Intent classification, to identify the speaker's intention, and slot filling, to label each token
with a semantic type, are critical tasks in natural language understanding. Traditionally the …

Pretrained Transformers achieve remarkable performance when training and test data are
from the same distribution. However, in real-world scenarios, the model often faces out-of …

Open intent classification is a challenging task in dialogue systems. On the one hand, it
should ensure the quality of known intent identification. On the other hand, it needs to detect …

Identifying the unknown (novel) user intents that have never appeared in the training set is a
challenging task in the dialogue system. In this paper, we present a two-stage method for …

Natural Language Understanding (NLU) is a vital component of dialogue systems, and its
ability to detect Out-of-Domain (OOD) inputs is critical in practical applications, since the …

Detecting Out-of-Domain (OOD) or unknown intents from user queries is essential in a task-
oriented dialog system. A key challenge of OOD detection is to learn discriminative semantic …

Detecting out-of-domain (OOD) input intents is critical in the task-oriented dialog system.
Different from most existing methods that rely heavily on manually labeled OOD samples, we …

Out-of-domain (OOD) detection for low-resource text classification is a realistic but
understudied task. The goal is to detect the OOD cases with limited in-domain (ID) training …

When faced with an out-of-distribution (OOD) question or image, visual question answering
(VQA) systems may provide unreliable answers. If relied on by real users or secondary …

Out-of-distribution (OOD) detection is essential for the reliable and safe deployment of
machine learning systems in the real world. Great progress has been made over the past …