%0 Generic
%A Wu, CS
%A Liu, L
%A Liu, W
%A Stenetorp, P
%A Xiong, C
%D 2021
%F discovery:10153278
%I Association for Computational Linguistics
%P 5108-5122
%T Controllable Abstractive Dialogue Summarization with Sketch Supervision
%U https://discovery.ucl.ac.uk/id/eprint/10153278/
%X In this paper, we aim to improve abstractive dialogue summarization quality and, at the same time, enable granularity control. Our model has two primary components and stages: 1) a two-stage generation strategy that generates a preliminary summary sketch serving as the basis for the final summary. This summary sketch provides a weakly supervised signal in the form of pseudo-labeled interrogative pronoun categories and key phrases extracted using a constituency parser. 2) A simple strategy to control the granularity of the final summary, in that our model can automatically determine or control the number of generated summary sentences for a given dialogue by predicting and highlighting different text spans from the source text. Our model achieves state-of-the-art performance on the largest dialogue summarization corpus SAMSum, with as high as 50.79 in ROUGE-L score. In addition, we conduct a case study and show competitive human evaluation results and controllability to human-annotated summaries.
%Z © 2022 ACL. Original content in this paper is licensed under the terms of the Creative Commons Attribution 4.0 International (CC BY 4.0) Licence (https://creativecommons.org/licenses/by/4.0/).