识别深度神经网络中多任务学习的有益任务关系
Identifying beneficial task relations for multi-task learning in deep neural networks
摘要:
NLP的深度神经网络中的多任务学习(MTL)最近受到了越来越多的关注,因为它有一些引人注目的好处,包括它有可能有效地正则化模型并减少对标记数据的需求。虽然它在许多NLP任务中带来了显着的改进,但报告的结果好坏参半,并且对MTL导致NLP收益的条件知之甚少。本文揭示了特定的任务关系,可以导致收益MTL模型在单任务设置。
英文摘要:
Multi-task learning (MTL) in deep neural networks for NLP has recently received increasing interest due to some compelling benefits, including its potential to efficiently regularize models and to reduce the need for labeled data. While it has brought significant improvements in a number of NLP tasks, mixed results have been reported, and little is known about the conditions under which MTL leads to gains in NLP. This paper sheds light on the specific task relations that can lead to gains from MTL models over single-task setups.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。