# Ustnlp16 at SemEval-2025 Task 9: Improving Model Performance through Imbalance Handling and Focal Loss

arXiv: https://arxiv.org/abs/2505.00021 · HTML: https://mlsanity.com/paper/2505.00021/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 11 references that are in the map.
- First posted on arXiv 24 Apr 2025.

## Builds on (most cited first, 8 of 8)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [Fast WordPiece Tokenization](https://mlsanity.com/paper/2012.15524/) (2020)
- [GoldCoin: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theory](https://mlsanity.com/paper/2406.11149/) (2024)
- [SemEval-2025 Task 9: The Food Hazard Detection Challenge](https://mlsanity.com/paper/2503.19800/) (2025)
- [Chain-of-Choice Hierarchical Policy Learning for Conversational Recommendation](https://mlsanity.com/paper/2310.17922/) (2023)
- [Improved Sampling Techniques for Learning an Imbalanced Data Set](https://mlsanity.com/paper/1601.04756/) (2016)

## Built on by (most cited first, 1 of 1)

- [Vectra: A New Metric, Dataset, and Model for Visual Quality Assessment in E-Commerce In-Image Machine Translation](https://mlsanity.com/paper/2602.07014/) (2026)

## Abstract (arXiv)

Classification tasks often suffer from imbal- anced data distribution, which presents chal- lenges in food hazard detection due to severe class imbalances, short and unstructured text, and overlapping semantic categories. In this paper, we present our system for SemEval- 2025 Task 9: Food Hazard Detection, which ad- dresses these issues by applying data augmenta- tion techniques to improve classification perfor- mance. We utilize transformer-based models, BERT and RoBERTa, as backbone classifiers and explore various data balancing strategies, including random oversampling, Easy Data Augmentation (EDA), and focal loss. Our ex- periments show that EDA effectively mitigates class imbalance, leading to significant improve- ments in accuracy and F1 scores. Furthermore, combining focal loss with oversampling and EDA further enhances model robustness, par- ticularly for hard-to-classify examples. These findings contribute to the development of more effective NLP-based classification models for food hazard detection.