Narrative Embedding: Re-Contextualization Through Attention

Sean Wilner, Daniel Woolridge, Madeleine Glick


Abstract
Narrative analysis is becoming increasingly important for a number of linguistic tasks including summarization, knowledge extraction, and question answering. We present a novel approach for narrative event representation using attention to re-contextualize events across the whole story. Comparing to previous analysis we find an unexpected attachment of event semantics to predicate tokens within a popular transformer model. We test the utility of our approach on narrative completion prediction, achieving state of the art performance on Multiple Choice Narrative Cloze and scoring competitively on the Story Cloze Task.
Anthology ID:
2021.emnlp-main.105
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1393–1405
Language:
URL:
https://aclanthology.org/2021.emnlp-main.105
DOI:
10.18653/v1/2021.emnlp-main.105
Bibkey:
Cite (ACL):
Sean Wilner, Daniel Woolridge, and Madeleine Glick. 2021. Narrative Embedding: Re-Contextualization Through Attention. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 1393–1405, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Narrative Embedding: Re-Contextualization Through Attention (Wilner et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.105.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.105.mp4