HOP to the Next Tasks and Domains for Continual Learning in NLP
U Michieli, M Ozay - Proceedings of the AAAI Conference on Artificial …, 2024 - ojs.aaai.org
Continual Learning (CL) aims to learn a sequence of problems (ie, tasks and domains) by
transferring knowledge acquired on previous problems, whilst avoiding forgetting of past …
transferring knowledge acquired on previous problems, whilst avoiding forgetting of past …
EvolveDetector: Towards an evolving fake news detector for emerging events with continual knowledge accumulation and transfer
The prevalence of fake news on social media poses devastating and wide-ranging threats to
political beliefs, economic activities, and public health. Due to the continuous emergence of …
political beliefs, economic activities, and public health. Due to the continuous emergence of …
Continual Contrastive Spoken Language Understanding
Recently, neural networks have shown impressive progress across diverse fields, with
speech processing being no exception. However, recent breakthroughs in this area require …
speech processing being no exception. However, recent breakthroughs in this area require …
CLIMB: Imbalanced Data Modelling Using Contrastive Learning with Limited Labels
Abstract Machine learning classifiers typically rely on the assumption of balanced training
datasets, with sufficient examples per class to facilitate effective model learning. However …
datasets, with sufficient examples per class to facilitate effective model learning. However …