Parallel Sense Tagger is a Natural Language Processing (NLP) project that performs Word Sense Disambiguation (WSD).
The system automatically assigns the correct semantic meaning to ambiguous words based on contextual information within a sentence.
This project focuses on improving efficiency by integrating parallel processing techniques during training and inference.
The model is fine-tuned from roberta-base using Hugging Face Transformers and PyTorch.
🔗 Hugging Face Model:
https://huggingface.co/kytrungchauwork/eng-viet-parallel-sense-tagger
Pipeline tag: token-classification
- Fine-tuned RoBERTa model for token-level sense tagging
- Context-aware word sense disambiguation
- Parallelized data preprocessing and training
- Scalable design for large text datasets
- Python
- PyTorch
- Hugging Face Transformers
- Multiprocessing / Parallel Computing
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("your-username/parallel-sense-tagger")
model = AutoModelForTokenClassification.from_pretrained("your-username/parallel-sense-tagger")
text = "The bank is near the river."
inputs = tokenizer(text, return_tensors="pt")
outputs = model(**inputs)