Out-of-Scope Intent Detection with Self-Supervision and Discriminative Training

Abstract

Out-of-scope intent detection is of practical importance in task-oriented dialogue systems. Since the distribution of outlier utterances is arbitrary and unknown in the training stage, existing methods commonly rely on strong assumptions on data distribution such as mixture of Gaussians to make inference, resulting in either complex multi-step training procedures or hand-crafted rules such as confidence threshold selection for outlier detection. In this paper, we propose a simple yet effective method to train an out-of-scope intent classifier in a fully end-to-end manner by simulating the test scenario in training, which requires no assumption on data distribution and no additional post-processing or threshold setting. Specifically, we construct a set of pseudo outliers in the training stage, by generating synthetic outliers using inliner features via self-supervision and sampling out-of-scope sentences from easily available open-domain datasets. The pseudo outliers are used to train a discriminative classifier that can be directly applied to and generalize well on the test task. We evaluate our method extensively on four benchmark dialogue datasets and observe significant improvements over state-of-the-art approaches. Our code has been released at https://github.com/liam0949/DCLOOS.

arXiv commentPublished as long oral paper in ACL 2021

References in corpus (10)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• HuggingFace's Transformers: State-of-the-art Natural Language Processing
• A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
• Using Pre-Training Can Improve Model Robustness and Uncertainty
• Deep Anomaly Detection with Outlier Exposure
• Weakly-Supervised Neural Text Classification
• Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples
• Deep Open Intent Classification with Adaptive Decision Boundary
• Robustness properties of Facebook's ResNeXt WSL models
• Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference