Leveraging Unlabeled Data for Zero-Shot Dialogue State Tracking
The core message of this paper is to leverage unlabeled data in the target domain to improve zero-shot dialogue state tracking performance by utilizing joint and self-training methods.
Effiziente Verarbeitung und Analyse von Inhalten zur Gewinnung von Erkenntnissen: Eine Methode zur Umwandlung von Zero-Shot in Few-Shot Dialogue State Tracking
Durch die Nutzung von ungelabelten Daten im Zielbereich und den Einsatz von Hilfstasks zur Generierung und Auswahl von Dialogzuständen kann die Leistung von Zero-Shot Dialogue State Tracking Modellen deutlich verbessert werden.
Mixture of Prefix Experts for Efficient Zero-Shot Dialogue State Tracking
The proposed Mixture of Prefix Experts (MoPE) model establishes connections between similar slots in different domains, strengthening the model's transfer performance in unseen domains for zero-shot dialogue state tracking.
A Zero-Shot Open-Vocabulary Pipeline for Efficient Dialogue Understanding
A zero-shot, open-vocabulary pipeline system that integrates domain classification and dialogue state tracking, enabling efficient and adaptable task-oriented dialogue understanding without relying on predefined ontologies.
© 2024 by Linnk AI