The CreativeSumm 2022 Shared Task: A Two-Stage Summarization Model using Scene Attributes

Eunchong Kim, Taewoo Yoo, Gunhee Cho, Suyoung Bae, Yun-Gyung Cheong


Abstract
In this paper, we describe our work for the CreativeSumm 2022 Shared Task, Automatic Summarization for Creative Writing. The task is to summarize movie scripts, which is challenging due to their long length and complex format. To tackle this problem, we present a two-stage summarization approach using both the abstractive and an extractive summarization methods. In addition, we preprocess the script to enhance summarization performance. The results of our experiment demonstrate that the presented approach outperforms baseline models in terms of standard summarization evaluation metrics.
Anthology ID:
2022.creativesumm-1.8
Volume:
Proceedings of The Workshop on Automatic Summarization for Creative Writing
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Editor:
Kathleen Mckeown
Venue:
CreativeSumm
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
51–56
Language:
URL:
https://aclanthology.org/2022.creativesumm-1.8
DOI:
Bibkey:
Cite (ACL):
Eunchong Kim, Taewoo Yoo, Gunhee Cho, Suyoung Bae, and Yun-Gyung Cheong. 2022. The CreativeSumm 2022 Shared Task: A Two-Stage Summarization Model using Scene Attributes. In Proceedings of The Workshop on Automatic Summarization for Creative Writing, pages 51–56, Gyeongju, Republic of Korea. Association for Computational Linguistics.
Cite (Informal):
The CreativeSumm 2022 Shared Task: A Two-Stage Summarization Model using Scene Attributes (Kim et al., CreativeSumm 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.creativesumm-1.8.pdf