Joint Intent Detection And Slot Filling Based on Continual Learning Model

TL;DR

This paper introduces CLIM, a continual learning model that effectively balances intent detection and slot filling in natural language understanding, achieving state-of-the-art results on ATIS and Snips datasets.

Contribution

The paper proposes a novel continual learning approach that considers different semantic information characteristics and balances accuracy between two related NLU tasks.

Findings

CLIM achieves state-of-the-art performance on ATIS.

CLIM outperforms existing models on Snips.

The model effectively balances accuracy between intent detection and slot filling.

Abstract

Slot filling and intent detection have become a significant theme in the field of natural language understanding. Even though slot filling is intensively associated with intent detection, the characteristics of the information required for both tasks are different while most of those approaches may not fully aware of this problem. In addition, balancing the accuracy of two tasks effectively is an inevitable problem for the joint learning model. In this paper, a Continual Learning Interrelated Model (CLIM) is proposed to consider semantic information with different characteristics and balance the accuracy between intent detection and slot filling effectively. The experimental results show that CLIM achieves state-of-the-art performace on slot filling and intent detection on ATIS and Snips.