# Neural Text Normalization for Luxembourgish using Real-Life Variation Data

arXiv: https://arxiv.org/abs/2412.09383 · HTML: https://mlsanity.com/paper/2412.09383/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 39 references that are in the map.
- First posted on arXiv 12 Dec 2024.

## Builds on (most cited first, 10 of 10)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [ByT5: Towards a token-free future with pre-trained byte-to-byte models](https://mlsanity.com/paper/2105.13626/) (2021)
- [A Simple Recipe for Multilingual Grammatical Error Correction](https://mlsanity.com/paper/2106.03830/) (2021)
- [DaN+: Danish Nested Named Entities and Lexical Normalization](https://mlsanity.com/paper/2105.11301/) (2021)
- [LuxBank: The First Universal Dependency Treebank for Luxembourgish](https://mlsanity.com/paper/2411.04813/) (2024)
- [Lexical Normalization for Code-switched Data and its Effect on POS-tagging](https://mlsanity.com/paper/2006.01175/) (2020)
- ['UFAL at MultiLexNorm 2021: Improving Multilingual Lexical Normalization by Fine-tuning ByT5](https://mlsanity.com/paper/2110.15248/) (2021)
- [Experiments to Improve Named Entity Recognition on Turkish Tweets](https://mlsanity.com/paper/1410.8668/) (2014)

## Built on by (most cited first, 6 of 6)

- [Do LLMs Judge Distantly Supervised Named Entity Labels Well? Constructing the JudgeWEL Dataset](https://mlsanity.com/paper/2601.00411/) (2026)
- [LuxBorrow: From Pompier to Pompjee, Tracing Borrowing in Luxembourgish](https://mlsanity.com/paper/2603.10789/) (2026)
- [A Subword Embedding Approach for Variation Detection in Luxembourgish User Comments](https://mlsanity.com/paper/2602.11795/) (2026)
- [Variation is the Norm: Embracing Sociolinguistics in NLP](https://mlsanity.com/paper/2603.24222/) (2026)
- [ltzGLUE: Luxembourgish General Language Understanding Evaluation](https://mlsanity.com/paper/2604.17976/) (2026)
- [Language Ideologies in a Multilingual Society: An LLM-based Analysis of Luxembourgish News Comments](https://mlsanity.com/paper/2604.27661/) (2026)

## Abstract (arXiv)

Orthographic variation is very common in Luxembourgish texts due to the absence of a fully-fledged standard variety. Additionally, developing NLP tools for Luxembourgish is a difficult task given the lack of annotated and parallel data, which is exacerbated by ongoing standardization. In this paper, we propose the first sequence-to-sequence normalization models using the ByT5 and mT5 architectures with training data obtained from word-level real-life variation data. We perform a fine-grained, linguistically-motivated evaluation to test byte-based, word-based and pipeline-based models for their strengths and weaknesses in text normalization. We show that our sequence model using real-life variation data is an effective approach for tailor-made normalization in Luxembourgish.