---
license: mit
language:
- en
pipeline_tag: text-classification
---

## XLM-RoBERTa-large-tweet-fid-TRC

This is a [XLM-RoBERTa-large](https://huggingface.co/xlm-roberta-large) model trained on the [Tweet-FID](https://arxiv.org/abs/2205.10726) dataset (*"TWEET-FID: An Annotated Dataset for Multiple Foodborne Illness Detection Tasks", Ruofan Hu et al, 2022* ) which is a collection of Twitter to detect incidents of foodborne illnesses.

The model is enriched with a binary classification head to  perform the custom task called Text Relevance Classification (TRC).
The objective is to determine whether a given text is related to a food risk, identified as *class_1*, or not, *class_0*.