Multitask NLP Classifier with BERT
Multitask BERT for paraphrase detection, semantic textual similarity and sentiment analysis.
NLPDeep Learning
Overview
Implemented multitask learning over a shared BERT encoder for three NLP tasks: Paraphrase Detection, Semantic Textual Similarity (STS) and Sentiment Analysis. Fine-tuned on the canonical benchmarks with strong cross-task generalization.
Key Highlights
- Shared-encoder multitask BERT setup
- Paraphrase + STS + Sentiment in one model
- Strong generalization across all three benchmarks
Tech Stack
PythonPyTorchTransformersHuggingFace
Other Projects
All ProjectsProjection Mapping in Unity3D
Data Engineering
Spatial calibration + blending for multi-projector image/video content, in Unity3D.
View ProjectArc-Mode Classification + PyQt GUI
Deep LearningComputer VisionPython
Deep-learning pipeline that classifies arc appearance modes from high-speed video, with a PyQt analysis GUI.
View ProjectMoving-Object Classification from a Single Line
Deep LearningComputer Vision
Deep CNN that classifies vehicles using only single-line pixel input from traffic videos.
View ProjectStay Updated
Subscribe to get the latest blog posts, project updates, and data science insights straight to your inbox.
No spam. Unsubscribe anytime.