When training a neural network, it will quickly memorise some source-target mappings from your dataset but never learn some others. Yet, memorisation is not easily expressed as a binary feature that is good or bad: individual datapoints lie on a memorisation-generalisation continuum. What determines a datapoint's position on that spectrum, and how does that spectrum influence neural models' performance? We address these two questions for neural machine translation (NMT) models. We use the counterfactual memorisation metric to (1) build a resource that places 5M NMT datapoints on a memorisation-generalisation map, (2) illustrate how the datapoints' surface-level characteristics and a models' per-datum training signals are predictive of memorisation in NMT, (3) and describe the influence that subsets of that map have on NMT systems' performance.

翻译：在训练神经网络时，模型会迅速记忆数据集中某些源语言到目标语言的映射关系，但始终无法学会其他映射。然而，记忆并非简单的二元特征（好或坏）：每个数据点都位于记忆-泛化的连续统上。是什么决定了数据点在该谱系中的位置？该谱系又如何影响神经模型的性能？我们针对神经机器翻译（NMT）模型探讨这两个问题。通过反事实记忆度量方法，我们（1）构建了将500万NMT数据点映射到记忆-泛化图谱的资源；（2）揭示了数据点的表层特征以及模型对每个数据的训练信号如何预测NMT中的记忆现象；（3）描述了该图谱子集对NMT系统性能的影响方式。