Intent Detection and Slot Filling for Vietnamese

TL;DR

This paper introduces the first Vietnamese intent detection and slot filling dataset and proposes a joint model that improves performance by explicitly incorporating intent context, advancing NLP capabilities for low-resource languages.

Contribution

The paper provides a new Vietnamese dataset and extends the JointBERT+CRF model with an intent-slot attention layer for better slot filling accuracy.

Findings

Proposed model outperforms JointBERT+CRF on Vietnamese dataset.

First publicly available Vietnamese intent detection and slot filling dataset.

Model effectively incorporates intent context for improved slot filling.

Abstract

Intent detection and slot filling are important tasks in spoken and natural language understanding. However, Vietnamese is a low-resource language in these research topics. In this paper, we present the first public intent detection and slot filling dataset for Vietnamese. In addition, we also propose a joint model for intent detection and slot filling, that extends the recent state-of-the-art JointBERT+CRF model with an intent-slot attention layer to explicitly incorporate intent context information into slot filling via "soft" intent label embedding. Experimental results on our Vietnamese dataset show that our proposed model significantly outperforms JointBERT+CRF. We publicly release our dataset and the implementation of our model at: https://github.com/VinAIResearch/JointIDSF