Controllable Abstractive Dialogue Summarization with Sketch Supervision
This work addresses the problem of generating controllable summaries for dialogues, which is incremental as it builds on existing methods with added control features.
The paper tackles improving abstractive dialogue summarization quality and enabling granularity control, achieving state-of-the-art performance on the SAMSum corpus with a ROUGE-L score of 50.79.
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.