Towards Spoken Language Understanding via Multi-level Multi-grained Contrastive Learning

TL;DR

This paper introduces a multi-level contrastive learning framework for spoken language understanding that enhances intent detection and slot filling by leveraging relationships at utterance, slot, and word levels, achieving state-of-the-art results.

Contribution

It proposes a novel multi-grained contrastive learning approach with self-distillation for improved SLU performance, addressing the mutual guidance between intent and slot subtasks.

Findings

Achieves 2.6% accuracy improvement on MixATIS dataset.

Demonstrates effectiveness of multi-level contrastive learning.

Outperforms previous state-of-the-art models.

Abstract

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.