English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Leveraging shared learning through Massively Multilingual Models,state-of-the-art machine translation models are often able to adapt to thepaucity of data for low-resource languages. However, this performance comes atthe cost of significantly bloated models which are not practically deployable.Knowledge Distillation is one popular technique to develop competitive,lightweight models: In this work, we first evaluate its use to compress MTmodels focusing on languages with extremely limited training data. Through ouranalysis across 8 languages, we find that the variance in the performance ofthe distilled models due to their dependence on priors including the amount ofsynthetic data used for distillation, the student architecture, traininghyperparameters and confidence of the teacher models, makes distillation abrittle compression mechanism. To mitigate this, we explore the use ofpost-training quantization for the compression of these models. Here, we findthat while distillation provides gains across some low-resource languages,quantization provides more consistent performance trends for the entire rangeof languages, especially the lowest-resource languages in our target set.

Too Brittle To Touch: Comparing the Stability of Quantization and Distillation Towards Developing Lightweight Low-Resource MT Models