Improving named entity correctness of abstractive summarization by generative negative sampling

Open Webpage

Zheng Chen, Hongyu Lin

Published: 01 Jan 2023, Last Modified: 06 Jun 2025Comput. Speech Lang. 2023EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•Named entity error ratio in Chinese abstractive summaries is as high as 58.1%.•We propose generative negative sampling strategies for training the discriminator.•We apply PU learning to improve performance by selecting high-confident samples.