A Cascade Approach to Neural Abstractive Summarization with Content Selection and Fusion

Logan Lebanoff, Franck Dernoncourt, Doo Soon Kim, Walter Chang, Fei Liu

Abstract
We present an empirical study in favor of a cascade architecture to neural text summarization. Summarization practices vary widely but few other than news summarization can provide a sufficient amount of training data enough to meet the requirement of end-to-end neural abstractive systems which perform content selection and surface realization jointly to generate abstracts. Such systems also pose a challenge to summarization evaluation, as they force content selection to be evaluated along with text generation, yet evaluation of the latter remains an unsolved problem. In this paper, we present empirical results showing that the performance of a cascaded pipeline that separately identifies important content pieces and stitches them together into a coherent text is comparable to or outranks that of end-to-end systems, whereas a pipeline architecture allows for flexible content selection. We finally discuss how we can take advantage of a cascaded pipeline in neural text summarization and shed light on important directions for future research.
Anthology ID:
2020.aacl-main.52
Volume:
Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing
Month:
December
Year:
2020
Address:
Suzhou, China
Editors:
Kam-Fai Wong, Kevin Knight, Hua Wu
Venue:
AACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
529–535
Language:
URL:
https://aclanthology.org/2020.aacl-main.52
DOI:
Bibkey:
Cite (ACL):
Logan Lebanoff, Franck Dernoncourt, Doo Soon Kim, Walter Chang, and Fei Liu. 2020. A Cascade Approach to Neural Abstractive Summarization with Content Selection and Fusion. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, pages 529–535, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
A Cascade Approach to Neural Abstractive Summarization with Content Selection and Fusion (Lebanoff et al., AACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/2020.aacl-main.52.pdf
Code
 ucfnlp/cascaded-summ
PDF Search Code