Personality-dependent Neural Text Summarization

Pablo Costa, Ivandré Paraboni


Abstract
In Natural Language Generation systems, personalization strategies - i.e, the use of information about a target author to generate text that (more) closely resembles human-produced language - have long been applied to improve results. The present work addresses one such strategy - namely, the use of Big Five personality information about the target author - applied to the case of abstractive text summarization using neural sequence-to-sequence models. Initial results suggest that having access to personality information does lead to more accurate (or human-like) text summaries, and paves the way for more robust systems of this kind.
Anthology ID:
R19-1024
Volume:
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)
Month:
September
Year:
2019
Address:
Varna, Bulgaria
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
205–212
Language:
URL:
https://aclanthology.org/R19-1024
DOI:
10.26615/978-954-452-056-4_024
Bibkey:
Cite (ACL):
Pablo Costa and Ivandré Paraboni. 2019. Personality-dependent Neural Text Summarization. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), pages 205–212, Varna, Bulgaria. INCOMA Ltd..
Cite (Informal):
Personality-dependent Neural Text Summarization (Costa & Paraboni, RANLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/remove-xml-comments/R19-1024.pdf