Enhancing Abstractiveness of Summarization Models through Calibrated Distillation

Sequence-level knowledge distillation reduces the size of Seq2Seq models for more efficient abstractive summarization. However, it often leads to a loss of abstractiveness in summarization. In this paper, we propose a novel approach named DisCal to enhance the level of abstractiveness (measured by n...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Song, Hwanjun, Shalyminov, Igor, Su, Hang, Singh, Siffi, Yao, Kaisheng, Mansour, Saab
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computation and Language
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!