MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modeling

Tomasz Limisiewicz, Terra Blevins, Hila Gonen, Orevaoghene Ahia, Luke Zettlemoyer


Abstract
A major consideration in multilingual language modeling is how to best represent languages with diverse vocabularies and scripts.Although contemporary text encoding methods cover most of the world’s writing systems, they exhibit bias towards the high-resource languages of the Global West. As a result, texts of underrepresented languages tend to be segmented into long sequences of linguistically meaningless units. To address the disparities, we introduce a new paradigm that encodes the same information with segments of consistent size across diverse languages. Our encoding convention (MYTE) is based on morphemes, as their inventories are more balanced across languages than characters, which are used in previous methods. We show that MYTE produces shorter encodings for all 99 analyzed languages, with the most notable improvements for non-European languages and non-Latin scripts. This, in turn, improves multilingual LM performance and diminishes the perplexity gap throughout diverse languages.
Anthology ID:
2024.acl-long.804
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
15059–15076
Language:
URL:
https://aclanthology.org/2024.acl-long.804
DOI:
10.18653/v1/2024.acl-long.804
Bibkey:
Cite (ACL):
Tomasz Limisiewicz, Terra Blevins, Hila Gonen, Orevaoghene Ahia, and Luke Zettlemoyer. 2024. MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modeling. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15059–15076, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modeling (Limisiewicz et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-long.804.pdf