论文标题
各种示范改善了文化的组成概括
Diverse Demonstrations Improve In-context Compositional Generalization
论文作者
论文摘要
在I.I.D语义解析拆分中表现出了巨大的成功，其中训练和测试集来自相同的分布。在此设置中，通常会提示模型，这些演示与输入话语相似。但是，在组成概括的设置中，在训练集中缺乏结构的输出上测试了模型，选择相似的演示不足，因为通常没有示例与输入相似。在这项工作中，我们提出了一种选择各种演示的方法，旨在集体涵盖输出计划中所需的所有结构，以鼓励模型从这些演示中推广到新结构。我们从经验上表明，将各种示范与内在的学习结合在一起，可以大大改善纯粹的内在学习设置中的三个组成概括语义解析数据集的性能，并在与Finetuning结合使用时。
In-context learning has shown great success in i.i.d semantic parsing splits, where the training and test sets are drawn from the same distribution. In this setup, models are typically prompted with demonstrations that are similar to the input utterance. However, in the setup of compositional generalization, where models are tested on outputs with structures that are absent from the training set, selecting similar demonstrations is insufficient, as often no example will be similar enough to the input. In this work, we propose a method to select diverse demonstrations that aims to collectively cover all of the structures required in the output program, in order to encourage the model to generalize to new structures from these demonstrations. We empirically show that combining diverse demonstrations with in-context learning substantially improves performance across three compositional generalization semantic parsing datasets in the pure in-context learning setup and when combined with finetuning.
