Crowdsourcing Piedmontese to Test LLMs on Non-Standard Orthography

Read full text Summarise with VIRAT
Authors: Gianluca Vico, Jindřch Libovický
Cited by: 0
References: 19

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

We present a crowdsourced dataset for Piedmontese, an endangered Romance language of northwestern Italy.The dataset comprises 145 Italian-Piedmontese parallel sentences derived from Flores+, with translations produced by speakers writing in their natural orthographic style rather than adhering to standardized conventions, along with manual word alignment.We use this resource to benchmark several large language models on tokenization parity, topic classification, and machine translation.Our analysis reveals that Piedmontese incurs a tokenization penalty relative to higher-resource Romance languages, yet LLMs achieve classification performance approaching that of Italian, French, and English.Machine translation results are asymmetric: models translate adequately from Piedmontese into high-resource languages, but generation into Piedmontese remains challenging.The dataset and code are publicly released.• Probabilmente corretta, l'avrei scritta in altro modo [Probably correct, I would have written it differently] • Parzialmente corretta [Partially correct] • Totalmente sbagliata o quasi [Totally wrong or almost] • Non lo so [I do not know] • Risposta mancante, offensiva o non pertinente [Missing, offensive or irrelevant response]

Fields of Study & Subjects

Natural Language Processing Techniques Topic Modeling Speech Recognition and Synthesis

Publication details

Journal / source
Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial)
Pages
70–86
Publication date
1 January 2026
Language
EN