Robust Multi-Prototypes Aware Integration for Zero-Shot Cross-Domain Slot Filling

Cross-domain slot filling is a widely explored problem in spoken language understanding (SLU), which requires the model to transfer between different domains under data sparsity conditions. Dominant two-step hierarchical models first extract slot entities and then calculate the similarity score betw...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE signal processing letters 2024, Vol.31, p.3169-3173
Hauptverfasser:	Chen, Shaoshen, Huang, Peijie, Zhu, Zhanbiao, Zhang, Yexing, Xu, Yuhong
Format:	Artikel
Sprache:	eng
Schlagworte:	Biological system modeling Cross-domain learning Embedding Filling Humanities Logic gates Overfitting Predictive models Prototypes Robustness Semantics slot filling spoken language understanding Training Zero shot learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!