# Information Type Classification with Contrastive Task-Specialized Sentence Encoders

arXiv: https://arxiv.org/abs/2312.11020 · HTML: https://mlsanity.com/paper/2312.11020/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 28 references that are in the map.
- First posted on arXiv 18 Dec 2023.

## Builds on (most cited first, 10 of 10)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [Efficient Few-Shot Learning Without Prompts](https://mlsanity.com/paper/2209.11055/) (2022)
- [CrisisMMD: Multimodal Twitter Datasets from Natural Disasters](https://mlsanity.com/paper/1805.00713/) (2018)
- [Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning](https://mlsanity.com/paper/2109.06349/) (2021)
- [HumAID: Human-Annotated Disaster Incidents Data from Twitter with Deep Learning Benchmarks](https://mlsanity.com/paper/2104.03090/) (2021)
- [Unsupervised Label-aware Event Trigger and Argument Classification](https://mlsanity.com/paper/2012.15243/) (2020)
- [ConvFiT: Conversational Fine-Tuning of Pretrained Language Models](https://mlsanity.com/paper/2109.10126/) (2021)
- [I-AID: Identifying Actionable Information from Disaster-related Tweets](https://mlsanity.com/paper/2008.13544/) (2020)
- [Transformer-based Multi-task Learning for Disaster Tweet Categorisation](https://mlsanity.com/paper/2110.08010/) (2021)

## 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.