Handling Bahasa Rojak (Malaysian Code Mixing Language) OOV and performing Sentiment Analysis using downstreamed Cross Lingual Model XLM-RoBERTa (XLM-T)
Jupyter Notebooks includes detailing of:
- Text Preprocessing
- Model Fine Tuning
- New Data Inference Pipeline
For further resources regarding the project, please access link below.
Access the project here: https://drive.google.com/drive/folders/12Uir9KE4B1VL6oQWdj2BWvCUZOC0vWa2