Where “where” Matters : Event Location Disambiguation with a BERT Language Model

Hristo Tanev, Bertrand De Longueville


Abstract
The method method presented in this paper uses a BERT model for classifying location mentions in event reporting news texts into two classes: a place of an event, called main location, or another location mention, called here secondary location. Our evaluation on articles, reporting protests, shows promising results and demonstrates the feasibility of our approach and the event geolocation task in general. We evaluate our method against a simple baseline and state of the art ML models and we achieve a significant improvement in all cases by using the BERT model. In contrast to other location classification approaches, we completelly avoid lingusitic pre processing and feature engineering, which is a pre-requisite for all multi-domain and multilingual applications.
Anthology ID:
2023.case-1.2
Volume:
Proceedings of the 6th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text
Month:
sEPTEMBER
Year:
2023
Address:
Varna, Bulgaria
Editors:
Ali Hürriyetoğlu, Hristo Tanev, Vanni Zavarella, Reyyan Yeniterzi, Erdem Yörük, Milena Slavcheva
Venues:
CASE | WS
SIG:
Publisher:
INCOMA Ltd., Shoumen, Bulgaria
Note:
Pages:
11–17
Language:
URL:
https://aclanthology.org/2023.case-1.2
DOI:
Bibkey:
Cite (ACL):
Hristo Tanev and Bertrand De Longueville. 2023. Where “where” Matters : Event Location Disambiguation with a BERT Language Model. In Proceedings of the 6th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text, pages 11–17, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.
Cite (Informal):
Where “where” Matters : Event Location Disambiguation with a BERT Language Model (Tanev & De Longueville, CASE-WS 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.case-1.2.pdf