%0 Conference Proceedings %T Noisy Self-Knowledge Distillation for Text Summarization %A Liu, Yang %A Shen, Sheng %A Lapata, Mirella %Y Toutanova, Kristina %Y Rumshisky, Anna %Y Zettlemoyer, Luke %Y Hakkani-Tur, Dilek %Y Beltagy, Iz %Y Bethard, Steven %Y Cotterell, Ryan %Y Chakraborty, Tanmoy %Y Zhou, Yichao %S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies %D 2021 %8 June %I Association for Computational Linguistics %C Online %F liu-etal-2021-noisy %X In this paper we apply self-knowledge distillation to text summarization which we argue can alleviate problems with maximum-likelihood training on single reference and noisy datasets. Instead of relying on one-hot annotation labels, our student summarization model is trained with guidance from a teacher which generates smoothed labels to help regularize training. Furthermore, to better model uncertainty during training, we introduce multiple noise signals for both teacher and student models. We demonstrate experimentally on three benchmarks that our framework boosts the performance of both pretrained and non-pretrained summarizers achieving state-of-the-art results. %R 10.18653/v1/2021.naacl-main.56 %U https://aclanthology.org/2021.naacl-main.56 %U https://doi.org/10.18653/v1/2021.naacl-main.56 %P 692-703