Multi-grained Label Refinement Network with Dependency Structures for Joint Intent Detection and Slot Filling

TL;DR

This paper introduces a multi-grained label refinement network that leverages dependency structures and label semantics to improve joint intent detection and slot filling in natural language understanding.

Contribution

It proposes a novel model integrating dependency structures and label semantic embeddings for better task performance.

Findings

Achieves competitive results on two public datasets.

Utilizes dependency structures via graph attention layers.

Combines syntactic and semantic information for improved accuracy.

Abstract

Slot filling and intent detection are two fundamental tasks in the field of natural language understanding. Due to the strong correlation between these two tasks, previous studies make efforts on modeling them with multi-task learning or designing feature interaction modules to improve the performance of each task. However, none of the existing approaches consider the relevance between the structural information of sentences and the label semantics of two tasks. The intent and semantic components of a utterance are dependent on the syntactic elements of a sentence. In this paper, we investigate a multi-grained label refinement network, which utilizes dependency structures and label semantic embeddings. Considering to enhance syntactic representations, we introduce the dependency structures of sentences into our model by graph attention layer. To capture the semantic dependency between the syntactic information and task labels, we combine the task specific features with corresponding label embeddings by attention mechanism. The experimental results demonstrate that our model achieves the competitive performance on two public datasets.