---
license: cc-by-sa-4.0
---
# Flair-abbr-roberta-pubmed-plos-unfiltered

This is a stacked model of embeddings from [roberta-large](https://huggingface.co/FacebookAI/roberta-large), [HunFlair pubmed models](https://github.com/flairNLP/flair/blob/master/resources/docs/HUNFLAIR.md) and [character-level language models trained on PLOS](https://github.com/shenbinqian/PLODv2-CLM4AbbrDetection/tree/main/clm), fine-tuning on the [PLODv2 unfiltered dataset](https://github.com/shenbinqian/PLODv2-CLM4AbbrDetection).
It is released with our LREC-COLING 2024 publication [Using character-level models for efficient abbreviation and long-form detection](https://aclanthology.org/2024.lrec-main.270/). It achieves the following results on the test set:

Results on abbreviations:
- Precision: 0.8977
- Recall: 0.9351
- F1: 0.9160


Results on long forms:
- Precision: 0.8726
- Recall: 0.9260
- F1: 0.8985