Knowledge and Keywords Augmented Abstractive Sentence Summarization

Shuo Guan


Abstract
In this paper, we study the abstractive sentence summarization. There are two essential information features that can influence the quality of news summarization, which are topic keywords and the knowledge structure of the news text. Besides, the existing knowledge encoder has poor performance on sparse sentence knowledge structure. Considering these, we propose KAS, a novel Knowledge and Keywords Augmented Abstractive Sentence Summarization framework. Tri-encoders are utilized to integrate contexts of original text, knowledge structure and keywords topic simultaneously, with a special linearized knowledge structure. Automatic and human evaluations demonstrate that KAS achieves the best performances.
Anthology ID:
2021.newsum-1.3
Volume:
Proceedings of the Third Workshop on New Frontiers in Summarization
Month:
November
Year:
2021
Address:
Online and in Dominican Republic
Editors:
Giuseppe Carenini, Jackie Chi Kit Cheung, Yue Dong, Fei Liu, Lu Wang
Venue:
NewSum
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
25–32
Language:
URL:
https://aclanthology.org/2021.newsum-1.3
DOI:
10.18653/v1/2021.newsum-1.3
Bibkey:
Cite (ACL):
Shuo Guan. 2021. Knowledge and Keywords Augmented Abstractive Sentence Summarization. In Proceedings of the Third Workshop on New Frontiers in Summarization, pages 25–32, Online and in Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Knowledge and Keywords Augmented Abstractive Sentence Summarization (Guan, NewSum 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/2021.newsum-1.3.pdf
Video:
 https://preview.aclanthology.org/ingest-2024-clasp/2021.newsum-1.3.mp4