A Case Against Implicit Standards: Homophone Normalization in Machine Translation for Languages that use the Ge'ez Script

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nigatu, Hellina Hailu, Tonja, Atnafu Lambebo, Ademtew, Henok Biadglign, Alemayehu, Hizkel Mitiku, Abadi, Negasi Haile, Belay, Tadesse Destaw, Yimam, Seid Muhie
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915401433088000
author Nigatu, Hellina Hailu
Tonja, Atnafu Lambebo
Ademtew, Henok Biadglign
Alemayehu, Hizkel Mitiku
Abadi, Negasi Haile
Belay, Tadesse Destaw
Yimam, Seid Muhie
author_facet Nigatu, Hellina Hailu
Tonja, Atnafu Lambebo
Ademtew, Henok Biadglign
Alemayehu, Hizkel Mitiku
Abadi, Negasi Haile
Belay, Tadesse Destaw
Yimam, Seid Muhie
contents Homophone normalization, where characters that have the same sound in a writing script are mapped to one character, is a pre-processing step applied in Amharic Natural Language Processing (NLP) literature. While this may improve performance reported by automatic metrics, it also results in models that are not able to understand different forms of writing in a single language. Further, there might be impacts in transfer learning, where models trained on normalized data do not generalize well to other languages. In this paper, we experiment with monolingual training and cross-lingual transfer to understand the impacts of normalization on languages that use the Ge'ez script. We then propose a post-inference intervention in which normalization is applied to model predictions instead of training data. With our simple scheme of post-inference normalization, we show that we can achieve an increase in BLEU score of up to 1.03 while preserving language features in training. Our work contributes to the broader discussion on technology-facilitated language change and calls for more language-aware interventions.
format Preprint
id arxiv_https___arxiv_org_abs_2507_15142
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Case Against Implicit Standards: Homophone Normalization in Machine Translation for Languages that use the Ge'ez Script
Nigatu, Hellina Hailu
Tonja, Atnafu Lambebo
Ademtew, Henok Biadglign
Alemayehu, Hizkel Mitiku
Abadi, Negasi Haile
Belay, Tadesse Destaw
Yimam, Seid Muhie
Computation and Language
Artificial Intelligence
Homophone normalization, where characters that have the same sound in a writing script are mapped to one character, is a pre-processing step applied in Amharic Natural Language Processing (NLP) literature. While this may improve performance reported by automatic metrics, it also results in models that are not able to understand different forms of writing in a single language. Further, there might be impacts in transfer learning, where models trained on normalized data do not generalize well to other languages. In this paper, we experiment with monolingual training and cross-lingual transfer to understand the impacts of normalization on languages that use the Ge'ez script. We then propose a post-inference intervention in which normalization is applied to model predictions instead of training data. With our simple scheme of post-inference normalization, we show that we can achieve an increase in BLEU score of up to 1.03 while preserving language features in training. Our work contributes to the broader discussion on technology-facilitated language change and calls for more language-aware interventions.
title A Case Against Implicit Standards: Homophone Normalization in Machine Translation for Languages that use the Ge'ez Script
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2507.15142