User-generated information content has become an important information source in crisis situations. However, classification models suffer from noise and event-related biases which still poses a challenging task and requires sophisticated task-adaptation. To address these challenges, we propose the use of contrastive task-specialized sentence encoders for downstream classification. We apply the task-specialization on the CrisisLex, HumAID, and TrecIS information type classification tasks and show performance gains w.r.t. F1-score. Furthermore, we analyse the cross-corpus and cross-lingual capabilities for two German event relevancy classification datasets.
@article{arxiv.2312.11020,
title = {Information Type Classification with Contrastive Task-Specialized Sentence Encoders},
author = {Philipp Seeberger and Tobias Bocklet and Korbinian Riedhammer},
journal= {arXiv preprint arXiv:2312.11020},
year = {2023}
}