Curriculum Learning (CL) is a technique of training models via ranking examples in a typically increasing difficulty trend with the aim of accelerating convergence and improving generalisability. Current approaches for Natural Language Understanding (NLU) tasks use CL to improve in-distribution data performance often via heuristic-oriented or task-agnostic difficulties. In this work, instead, we employ CL for NLU by taking advantage of training dynamics as difficulty metrics, i.e., statistics that measure the behavior of the model at hand on specific task-data instances during training and propose modifications of existing CL schedulers based on these statistics. Differently from existing works, we focus on evaluating models on in-distribution (ID), out-of-distribution (OOD) as well as zero-shot (ZS) cross-lingual transfer datasets. We show across several NLU tasks that CL with training dynamics can result in better performance mostly on zero-shot cross-lingual transfer and OOD settings with improvements up by 8.5% in certain cases. Overall, experiments indicate that training dynamics can lead to better performing models with smoother training compared to other difficulty metrics while being 20% faster on average. In addition, through analysis we shed light on the correlations of task-specific versus task-agnostic metrics.
翻译:课程学习(CL)是一种培训模式的技巧,在典型的日益困难趋势中,通过排名实例进行培训,目的是加速趋同和改进通用性。目前,自然语言理解(NLU)任务的方法使用CL来提高分布数据性能,通常是通过超理论性或跨语言传输(ZS)数据集来提高分布数据性能。在这项工作中,我们为NLU采用CL, 利用培训动态作为难度度量,即统计数据,衡量培训中特定任务数据实例的当前模式行为,并根据这些统计数据建议修改现有的CL时间表。与现有工作不同,我们侧重于评价分配(ID)、分配外分配(OOD)和零点(ZS)跨语言传输数据集的模型。我们从几个NLLU任务中显示,培训动态的CL能够提高绩效,主要是零点跨语言传输和OOD环境的绩效,在某些情况下改进了8.5%。总体而言,实验表明,培训动态可以使模型的运行得更好,而与其他困难度培训相比,与其他困难度(ID)指标相比,同时进行20 %的进度分析。