ELLEN: Extremely Lightly Supervised Learning For Efficient Named Entity Recognition

1 code implementation • 26 Mar 2024 • Haris Riaz, Razvan-Gabriel Dumitru, Mihai Surdeanu

In a zero-shot setting, ELLEN also achieves over 75% of the performance of a strong, fully supervised model trained on gold data.

Language Modelling named-entity-recognition +2

Enhancing Transformer RNNs with Multiple Temporal Perspectives

1 code implementation • 4 Feb 2024 • Razvan-Gabriel Dumitru, Darius Peteleaza, Mihai Surdeanu

Further, the additional parameters necessary for the multiple temporal perspectives are fine-tuned with minimal computational overhead, avoiding the need for a full pre-training.

Using DUCK-Net for Polyp Image Segmentation

1 code implementation • Nature Scientific Reports 2023 • Razvan-Gabriel Dumitru, Darius Peteleaza, Catalin Craciun

While our architecture is versatile and applicable to various segmentation tasks, in this study, we demonstrate its capabilities specifically for polyp segmentation in colonoscopy images.

Data Augmentation Image Segmentation +2