A Chat About Boring Problems: Studying GPT-based text normalization
Abstract
Text normalization - the conversion of text from written to spoken form - is traditionally assumed to be an ill-formed task for language models. In this work, we argue otherwise. We empirically show the capacity of Large-Language Models (LLM) for text normalization in few-shot scenarios. Combining self-consistency reasoning with linguistic-informed prompt engineering, we find LLM based text normalization to achieve error rates around 40\% lower than top normalization systems. Further, upon error analysis, we note key limitations in the conventional design of text normalization tasks. We create a new taxonomy of text normalization errors and apply it to results from GPT-3.5-Turbo and GPT-4.0. Through this new framework, we can identify strengths and weaknesses of GPT-based TN, opening opportunities for future work.
Cite
@article{arxiv.2309.13426,
title = {A Chat About Boring Problems: Studying GPT-based text normalization},
author = {Yang Zhang and Travis M. Bartley and Mariana Graterol-Fuenmayor and Vitaly Lavrukhin and Evelina Bakhturina and Boris Ginsburg},
journal= {arXiv preprint arXiv:2309.13426},
year = {2024}
}
Comments
Accepted to ICASSP 2024