Revisiting Syllables in Language Modelling and their Application on Low-Resource Machine Translation

TL;DR

This paper investigates the use of syllables in language modeling and low-resource machine translation, demonstrating their advantages over characters and subwords in various languages and translation tasks.

Contribution

It introduces syllables as an effective unit for language modeling and translation, especially in low-resource and highly synthetic languages, with comprehensive experiments across multiple languages.

Findings

Syllables outperform characters and subwords in perplexity.

Syllables improve translation quality for low-resource, synthetic languages.

Human evaluation confirms the benefits of syllable-based models.

Abstract

Language modelling and machine translation tasks mostly use subword or character inputs, but syllables are seldom used. Syllables provide shorter sequences than characters, require less-specialised extracting rules than morphemes, and their segmentation is not impacted by the corpus size. In this study, we first explore the potential of syllables for open-vocabulary language modelling in 21 languages. We use rule-based syllabification methods for six languages and address the rest with hyphenation, which works as a syllabification proxy. With a comparable perplexity, we show that syllables outperform characters and other subwords. Moreover, we study the importance of syllables on neural machine translation for a non-related and low-resource language-pair (Spanish--Shipibo-Konibo). In pairwise and multilingual systems, syllables outperform unsupervised subwords, and further morphological segmentation methods, when translating into a highly synthetic language with a transparent orthography (Shipibo-Konibo). Finally, we perform some human evaluation, and discuss limitations and opportunities.