R2T: Rule-Encoded Loss Functions for Low-Resource Sequence Tagging

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Keita, Mamadou K., Homan, Christopher, Diarra, Sebastien
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915556683153408
author Keita, Mamadou K.
Homan, Christopher
Diarra, Sebastien
author_facet Keita, Mamadou K.
Homan, Christopher
Diarra, Sebastien
contents We introduce the Rule-to-Tag (R2T) framework, a hybrid approach that integrates a multi-tiered system of linguistic rules directly into a neural network's training objective. R2T's novelty lies in its adaptive loss function, which includes a regularization term that teaches the model to handle out-of-vocabulary (OOV) words with principled uncertainty. We frame this work as a case study in a paradigm we call principled learning (PrL), where models are trained with explicit task constraints rather than on labeled examples alone. Our experiments on Zarma part-of-speech (POS) tagging show that the R2T-BiLSTM model, trained only on unlabeled text, achieves 98.2% accuracy, outperforming baselines like AfriBERTa fine-tuned on 300 labeled sentences. We further show that for more complex tasks like named entity recognition (NER), R2T serves as a powerful pre-training step; a model pre-trained with R2T and fine-tuned on just 50 labeled sentences outperformes a baseline trained on 300.
format Preprint
id arxiv_https___arxiv_org_abs_2510_13854
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle R2T: Rule-Encoded Loss Functions for Low-Resource Sequence Tagging
Keita, Mamadou K.
Homan, Christopher
Diarra, Sebastien
Computation and Language
Machine Learning
We introduce the Rule-to-Tag (R2T) framework, a hybrid approach that integrates a multi-tiered system of linguistic rules directly into a neural network's training objective. R2T's novelty lies in its adaptive loss function, which includes a regularization term that teaches the model to handle out-of-vocabulary (OOV) words with principled uncertainty. We frame this work as a case study in a paradigm we call principled learning (PrL), where models are trained with explicit task constraints rather than on labeled examples alone. Our experiments on Zarma part-of-speech (POS) tagging show that the R2T-BiLSTM model, trained only on unlabeled text, achieves 98.2% accuracy, outperforming baselines like AfriBERTa fine-tuned on 300 labeled sentences. We further show that for more complex tasks like named entity recognition (NER), R2T serves as a powerful pre-training step; a model pre-trained with R2T and fine-tuned on just 50 labeled sentences outperformes a baseline trained on 300.
title R2T: Rule-Encoded Loss Functions for Low-Resource Sequence Tagging
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2510.13854