Discourse as a Function of Event: Profiling Discourse Structure in News Articles around the Main Event

Prafulla Kumar Choubey, Aaron Lee, Ruihong Huang, Lu Wang


Abstract
Understanding discourse structures of news articles is vital to effectively contextualize the occurrence of a news event. To enable computational modeling of news structures, we apply an existing theory of functional discourse structure for news articles that revolves around the main event and create a human-annotated corpus of 802 documents spanning over four domains and three media sources. Next, we propose several document-level neural-network models to automatically construct news content structures. Finally, we demonstrate that incorporating system predicted news structures yields new state-of-the-art performance for event coreference resolution. The news documents we annotated are openly available and the annotations are publicly released for future research.
Anthology ID:
2020.acl-main.478
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5374–5386
Language:
URL:
https://aclanthology.org/2020.acl-main.478
DOI:
10.18653/v1/2020.acl-main.478
Bibkey:
Cite (ACL):
Prafulla Kumar Choubey, Aaron Lee, Ruihong Huang, and Lu Wang. 2020. Discourse as a Function of Event: Profiling Discourse Structure in News Articles around the Main Event. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5374–5386, Online. Association for Computational Linguistics.
Cite (Informal):
Discourse as a Function of Event: Profiling Discourse Structure in News Articles around the Main Event (Choubey et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.478.pdf
Dataset:
 2020.acl-main.478.Dataset.zip
Video:
 http://slideslive.com/38928770