iiinova — where your digital self keeps evolving

Antonios Dimakis

@antoniosdimakis.bsky.social

PhD fellow at Archimedes Unit, Athena Research Center | PhD student at the National and Kapodistrian University of Athens Interested in NLP for low-resource languages/terms, tokenization, and linguistics

Posts Replies Media

Antonios Dimakis @antoniosdimakis.bsky.social · 25/07/2025

Proud to work with John Pavlopoulos and @antonisa.bsky.social on this publication! Check out the data and code here: github.com/andhmak/rule... 4/4

github.com

GitHub - andhmak/rule_dialnorm: Code and datasets associated with the paper titled "Dialect Normalization using Large Language Models and Morphological Rules"

Code and datasets associated with the paper titled "Dialect Normalization using Large Language Models and Morphological Rules" - GitHub - andhmak/rule_dialnorm: Code and datasets associa...

021

Antonios Dimakis @antoniosdimakis.bsky.social · 25/07/2025

We implement our method for Greek, and experiment on a proverb dataset. We therefore very cheaply extend NLU coverage of models pre-trained on just the standard to almost every Greek dialect. After normalizing we even find cultural insights which were previously obscured! 3/4

Regions clustered based on the embeddings of their proverbs. Normalized proverbs produce much more meaningful groupings.

110

Antonios Dimakis @antoniosdimakis.bsky.social · 25/07/2025

"Dialect Normalization using Large Language Models and Morphological Rules" By applying rule-based, linguistically informed transformations to the input before passing it to a LLM, with targeted few-shot prompting, we can obtain high-quality normalized outputs. 2/4

Table showing normalization quality for different setups, with the full setup obtaining good scores.

100

Antonios Dimakis @antoniosdimakis.bsky.social · 25/07/2025

How can we make models understand dialectal input, even in dialects with very little data available? Our work indicates that Rule-Based Normalization can significantly help. If you're at #ACL2025, check out our poster on Monday at 6pm! aclanthology.org/2025.finding... 1/4

Example of a dialectal sentence being normalized incorrectly when using a base LLM, and the same sentence normalized correctly using our method.

120