R2T: Rule-Encoded Loss Functions for Low-Resource Sequence Tagging
This addresses the problem of data scarcity for low-resource languages in NLP, offering a hybrid approach that is incremental in combining rules with neural methods.
The paper tackles low-resource sequence tagging by introducing the R2T framework, which integrates linguistic rules into a neural network's training objective, achieving 98.2% accuracy on Zarma POS tagging with unlabeled text and outperforming baselines in NER with minimal labeled data.
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.