6334513
doi
10.5281/zenodo.6334513
oai:zenodo.org:6334513
user-newseye
user-eu
Khoa Nguyen, Nhu
University of La Rochelle
Lejeune, Gaƫl
Sorbonne University, STIH/CERES
Coustaty, Mickael
University of La Rochelle
Doucet, Antoine
University of La Rochelle
Transformer-based Methods with #Entities for Detecting Emergency Events on Social Media
Boros, Emanuela
University of La Rochelle
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/legalcode
Event detection, Named entity recognition, Transformer
<p>This paper summarizes the participation of the L3i laboratory of the University of La Rochelle in the TREC Incident Streams 2021. This track aimed at identifying critical information present in social media by categorizing and prioritizing tweets in disaster situation to assist emergency service operators. For both classifying tweets by information type, and ranking tweets by criticality, we proposed a multitask and multilabel learning approach based on representing the tweet text and the event types with pre-trained language models, and by highlighting entities and hashtags. We also experimented with bag of words representation and classical machine learning methods for the prioritization task. We conclude that our multitask approach, while it can take advantage from both tasks, achieved the best performance in comparison with different proposed ensembles. Our submissions obtained top performance for the prioritization task, and higher than the median for the information type classification task.</p>
Zenodo
2022-03-07
info:eu-repo/semantics/conferencePaper
6334512
user-newseye
user-eu
award_title=NewsEye: A Digital Investigator for Historical Newspapers; award_number=770299; award_identifiers_scheme=url; award_identifiers_identifier=https://cordis.europa.eu/projects/770299; funder_id=00k4n6c32; funder_name=European Commission;
1646704140.712606
267968
md5:853f7d3214934c7a781e83e8041f0615
https://zenodo.org/records/6334513/files/TREC_2021___Incident_Track___5_November___no_limit___Transformer_based_Methods_for_Detecting_Emergency_Events_on_Social_Media.pdf
public
10.5281/zenodo.6334512
isVersionOf
doi