State-of-the-art neural text generation models are typically trained to maximize the likelihood of each token in the ground-truth sequence conditioned on the previous target tokens. However, during inference, the model needs to make a prediction conditioned on the tokens generated by itself. This train-test discrepancy is referred to as exposure bias. Scheduled sampling is a curriculum learning strategy that gradually exposes the model to its own predictions during training to mitigate this bias. Most of the proposed approaches design a scheduler based on training steps, which generally requires careful tuning depending on the training setup. In this work, we introduce Dynamic Scheduled Sampling with Imitation Loss (DySI), which maintains the schedule based solely on the training time accuracy, while enhancing the curriculum learning by introducing an imitation loss, which attempts to make the behavior of the decoder indistinguishable from the behavior of a teacher-forced decoder. DySI is universally applicable across training setups with minimal tuning. Extensive experiments and analysis show that DySI not only achieves notable improvements on standard machine translation benchmarks, but also significantly improves the robustness of other text generation models.

翻译：当前最先进的神经文本生成模型通常基于真实序列中每个标记在前序目标标记条件下的似然最大化进行训练。然而在推理阶段，模型需要基于自身生成的标记进行预测，这种训练-测试不一致性被称为曝光偏差。调度采样是一种课程学习策略，通过在训练过程中逐步使模型暴露于自身预测来缓解该偏差。现有方法大多设计基于训练步数的调度器，这通常需要根据训练设置进行精细调参。本文提出基于模仿损失的动态调度采样方法（DySI），该方法仅依赖训练时准确率维护调度策略，同时通过引入模仿损失增强课程学习效果，该损失旨在使解码器的行为与教师强制解码器的行为难以区分。DySI 可通用适配多种训练设置且仅需最小化调参。大量实验与分析表明，DySI 不仅能在标准机器翻译基准上实现显著提升，还能有效增强其他文本生成模型的鲁棒性。