State-of-the-art spoken language understanding (SLU) models have shown
tremendous success in benchmark SLU datasets, yet they still fail in many
practical scenario due to the lack of model compositionality when trained on
limited training data. In this paper, we study two types of compositionality:
(a) novel slot combination, and (b) length generalization. We first conduct
in-depth analysis, and find that state-of-the-art SLU models often learn
spurious slot correlations during training, which leads to poor performance in
both compositional cases. To mitigate these limitations, we create the first
compositional splits of benchmark SLU datasets and we propose the first
compositional SLU model, including compositional loss and paired training that
tackle each compositional case respectively. On both benchmark and
compositional splits in ATIS and SNIPS, we show that our compositional SLU
model significantly outperforms (up to $5\%$ F1 score) state-of-the-art BERT
SLU model.

我们提出了一种基于组合性的口语语言理解模型，通过对位于有限训练数据上进行训练时学习到的模型组合性的两种类型（新颖的槽组合和长度概括）进行深入分析，我们克服了现有模型因训练时学习到的虚假槽相关性而在组合性问题上表现不佳的限制，进而在 ATIS 和 SNIPS 的基准和组合性数据集上展示了该模型相对于最先进的 BERT SLU 模型的显著性能优势（高达 5% 的 F1 分数提升）。