Wu, CS; Liu, L; Liu, W; Stenetorp, P; Xiong, C; (2021) Controllable Abstractive Dialogue Summarization with Sketch Supervision. In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. (pp. pp. 5108-5122). Association for Computational Linguistics

Preview

Text 2021.findings-acl.454.pdf - Published Version Download (731kB) | Preview

Abstract

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.

Download activity - last month

Export as XMLCSVJSON

Download activity - last 12 months

Export as XMLJSONCSV

Downloads by country - last 12 months

Export as XMLCSVJSON

Archive Staff Only

View Item