A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding

TL;DR

This paper introduces a novel Stack-Propagation framework with token-level intent detection for spoken language understanding, significantly improving intent detection and slot filling accuracy by leveraging intent information more effectively.

Contribution

The paper proposes a joint Stack-Propagation model with token-level intent detection that enhances SLU performance and mitigates error propagation, achieving state-of-the-art results.

Findings

Achieves state-of-the-art performance on two datasets.

Outperforms previous methods by a large margin.

BERT integration further boosts SLU accuracy.

Abstract

Intent detection and slot filling are two main tasks for building a spoken language understanding (SLU) system. The two tasks are closely tied and the slots often highly depend on the intent. In this paper, we propose a novel framework for SLU to better incorporate the intent information, which further guides the slot filling. In our framework, we adopt a joint model with Stack-Propagation which can directly use the intent information as input for slot filling, thus to capture the intent semantic knowledge. In addition, to further alleviate the error propagation, we perform the token-level intent detection for the Stack-Propagation framework. Experiments on two publicly datasets show that our model achieves the state-of-the-art performance and outperforms other previous methods by a large margin. Finally, we use the Bidirectional Encoder Representation from Transformer (BERT) model in our framework, which further boost our performance in SLU task.