DeepAI AI Chat
Log In Sign Up

Enhancing the Generalization for Intent Classification and Out-of-Domain Detection in SLU

by   Yilin Shen, et al.

Intent classification is a major task in spoken language understanding (SLU). Since most models are built with pre-collected in-domain (IND) training utterances, their ability to detect unsupported out-of-domain (OOD) utterances has a critical effect in practical use. Recent works have shown that using extra data and labels can improve the OOD detection performance, yet it could be costly to collect such data. This paper proposes to train a model with only IND data while supporting both IND intent classification and OOD detection. Our method designs a novel domain-regularized module (DRM) to reduce the overconfident phenomenon of a vanilla classifier, achieving a better generalization in both cases. Besides, DRM can be used as a drop-in replacement for the last layer in any neural network-based intent classifier, providing a low-cost strategy for a significant improvement. The evaluation on four datasets shows that our method built on BERT and RoBERTa models achieves state-of-the-art performance against existing approaches and the strong baselines we created for the comparisons.


page 1

page 2

page 3

page 4


Intent Features for Rich Natural Language Understanding

Complex natural language understanding modules in dialog systems have a ...

CG-BERT: Conditional Text Generation with BERT for Generalized Few-shot Intent Detection

In this paper, we formulate a more realistic and difficult problem setup...

Improving End-to-End Speech-to-Intent Classification with Reptile

End-to-end spoken language understanding (SLU) systems have many advanta...

OneNet: Joint Domain, Intent, Slot Prediction for Spoken Language Understanding

In practice, most spoken language understanding systems process user inp...

Automatic Discovery of Novel Intents Domains from Text Utterances

One of the primary tasks in Natural Language Understanding (NLU) is to r...

A character representation enhanced on-device Intent Classification

Intent classification is an important task in natural language understan...

Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detection

Real-life applications, heavily relying on machine learning, such as dia...