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 2401.03563cs.CLcs.IR
收藏

数据课程:基于指令的学习的句子表示学习

Data-CUBE: Data Curriculum for Instruction-based Sentence Representation Learning

School of Information, Renmin University of China(中国人民大学信息学院);Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学歌华人工智能学院);Alibaba Group(阿里巴巴集团)

Yingqian Min, Kun Zhou, Dawei Gao, Wayne Xin Zhao, He Hu, Yaliang Li

AI总结:

本文提出Data-CUBE数据课程方法,通过优化任务顺序和实例难度分配,减少多任务学习中的干扰,提升句子表示学习性能。

摘要:

最近,多任务指令微调已被应用于句子表示学习,通过任务指令指导生成特定表示,展现出在新任务上的强泛化能力。然而,这些方法大多忽略了不同任务和实例间的潜在干扰问题,可能影响模型训练和收敛。为此,我们提出Data-CUBE数据课程方法,通过安排所有多任务数据的顺序进行训练,以最小化来自两个视角的干扰风险。在任务层面,我们旨在找到最优的任务顺序以最小化总跨任务干扰风险,即旅行推销员问题,因此利用模拟退火算法寻找其解。在实例层面,我们测量所有实例的难度,然后将它们分成由易到难的mini-batch进行训练。在MTEB句子表示评估任务上的实验表明,我们的方法可以提升最先进的方法性能。我们的代码和数据可在链接:https://github.com/RUCAIBox/Data-CUBE 上公开获取。

英文摘要:

Recently, multi-task instruction tuning has been applied into sentence representation learning, which endows the capability of generating specific representations with the guidance of task instruction, exhibiting strong generalization ability on new tasks. However, these methods mostly neglect the potential interference problems across different tasks and instances, which may affect the training and convergence of the model. To address it, we propose a data curriculum method, namely Data-CUBE, that arranges the orders of all the multi-task data for training, to minimize the interference risks from the two views. In the task level, we aim to find the optimal task order to minimize the total cross-task interference risk, which is exactly the traveling salesman problem, hence we utilize a simulated annealing algorithm to find its solution. In the instance level, we measure the difficulty of all instances per task, then divide them into the easy-to-difficult mini-batches for training. Experiments on MTEB sentence representation evaluation tasks show that our approach can boost the performance of state-of-the-art methods. Our code and data are publicly available at the link: \url{https://github.com/RUCAIBox/Data-CUBE}.

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。

↑