A multi-task adversarial attack that selectively degrades a target task while preserving or improving other tasks, using negative loss weights and automated weight tuning.
A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methods
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Multi-task learning (MTL) has become increasingly popular in natural language processing (NLP) because it improves the performance of related tasks by exploiting their commonalities and differences. Nevertheless, it is still not understood very well how multi-task learning can be implemented based on the relatedness of training tasks. In this survey, we review recent advances of multi-task learning methods in NLP, with the aim of summarizing them into two general multi-task training methods based on their task relatedness: (i) joint training and (ii) multi-step training. We present examples in various NLP downstream applications, summarize the task relationships and discuss future directions of this promising topic.
fields
cs.CR 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Stealthy Multi-Task Adversarial Attacks
A multi-task adversarial attack that selectively degrades a target task while preserving or improving other tasks, using negative loss weights and automated weight tuning.