<subj>손흥민</subj>은 <obj>대한민국</obj>에서 태어났다."

encodings = tokenizer(sentence, 
                      max_length=128, 
                      truncation=True, 
                      padding="max_length", 
                      return_tensors="pt")

outputs = model(**encodings)

logits = outputs['logits']

preds = torch.argmax(logits, dim=1)

About us

• Teachable NLP - Train NLP models with your own text without writing any code
• Ainize - Deploy ML project using free gpu