Адаптерное слияние

AbstractSequential fine-tuning and multi-task learning are methods aiming to incorporate knowledge from multiple tasks; however, they suffer from catastrophic forgetting and difficulties in dataset balancing. To address these shortcomings, we …...

AbstractThanks to the development of pre-trained language models, multitask learning (MTL) methods achieve a great success in natural language understanding area. However, current MTL methods pay more attention to task …...

AbstractThis paper describes the submission of the joint Samsung Research Philippines - Datasaur AI team for the WMT22 Large Scale Multilingual African Translation shared task. We approach the contest as …...

AbstractAssessing the quality of an argument is a complex, highly subjective task, influenced by heterogeneous factors (e.g., prior beliefs of the annotators, topic, domain, and application), and crucial for its …...

AbstractThis paper describes our approach for Subtask 1 of Task 3 at SemEval-2023. In this subtask, task participants were asked to classify multilingual news articles for one of three classes: …...

AbstractLarge pre-trained language models contain societal biases and carry along these biases to downstream tasks. Current in-processing bias mitigation approaches (like adversarial training) impose debiasing by updating a model’s parameters, …...