Generating Contrastive Narratives Using the Brownian Bridge Process for Narrative Coherence Learning

Feiteng Mu, Wenjie Li


Abstract
A major challenge for narrative reasoning is to learn narrative coherence. Existing works mainly follow the contrastive learning paradigm. However, the negative samples in their methods can be easily distinguished, which makes their methods unsatisfactory. In this work, we devise two strategies for mining hard negatives, including (1) crisscrossing a narrative and its contrastive variants; and (2) event-level replacement. To obtain contrastive variants, we utilize the Brownian Bridge process to guarantee the quality of generated contrastive narratives. We evaluate our model on several tasks. The result proves the effectiveness of our method, and shows that our method is applicable to many applications.
Anthology ID:
2024.acl-long.353
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6538–6555
Language:
URL:
https://aclanthology.org/2024.acl-long.353
DOI:
10.18653/v1/2024.acl-long.353
Bibkey:
Cite (ACL):
Feiteng Mu and Wenjie Li. 2024. Generating Contrastive Narratives Using the Brownian Bridge Process for Narrative Coherence Learning. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6538–6555, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Generating Contrastive Narratives Using the Brownian Bridge Process for Narrative Coherence Learning (Mu & Li, ACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2024.acl-long.353.pdf
Video:
 https://preview.aclanthology.org/add_acl24_videos/2024.acl-long.353.mp4