login
Home / Papers / GSum: A General Framework for Guided Neural Abstractive Summarization

GSum: A General Framework for Guided Neural Abstractive Summarization

199 Citations2021
Zi-Yi Dou, Pengfei Liu, Hiroaki Hayashi
journal unavailable

A general and extensible guided summarization framework that can effectively take different kinds of external guidance as input is proposed and demonstrated, and how different types of guidance generate qualitatively different summaries is demonstrated, lending a degree of controllability to the learned models.

Abstract

Zi-Yi Dou, Pengfei Liu, Hiroaki Hayashi, Zhengbao Jiang, Graham Neubig. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.