Enhancing Abstractiveness of Summarization Models through Calibrated Distillation

Hwanjun Song, Igor Shalyminov, Hang Su, Siffi Singh, Kaisheng Yao, Saab Mansour

Submission Type: Regular Long Paper

Submission Track: Summarization

Submission Track 2: Efficient Methods for NLP

Keywords: abstractive summarization, knowledge distillation

TL;DR: abstractive summarization distillation

Abstract: In this paper, we propose a novel approach named DisCal to enhance the level of abstractiveness (measured by n-gram overlap) without sacrificing the informativeness (measured by ROUGE) of generated summaries. DisCal exposes diverse pseudo summaries with two supervision to the student model. Firstly, the best pseudo summary is identified in terms of abstractiveness and informativeness and used for sequence-level distillation. Secondly, their ranks are used to ensure the student model to assign higher prediction scores to summaries with higher ranks. Our experiments show that DisCal outperforms prior methods in abstractive summarization distillation, producing highly abstractive and informative summaries.

Submission Number: 666