Recognizing Arrow Of Time In The Short Stories

Fahimeh Hosseini, Hosein Fooladi, Mohammad Reza Samsami

Abstract
Recognizing the arrow of time in the context of paragraphs in short stories is a challenging task. i.e., given only two paragraphs (excerpted from a random position in a short story), determining which comes first and which comes next is a difficult task even for humans. In this paper, we have collected and curated a novel dataset for tackling this challenging task. We have shown that a pre-trained BERT architecture achieves reasonable accuracy on the task, and outperforms RNN-based architectures.
Anthology ID:
W19-3606
Volume:
Proceedings of the 2019 Workshop on Widening NLP
Month:
August
Year:
2019
Address:
Florence, Italy
Editors:
Amittai Axelrod, Diyi Yang, Rossana Cunha, Samira Shaikh, Zeerak Waseem
Venue:
WiNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14–16
Language:
URL:
https://aclanthology.org/W19-3606
DOI:
Bibkey:
Cite (ACL):
Fahimeh Hosseini, Hosein Fooladi, and Mohammad Reza Samsami. 2019. Recognizing Arrow Of Time In The Short Stories. In Proceedings of the 2019 Workshop on Widening NLP, pages 14–16, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Recognizing Arrow Of Time In The Short Stories (Hosseini et al., WiNLP 2019)
Copy Citation:
Search