6036739
doi
10.5281/zenodo.6036739
oai:zenodo.org:6036739
user-aidaproject
user-eu
Despoina Chatzakou
Information Technologies Institute, Centre for Research and Technology Hellas
Theodora Tsikrika
Information Technologies Institute, Centre for Research and Technology Hellas
Stefanos Vrochidis
Information Technologies Institute, Centre for Research and Technology Hellas
Ioannis Kompatsiaris
Information Technologies Institute, Centre for Research and Technology Hellas
Leveraging Transformer Self Attention Encoder for Crisis Event Detection in Short Texts
Pantelis Kyriakidis
Information Technologies Institute, Centre for Research and Technology Hellas
info:eu-repo/semantics/openAccess
Creative Commons Attribution 2.0 Generic
https://creativecommons.org/licenses/by/2.0/legalcode
Self attention
Multihead attention
Crisis event detection
<p>Analyzing content generated on social media has proven to be a powerful tool for early detection of crisis-related events. Such an analysis may allow for timely action, mitigating or even preventing altogether the effects of a crisis. However, the high noise levels in short texts present in microblogging platforms, combined with the limited publicly available datasets have rendered the task difficult. Here, we propose deep learning models based on a transformer self-attention encoder, which is capable of detecting event-related parts in a text, while also minimizing potential noise levels. Our models efficacy is shown by experimenting with CrisisLexT26, achieving up to 81.6% f1-score and 92.7% AUC.</p>
This preprint has not undergone peer review (when applicable) or any post-submission improvements or corrections. The Version of Record of this contribution is published in the 44th European Conference on Information Retrieval, and is available online at https://doi.org/10.1007/978-3-030-99739-7_19
Zenodo
2022-02-10
info:eu-repo/semantics/conferencePaper
6036738
user-aidaproject
user-eu
award_title=IMMERSE. INTERACT. INVESTIGATE; award_number=883293; award_identifiers_scheme=url; award_identifiers_identifier=https://cordis.europa.eu/projects/883293; funder_id=00k4n6c32; funder_name=European Commission;
award_title=Artificial Intelligence and advanced Data Analytics for Law Enforcement Agencies; award_number=883596; award_identifiers_scheme=url; award_identifiers_identifier=https://cordis.europa.eu/projects/883596; funder_id=00k4n6c32; funder_name=European Commission;
1673512438.353228
372448
md5:bdcb24641493d1f4408f17285c5189bd
https://zenodo.org/records/6036739/files/Leveraging Transformer Self Attention Encoder.pdf
public
10.5281/zenodo.6036738
isVersionOf
doi