Edoardo Barba's Projects
Robust recipes to align language models with human and AI preferences
Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
A beautiful, simple, clean, and responsive Jekyll theme for academics
Pytorch implementation of EntQA paper
ESC: Redesigning WSD with Extractive Sense Comprehension
Autoregressive Entity Retrieval
Semeval-2013 and -2015 multilingual WSD datasets for BabelNet 4.0
Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.
On the Variance of the Adaptive Learning Rate and Beyond
π₯Fast State-of-the-Art Tokenizers optimized for Research and Production
π€ Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.
Experiment code for the ACL 2020 paper "Moving Down the Long Tail of Word Sense Disambiguation with Gloss Informed Bi-encoders".