arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.18449cs.CLcs.AIcs.LG
收藏

HOP:迈向 NLP 持续学习中的下一任务与领域

HOP to the Next Tasks and Domains for Continual Learning in NLP

Samsung Research UK(三星英国研究院)

Umberto Michieli, Mete Ozay

AI总结:

本文提出统一持续学习框架 HOP,通过 adapter、高阶分布统计量和任务专用辅助头实现跨任务与领域的知识迁移,并在多个 NLP 基准上验证其效果。

摘要:

持续学习(Continual Learning, CL)旨在通过迁移在先前问题上获得的知识来学习一系列问题(即任务和领域),同时避免遗忘过去的问题。不同于以往聚焦于特定用例中单一 NLP 任务或领域的持续学习方法,本文在一个统一框架中处理一种更通用的持续学习设定,即从一系列问题中进行学习。我们的方法 HOP 能够在任务和领域之间跳转,并沿三个方向解决持续学习问题:(i)采用一组 adapter,使大型预训练模型能够泛化到未见过的问题;(ii)在嵌入表示的分布上计算高阶矩,以区分不同任务和领域之间相互独立及相关的统计量;(iii)使用面向每个最终问题的专用辅助头来处理这些增强信息。在 4 个 NLP 应用、5 个基准和 2 种持续学习设置上开展的大量实验,证明了 HOP 的有效性。

英文摘要:

Continual Learning (CL) aims to learn a sequence of problems (i.e., tasks and domains) by transferring knowledge acquired on previous problems, whilst avoiding forgetting of past ones. Different from previous approaches which focused on CL for one NLP task or domain in a specific use-case, in this paper, we address a more general CL setting to learn from a sequence of problems in a unique framework. Our method, HOP, permits to hop across tasks and domains by addressing the CL problem along three directions: (i) we employ a set of adapters to generalize a large pre-trained model to unseen problems, (ii) we compute high-order moments over the distribution of embedded representations to distinguish independent and correlated statistics across different tasks and domains, (iii) we process this enriched information with auxiliary heads specialized for each end problem. Extensive experimental campaign on 4 NLP applications, 5 benchmarks and 2 CL setups demonstrates the effectiveness of our HOP.

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。

↑