“…Curriculum Learning In recent years, curriculum learning (Bengio et al, 2009), which enables the models to gradually proceed from easy samples to more complex ones in training (Elman, 1993), has received growing research interests in natural language processing field, e.g., neural machine translation (Platanios et al, 2019;Kumar et al, 2019;Zhao et al, 2020;Liu et al, 2020b;Kocmi and Bojar, 2017;Xu et al, 2020) and computer vision field, e.g., image classification (Weinshall et al, 2018), human attribute analysis and visual question answering (Li et al, 2020). For example, in neural machine translation, Platanios et al (2019) proposed to utilize the training samples in order of easy-to-hard and to describe the "difficulty" of a training sample using the sentence length or the rarity of the words appearing in it (Zhao et al, 2020).…”