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

Arturo Oncevay, Kervy Dante Rivas Rojas, Liz Karen Chavez Sanchez, Roberto Zariquiey


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.
Anthology ID:
2022.coling-1.374
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
4258–4267
Language:
URL:
https://aclanthology.org/2022.coling-1.374
DOI:
Bibkey:
Cite (ACL):
Arturo Oncevay, Kervy Dante Rivas Rojas, Liz Karen Chavez Sanchez, and Roberto Zariquiey. 2022. Revisiting Syllables in Language Modelling and Their Application on Low-Resource Machine Translation. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4258–4267, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Revisiting Syllables in Language Modelling and Their Application on Low-Resource Machine Translation (Oncevay et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.374.pdf