Titlebook: Intent Recognition for Human-Machine Interactions; Hua Xu,Hanlei Zhang,Ting-En Lin Book 2023 Tsinghua University Press 2023 Human Computer

兇兆

其他

FLIRT

Accrue

Dialogue System quality and providing personalized services. Existing research on new intent discovery is divided into three schools based on unknown intent detection, non-clustering, and semi-clustering, but accurately identifying and understanding new types of user intents is still challenging. Efficiently ident

軌道

Intent Recognitionof detecting new user intents that do not appear in the pre-defined intent set is called “unknown intent detection.” After successfully separating unknown intents from known intents, more attention is given to what new intents have been discovered. The process of classifying unknown intents into new

CRASS

描繪

Cocker

Unknown Intent Detection Method Based on Model Post-Processingks are fed into a traditional novelty detection algorithm to detect unknown intents from different perspectives. Finally, the methods mentioned above are combined to facilitate joint prediction. The proposed?method classifies examples that differ from known intents as unknown and does not require an

邪惡的你

Discovering New Intents with Deep Aligned Clusteringer of intent categories is predicted by eliminating low-confidence intent-wise clusters. Extensive experiments on two benchmark datasets show that the method?presented is more robust and achieves substantial improvements over the state-of-the-art methods.

legitimate