Estimating soft labels for out-of-domain intent detection

H Lang, Y Zheng, J Sun, F Huang, L Si, Y Li - arXiv preprint arXiv …, 2022 - arxiv.org
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 …

Learning discriminative representations and decision boundaries for open intent detection

H Zhang, H Xu, S Zhao, Q Zhou - IEEE/ACM Transactions on …, 2023 - ieeexplore.ieee.org
Open intent detection is a significant problem in natural language understanding, which
aims to identify the unseen open intent while ensuring known intent identification …

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 …

Few-shot out-of-scope intent classification: analyzing the robustness of prompt-based learning

Y Jiang, M De Raedt, J Deleu, T Demeester… - Applied …, 2024 - Springer
Abstract Out-of-scope (OOS) intent classification is an emerging field in conversational AI
research. The goal is to detect out-of-scope user intents that do not belong to a predefined …

A Segment Augmentation and Prediction Consistency Framework for Multi-label Unknown Intent Detection

J Yang, M Chen, C Liu, B Dai, HT Zheng… - ACM Transactions on …, 2024 - dl.acm.org
Multi-label unknown intent detection is a challenging task where each utterance may contain
not only multiple known but also unknown intents. To tackle this challenge, pioneers …

Multimodal Classification and Out-of-distribution Detection for Multimodal Intent Understanding

H Zhang, Q Zhou, H Xu, J Su, R Evans… - arXiv preprint arXiv …, 2024 - arxiv.org
Multimodal intent understanding is a significant research area that requires effectively
leveraging multiple modalities to analyze human language. Existing methods face two main …

TK-KNN: A Balanced Distance-Based Pseudo Labeling Approach for Semi-Supervised Intent Classification

N Botzer, D Vasquez, T Weninger, I Laradji - arXiv preprint arXiv …, 2023 - arxiv.org
The ability to detect intent in dialogue systems has become increasingly important in modern
technology. These systems often generate a large amount of unlabeled data, and manually …

Improving Open Intent Detection via Triplet-Contrastive Learning and Adaptive Boundary

G Chen, Q Xu, C Zhan, FL Wang, K Liu… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
Open intent detection is a critical task within dialogue systems, aiming to effectively classify
known intents while also identifying unknown intents that have not been encountered in the …

Multi-Granularity Open Intent Classification via Adaptive Granular-Ball Decision Boundary

Y Li, X Ouyang, C Pan, J Zhang, S Zhao, S Xia… - arXiv preprint arXiv …, 2024 - arxiv.org
Open intent classification is critical for the development of dialogue systems, aiming to
accurately classify known intents into their corresponding classes while identifying unknown …

[图书][B] Navigating Social Media Narratives

N Botzer - 2023 - search.proquest.com
As social media continues to shape modern society, understanding how individuals engage
in these online spaces and form overarching narratives is crucial. Narratives have a …