Tree-Structured Semantic Encoder with Knowledge Sharing for Domain Adaptation in Natural Language Generation

Domain adaptation in natural language generation (NLG) remains challenging because of the high complexity of input semantics across domains and limited data of a target domain. This is particularly the case for dialogue systems, where we want to be able to seamlessly include new domains into the con...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2019-10
Hauptverfasser:	Bo-Hsiang Tseng, Budzianowski, Paweł, Yen-Chen, Wu, Gašić, Milica
Format:	Artikel
Sprache:	eng
Schlagworte:	Adaptation Coders Complexity Domains Knowledge sharing Natural language Semantics Sentences
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!