Lightweight Baselines for Medical Abstract Classification: DistilBERT with Cross-Entropy as a Strong Default

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Jiaqi, Wang, Tong, Liu, Su, Hu, Xin, Tong, Ran, Wang, Lanruo, Xu, Jiexi
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917030305726464
author Liu, Jiaqi
Wang, Tong
Liu, Su
Hu, Xin
Tong, Ran
Wang, Lanruo
Xu, Jiexi
author_facet Liu, Jiaqi
Wang, Tong
Liu, Su
Hu, Xin
Tong, Ran
Wang, Lanruo
Xu, Jiexi
contents The research evaluates lightweight medical abstract classification methods to establish their maximum performance capabilities under financial budget restrictions. On the public medical abstracts corpus, we finetune BERT base and Distil BERT with three objectives cross entropy (CE), class weighted CE, and focal loss under identical tokenization, sequence length, optimizer, and schedule. DistilBERT with plain CE gives the strongest raw argmax trade off, while a post hoc operating point selection (validation calibrated, classwise thresholds) sub stantially improves deployed performance; under this tuned regime, focal benefits most. We report Accuracy, Macro F1, and WeightedF1, release evaluation artifacts, and include confusion analyses to clarify error structure. The practical takeaway is to start with a compact encoder and CE, then add lightweight calibration or thresholding when deployment requires higher macro balance.
format Preprint
id arxiv_https___arxiv_org_abs_2510_10025
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Lightweight Baselines for Medical Abstract Classification: DistilBERT with Cross-Entropy as a Strong Default
Liu, Jiaqi
Wang, Tong
Liu, Su
Hu, Xin
Tong, Ran
Wang, Lanruo
Xu, Jiexi
Computation and Language
Artificial Intelligence
The research evaluates lightweight medical abstract classification methods to establish their maximum performance capabilities under financial budget restrictions. On the public medical abstracts corpus, we finetune BERT base and Distil BERT with three objectives cross entropy (CE), class weighted CE, and focal loss under identical tokenization, sequence length, optimizer, and schedule. DistilBERT with plain CE gives the strongest raw argmax trade off, while a post hoc operating point selection (validation calibrated, classwise thresholds) sub stantially improves deployed performance; under this tuned regime, focal benefits most. We report Accuracy, Macro F1, and WeightedF1, release evaluation artifacts, and include confusion analyses to clarify error structure. The practical takeaway is to start with a compact encoder and CE, then add lightweight calibration or thresholding when deployment requires higher macro balance.
title Lightweight Baselines for Medical Abstract Classification: DistilBERT with Cross-Entropy as a Strong Default
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2510.10025