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

One of the challenges with finetuning pretrained language models (PLMs) isthat their tokenizer is optimized for the language(s) it was pretrained on, butbrittle when it comes to previously unseen variations in the data. This can forinstance be observed when finetuning PLMs on one language and evaluating themon data in a closely related language variety with no standardized orthography.Despite the high linguistic similarity, tokenization no longer corresponds tomeaningful representations of the target data, leading to low performance in,e.g., part-of-speech tagging.  In this work, we finetune PLMs on seven languages from three differentfamilies and analyze their zero-shot performance on closely related,non-standardized varieties. We consider different measures for the divergencein the tokenization of the source and target data, and the way they can beadjusted by manipulating the tokenization during the finetuning step. Overall,we find that the similarity between the percentage of words that get split intosubwords in the source and target data (the split word ratio difference) is thestrongest predictor for model performance on target data.

Does Manipulating Tokenization Aid Cross-Lingual Transfer? A Study on POS Tagging for Non-Standardized Languages