AligNarr: Aligning Narratives on Movies

Paramita Mirza, Mostafa Abouhamra, Gerhard Weikum


Abstract
High-quality alignment between movie scripts and plot summaries is an asset for learning to summarize stories and to generate dialogues. The alignment task is challenging as scripts and summaries substantially differ in details and abstraction levels as well as in linguistic register. This paper addresses the alignment problem by devising a fully unsupervised approach based on a global optimization model. Experimental results on ten movies show the viability of our method with 76% F1-score and its superiority over a previous baseline. We publish alignments for 914 movies to foster research in this new topic.
Anthology ID:
2021.acl-short.54
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
427–433
Language:
URL:
https://aclanthology.org/2021.acl-short.54
DOI:
10.18653/v1/2021.acl-short.54
Bibkey:
Cite (ACL):
Paramita Mirza, Mostafa Abouhamra, and Gerhard Weikum. 2021. AligNarr: Aligning Narratives on Movies. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 427–433, Online. Association for Computational Linguistics.
Cite (Informal):
AligNarr: Aligning Narratives on Movies (Mirza et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-short.54.pdf
Video:
 https://aclanthology.org/2021.acl-short.54.mp4
Code
 paramitamirza/alignarr