Information Type Classification with Contrastive Task-Specialized Sentence Encoders
This work addresses classification challenges in crisis information management, but it appears incremental as it builds on existing methods for task adaptation.
The paper tackled the problem of classifying user-generated information in crisis situations, which suffers from noise and event-related biases, by proposing contrastive task-specialized sentence encoders, resulting in performance gains in F1-score on datasets like CrisisLex, HumAID, and TrecIS.
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.