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

arXiv: https://arxiv.org/abs/2510.13854 · HTML: https://mlsanity.com/paper/2510.13854/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 27 references that are in the map.
- First posted on arXiv 12 Oct 2025.

## Builds on (most cited first, 12 of 12)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Neural Architectures for Named Entity Recognition](https://mlsanity.com/paper/1603.01360/) (2016)
- [Bidirectional LSTM-CRF Models for Sequence Tagging](https://mlsanity.com/paper/1508.01991/) (2015)
- [Regularizing Neural Networks by Penalizing Confident Output Distributions](https://mlsanity.com/paper/1701.06548/) (2017)
- [How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models](https://mlsanity.com/paper/2012.15613/) (2020)
- [Data Programming: Creating Large Training Sets, Quickly](https://mlsanity.com/paper/1605.07723/) (2016)
- [Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems](https://mlsanity.com/paper/1903.12394/) (2019)
- [Label-Free Supervision of Neural Networks with Physics and Domain Knowledge](https://mlsanity.com/paper/1609.05566/) (2016)
- [Feriji: A French-Zarma Parallel Corpus, Glossary & Translator](https://mlsanity.com/paper/2406.05888/) (2024)
- [Grammatical Error Correction for Low-Resource Languages: The Case of Zarma](https://mlsanity.com/paper/2410.15539/) (2024)

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

- [Data Synthesis and Parameter-Efficient Fine-Tuning for Low-Resource NMT: A Case Study on Q'eqchi' Mayan](https://mlsanity.com/paper/2606.09767/) (2026)

## Abstract (arXiv)

We introduce Rule-to-Tag (R2T), a framework that turns linguistic rules into the training signal for neural sequence taggers in low-resource languages. R2T encodes lexical, morphological, and syntactic rules as differentiable loss terms, so that a tagger learns from rules and unlabeled text, with no labeled training data. It also adds an out-of-vocabulary (OOV) loss term that discourages confident predictions on words that no rule covers. R2T is a first instance of a broader paradigm we call principled learning (PrL): using explicit principles as a learning signal, rather than relying on example-based supervision alone. We evaluate R2T on part-of-speech (POS) tagging for Zarma (Songhay), Bambara (Mande), and French (Romance), and on named entity recognition (NER) for Zarma. On Zarma POS tagging, R2T-BiLSTM uses no labeled training data, yet it reaches 0.968 Macro F1. This score comes within 0.007 of a supervised BiLSTM-CRF trained on 300 labeled sentences (0.975) and exceeds AfriBERTa fine-tuned on the same sentences (0.941). On NER, R2T works well as pre-training: after R2T pre-training, a model fine-tuned on 50 labeled sentences outperforms AfriBERTa fine-tuned on 300 (0.83 vs. 0.79 span F1). On Bambara, R2T reaches 0.91 Macro F1 with rules written in about 2.75 hours, while a supervised Masakhane tagger reaches 0.78. We release ZarmaPOS-Bench, a silver-standard Zarma POS corpus, together with ZarmaNER-600 and all trained models, to support future work on under-resourced languages.