Sentence-level Planning for Especially Abstractive Summarization

Andreas Marfurt, James Henderson


Abstract
Abstractive summarization models heavily rely on copy mechanisms, such as the pointer network or attention, to achieve good performance, measured by textual overlap with reference summaries. As a result, the generated summaries stay close to the formulations in the source document. We propose the *sentence planner* model to generate more abstractive summaries. It includes a hierarchical decoder that first generates a representation for the next summary sentence, and then conditions the word generator on this representation. Our generated summaries are more abstractive and at the same time achieve high ROUGE scores when compared to human reference summaries. We verify the effectiveness of our design decisions with extensive evaluations.
Anthology ID:
2021.newsum-1.1
Volume:
Proceedings of the Third Workshop on New Frontiers in Summarization
Month:
November
Year:
2021
Address:
Online and in Dominican Republic
Venues:
EMNLP | newsum
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1–14
Language:
URL:
https://aclanthology.org/2021.newsum-1.1
DOI:
10.18653/v1/2021.newsum-1.1
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.newsum-1.1.pdf
Code
 idiap/sentence-planner
Data
CNN/Daily Mail