Lost in Translation: Loss and Decay of Linguistic Richness in Machine Translation

2019/06/28 by Eva Vanmassenhove, Vanmassenhove, Eva, Dimitar Shterionov +3 · 5 citations
Arts and Humanities · Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Topic Modeling #Translation Studies and Practices

paper · pdf · doi:10.48550/arxiv.1906.12068

openalex publication_date 2019/06/28 · openalex created_date 2019/07/12 · openalex updated_date 2026/07/28

Abstract

This work presents an empirical approach to quantifying the loss of lexical richness in Machine Translation (MT) systems compared to Human Translation (HT). Our experiments show how current MT systems indeed fail to render the lexical diversity of human generated or translated text. The inability of MT systems to generate diverse outputs and its tendency to exacerbate already frequent patterns while ignoring less frequent ones, might be the underlying cause for, among others, the currently heavily debated issues related to gender biased output. Can we indeed, aside from biased data, talk about an algorithm that exacerbates seen biases?

Citations

• Adam: A Method for Stochastic Optimization

Cited by

• Fluent Alignment with Disfluent Judges: Post-training for Lower-resource Languages
• Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation
• Automatic Machine Translation Detection Using a Surrogate Multilingual Translation Model
• The machine translator’s visibility
• NeoBabel: A Multilingual Open Tower for Visual Generation

Related

• Machine Translationese: Effects of Algorithmic Bias on Linguistic\n Complexity in Machine Translation
• On the Integration of LinguisticFeatures into Statistical and Neural Machine Translation
• Gender Bias in Machine Translation and The Era of Large Language Models
• Thesis proposal: Are We Losing Textual Diversity to Natural Language Processing?
• Misgendering and Assuming Gender in Machine Translation when Working with Low-Resource Languages