Zero-shot out-of-distribution detection based on the pre-trained model clip
In an out-of-distribution (OOD) detection problem, samples of known classes (also called in-
distribution classes) are used to train a special classifier. In testing, the classifier can (1) …
distribution classes) are used to train a special classifier. In testing, the classifier can (1) …
Estimating soft labels for out-of-domain intent detection
Out-of-Domain (OOD) intent detection is important for practical dialog systems. To alleviate
the issue of lacking OOD training samples, some works propose synthesizing pseudo OOD …
the issue of lacking OOD training samples, some works propose synthesizing pseudo OOD …
A survey on out-of-distribution detection in nlp
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 …
machine learning systems in the real world. Great progress has been made over the past …
Open-world social event classification
With the rapid development of Internet and the expanding scale of social media, social event
classification has attracted increasing attention. The key to social event classification is …
classification has attracted increasing attention. The key to social event classification is …
Exploring large language models for multi-modal out-of-distribution detection
Out-of-distribution (OOD) detection is essential for reliable and trustworthy machine learning.
Recent multi-modal OOD detection leverages textual information from in-distribution (ID) …
Recent multi-modal OOD detection leverages textual information from in-distribution (ID) …
Generalized intent discovery: Learning from open world dialogue system
Traditional intent classification models are based on a pre-defined intent set and only
recognize limited in-domain (IND) intent classes. But users may input out-of-domain (OOD) …
recognize limited in-domain (IND) intent classes. But users may input out-of-domain (OOD) …
Modeling intra-class and inter-class constraints for out-of-domain detection
Abstract Out-of-Domain (OOD) detection aims to identify whether a query falls outside the
predefined intent set, which is crucial to maintaining high reliability and improving user …
predefined intent set, which is crucial to maintaining high reliability and improving user …
Out-of-scope intent detection with intent-invariant data augmentation
F Sun, H Huang, P Yang, H Xu, X Mao - Knowledge-Based Systems, 2024 - Elsevier
In practical dialogue systems, it is crucial to avoid undesired responses and poor user
experiences by detecting Out-Of-Scope (OOS) intents from user utterances. Currently, to …
experiences by detecting Out-Of-Scope (OOS) intents from user utterances. Currently, to …
Open-World Continual Learning: A Framework
S Mazumder, B Liu - Lifelong and Continual Learning Dialogue Systems, 2024 - Springer
As more and more AI agents are used in practice, we need to think about how to make these
agents fully autonomous so that they can (1) learn by themselves continually in a self …
agents fully autonomous so that they can (1) learn by themselves continually in a self …
Out-of-domain intent detection considering multi-turn dialogue contexts
Out-of-Domain (OOD) intent detection is vital for practical dialogue systems, and it usually
requires considering multi-turn dialogue contexts. However, most previous OOD intent …
requires considering multi-turn dialogue contexts. However, most previous OOD intent …