paper-with-me

Papers

Not All Pretraining are Created Equal: Threshold Tuning and Class Weighting for Imbalanced Polarization Tasks in Low-Resource Settings

2026-03-08 · Abass Oguntade arxiv

This paper describes my submission to the Polarization Shared Task at SemEval-2025, which addresses polarization detection and classification in social media text. I develop Transformer-based systems for English and Swahili across three subtasks: binary polarization detection, multi-label target type classification, and multi-label manifestation identification. The approach leverages multilingual and African language-specialized models (mDeBERTa-v3-base, SwahBERT, AfriBERTa-large), class-weighted loss functions, iterative stratified data splitting, and per-label threshold tuning to handle severe class imbalance. The best configuration, mDeBERTa-v3-base, achieves 0.8032 macro-F1 on validation for binary detection, with competitive performance on multi-label tasks (up to 0.556 macro-F1). Error analysis reveals persistent challenges with implicit polarization, code-switching, and distinguishing heated political discourse from genuine polarization.

📄 PDF Abstract BibTeX arXiv:2603.23534

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Finite sample guarantees for quantile estimation: An application to detector threshold tuning

2021-05-25 · David Umsonst, Justin Ruths, Henrik Sandberg

In threshold-based anomaly detection, we want to tune the threshold of a detector to achieve an acceptable false alarm rate. However, tuning the threshold is often a non-trivial task due to unknown detector output distri…

Anomaly Detection

Sugeno integral generalization applied to improve adaptive image binarization

2020-10-20 · Information Fusion 2020 10 · Bardozzo Francesco, De La Osa Borja, Horansk{\'a}, L'ubom{\'\i}ra 외

Classic adaptive binarization methodologies threshold pixels intensity with re-spect to adjacent pixels exploiting integral images. In turn, integral imagesare generally computed optimally by using the summed-area-table …

Binarization

Multilingual Translation with Extensible Multilingual Pretraining and Finetuning

2020-08-02 · Yuqing Tang, Chau Tran, Xi-An Li, Peng-Jen Chen 외

Recent work demonstrates the potential of multilingual pretraining of creating one model that can be used for various tasks in different languages. Previous work in multilingual pretraining has demonstrated that machine …

Machine TranslationTranslation

Towards Threshold Invariant Fair Classification

2020-06-18 · Mingliang Chen, Min Wu

Effective machine learning models can automatically learn useful information from a large quantity of data and provide decisions in a high accuracy. These models may, however, lead to unfair predictions in certain sense …

BIG-bench Machine LearningClassificationFairnessGeneral Classification

Domain-Specific Japanese ELECTRA Model Using a Small Corpus

2021-09-01 · RANLP 2021 9 · Youki Itoh, Hiroyuki Shinnou

Recently, domain shift, which affects accuracy due to differences in data between source and target domains, has become a serious issue when using machine learning methods to solve natural language processing tasks. With…

ArticlesComputational EfficiencyDocument ClassificationLanguage Modeling+2