OutFlip: Generating Out-of-Domain Samples for Unknown Intent Detection with Natural Language Attack
Out-of-domain (OOD) input detection is vital in a task-oriented dialogue system since the acceptance of unsupported inputs could lead to an incorrect response of the system. This paper proposes OutFlip, a method to generate out-of-domain samples using only in-domain training dataset automatically. A white-box natural language attack method HotFlip is revised to generate out-of-domain samples instead of adversarial examples. Our evaluation results showed that integrating OutFlip-generated out-of-domain samples into the training dataset could significantly improve an intent classification model's out-of-domain detection performance.
Code (1)
Tasks
intent-classificationIntent ClassificationIntent DetectionSimilar Papers 제목 키워드 기반
OutFlip: Generating Examples for Unknown Intent Detection with Natural Language Attack
Unknown Intent Detection Using Multi-Objective Optimization on Deep Learning Classifiers
Modelling and understanding dialogues in a conversation depends on identifying the user intent from the given text. Unknown or new intent detection is a critical task, as in a realistic scenario a user intent may frequen…
Intent DetectionIntent DiscoveryIntent Detection and Discovery from User Logs via Deep Semi-Supervised Contrastive Clustering
Intent Detection is a crucial component of Dialogue Systems wherein the objective is to classify a user utterance into one of multiple pre-defined intents. A pre-requisite for developing an effective intent identifier is…
ClusteringIntent DetectionIntent DiscoveryOpen Intent Discovery+2Disentangling Confidence Score Distribution for Out-of-Domain Intent Detection with Energy-Based Learning
Detecting Out-of-Domain (OOD) or unknown intents from user queries is essential in a task-oriented dialog system. Traditional softmax-based confidence scores are susceptible to the overconfidence issue. In this paper, we…
Intent DetectionOut of Distribution (OOD) DetectionLearning to Classify Open Intent via Soft Labeling and Manifold Mixup
Open intent classification is a practical yet challenging task in dialogue systems. Its objective is to accurately classify samples of known intents while at the same time detecting those of open (unknown) intents. Exist…
intent-classificationIntent ClassificationOutlier Detection