I²KD-SLU：面向零样本跨语言口语理解的内部-相互知识蒸馏框架
I$^2$KD-SLU: An Intra-Inter Knowledge Distillation Framework for Zero-Shot Cross-Lingual Spoken Language Understanding
AI总结：
针对零样本跨语言SLU中意图与槽位缺乏相互引导的问题，提出I²KD-SLU框架，通过语言内同类预测蒸馏及意图-槽位跨任务蒸馏，在MultiATIS++上达到新SOTA。
摘要：
口语理解（SLU）通常包括意图检测和槽位填充两个子任务。目前，它在高资源语言中已取得巨大成功，但由于标注训练数据稀缺，在低资源语言中仍具挑战性。因此，零样本跨语言SLU日益受到关注。尽管现有零样本跨语言SLU模型取得了成功，但其中大多数忽视了实现意图与槽位之间的相互引导。为解决这一问题，我们提出了一种用于零样本跨语言口语理解的内部-相互知识蒸馏框架（I²KD-SLU），以建模这种相互引导。具体而言，我们不仅对同一话语在不同语言中的意图预测之间或槽位预测之间应用内部知识蒸馏，还对同一话语的意图预测与槽位预测之间应用相互知识蒸馏。实验结果表明，与强基线相比，我们提出的框架显著提升了性能，并在MultiATIS++数据集上取得了新的最先进性能，在总体准确率上较此前最佳模型获得显著提升。
英文摘要：
Spoken language understanding (SLU) typically includes two subtasks: intent detection and slot filling. Currently, it has achieved great success in high-resource languages, but it still remains challenging in low-resource languages due to the scarcity of labeled training data. Hence, there is a growing interest in zero-shot cross-lingual SLU. Despite of the success of existing zero-shot cross-lingual SLU models, most of them neglect to achieve the mutual guidance between intent and slots. To address this issue, we propose an Intra-Inter Knowledge Distillation framework for zero-shot cross-lingual Spoken Language Understanding (I$^2$KD-SLU) to model the mutual guidance. Specifically, we not only apply intra-knowledge distillation between intent predictions or slot predictions of the same utterance in different languages, but also apply inter-knowledge distillation between intent predictions and slot predictions of the same utterance. Our experimental results demonstrate that our proposed framework significantly improves the performance compared with the strong baselines and achieves the new state-of-the-art performance on the MultiATIS++ dataset, obtaining a significant improvement over the previous best model in overall accuracy.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
