Information Type Classification with Contrastive Task-Specialized Sentence Encoders
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 10 of its 28 references that are in the map. First posted on arXiv 18 Dec 2023.
Builds on
10 of 28 references.
References · 10
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 973
- 2022Efficient Few-Shot Learning Without Promptscited by 135
- 2018CrisisMMD: Multimodal Twitter Datasets from Natural Disasterscited by 88
- 2021Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuningcited by 46
- 2021HumAID: Human-Annotated Disaster Incidents Data from Twitter with Deep Learning Benchmarkscited by 38
- 2020Unsupervised Label-aware Event Trigger and Argument Classificationcited by 27
- 2021ConvFiT: Conversational Fine-Tuning of Pretrained Language Modelscited by 25
- 2020I-AID: Identifying Actionable Information from Disaster-related Tweetscited by 6
- 2021Transformer-based Multi-task Learning for Disaster Tweet Categorisationcited by 5
Built on by
Not cited yet.