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
Interested in NLP for low-resource languages/terms, tokenization, and linguistics
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
After normalizing we even find cultural insights which were previously obscured!
3/4
July 25, 2025 at 5:50 PM
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
After normalizing we even find cultural insights which were previously obscured!
3/4
"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
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
July 25, 2025 at 5:49 PM
"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
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
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
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
July 25, 2025 at 5:46 PM
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
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