通过多级多粒度对比学习迈向口语理解
Towards Spoken Language Understanding via Multi-level Multi-grained Contrastive Learning
AI总结：
针对口语理解中意图与槽位缺乏相互指导的问题，提出多级多粒度对比学习框架MMCL，在话语、槽位和词级别应用对比学习并结合自蒸馏，在两个公开多意图数据集上取得最优结果。
摘要：
口语理解（SLU）是面向任务的对话系统中的核心任务，旨在通过构建语义框架来理解用户的当前目标。SLU通常包含意图检测和槽位填充两个子任务。尽管存在一些联合建模这两个子任务并取得高性能的SLU框架，但大多数框架仍忽略了意图与槽位之间的内在关系，未能实现两个子任务间的相互指导。为解决该问题，我们提出了一种多级多粒度SLU框架MMCL，在话语级、槽位级和词级三个层级应用对比学习，使意图与槽位能够相互指导。在话语级，该框架同时实现了粗粒度对比学习与细粒度对比学习。此外，我们还应用了自蒸馏方法来提升模型的鲁棒性。实验结果及进一步分析表明，我们提出的模型在两个公开的多意图SLU数据集上取得了新的最优结果，与先前的最佳模型相比，在MixATIS数据集上获得了2.6的整体准确率提升。
英文摘要：
Spoken language understanding (SLU) is a core task in task-oriented dialogue systems, which aims at understanding the user's current goal through constructing semantic frames. SLU usually consists of two subtasks, including intent detection and slot filling. Although there are some SLU frameworks joint modeling the two subtasks and achieving high performance, most of them still overlook the inherent relationships between intents and slots and fail to achieve mutual guidance between the two subtasks. To solve the problem, we propose a multi-level multi-grained SLU framework MMCL to apply contrastive learning at three levels, including utterance level, slot level, and word level to enable intent and slot to mutually guide each other. For the utterance level, our framework implements coarse granularity contrastive learning and fine granularity contrastive learning simultaneously. Besides, we also apply the self-distillation method to improve the robustness of the model. Experimental results and further analysis demonstrate that our proposed model achieves new state-of-the-art results on two public multi-intent SLU datasets, obtaining a 2.6 overall accuracy improvement on the MixATIS dataset compared to previous best models.
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。
