2024/12/12 by Anne-Marie Lutgen, Lutgen, Anne-Marie, Alistair Plum +5 · 1 voice
Computer Science · Mathematics · #Artificial intelligence #Artificial neural network #Computation and Language (cs.CL) #Computer science #Econometrics #FOS: Computer and information sciences #Mathematics #Natural Language Processing Techniques #Normalization (sociology) #Pattern recognition (psychology) #Physics #Social science #Sociology #Speech recognition #Variation (astronomy) #cs.CL
paper · pdf · doi:10.48550/arxiv.2412.09383
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2024/12/12 · arxiv published 2024/12/12 · arxiv updated 2024/12/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.