no code implementations • RANLP 2021 • Jean-Philippe Corbeil, Hadi Abdi Ghavidel
In the domain of natural language augmentation, the eligibility of generated samples remains not well understood.
1 code implementation • 23 Apr 2024 • Jean-Philippe Corbeil
In natural language processing applied to the clinical domain, utilizing large language models has emerged as a promising avenue for error detection and correction on clinical notes, a knowledge-intensive task for which annotated data is scarce.
1 code implementation • 5 Jun 2023 • Jean-Michel Attendu, Jean-Philippe Corbeil
Pruned data selection with static methods is based on a score calculated for each training example prior to finetuning, which involves important computational overhead.
no code implementations • 26 Aug 2022 • Jean-Philippe Corbeil, Mia Taige Li, Hadi Abdi Ghavidel
Our pipeline mines intent-span candidates with an extractive Question-Answering Electra model and leverages sentence embeddings to apply a low-level density clustering followed by a top-level hierarchical clustering.
1 code implementation • 25 Sep 2020 • Jean-Philippe Corbeil, Hadi Abdi Ghadivel
We call this approach BET by which we analyze the backtranslation data augmentation on the transformer-based architectures.