3 papers
cs.CV2025
A simple and effective approach for body part recognition on CT scans based on projection estimation
Franko Hrzic, Mohammadreza Movahhedi, Ophelie Lavoie-Gagne +1
It is well known that machine learning models require a high amount of annotated data to obtain optimal performance. Labelling Computed Tomography (CT) data can be a particularly c…
cs.CL2023
Do not Mask Randomly: Effective Domain-adaptive Pre-training by Masking In-domain Keywords
Shahriar Golchin, Mihai Surdeanu, Nazgol Tavabi +1
We propose a novel task-agnostic in-domain pre-training method that sits between generic pre-training and fine-tuning. Our approach selectively masks in-domain keywords, i.e., word…
cs.CL2022
A Compact Pretraining Approach for Neural Language Models
Shahriar Golchin, Mihai Surdeanu, Nazgol Tavabi +1
Domain adaptation for large neural language models (NLMs) is coupled with massive amounts of unstructured data in the pretraining phase. In this study, however, we show that pretra…