omarkamali/spacy-nlp
Viewer • Updated • 14.7M • 168
Omar Kamali PRO
omarkamali
AI & ML interests
NLP & LLMs for low resource languages.
Recent Activity
posted an update about 15 hours ago
Apparently grammar can travel without a passport 🌍
We trained a new neural grammar model *Tarakib* across 166 languages on top of Sawtone [1] - itself trained on nearly 400 langs. We then tested it on 28 languages that contributed no training updates to the grammar task.
The surprising result: it still learned useful parts-of-speech structure based on the foundational linguistic representation offered by Sawtone.
Performance varied considerably, and the transfer was not limited to close, same-script relatives but crossed writing systems. We found connections across language families, and about a quarter of the stable transfer links crossed writing systems.
This does not mean universal parsing is solved. But it suggests that Sawtone's representations contain universal grammatical clues that a shared model can reuse in languages it was never directly taught to parse.
A small step toward "spaCy for every language" ✌️
1. https://www.omneitylabs.com/models/sawtone updated a dataset 1 day ago
omarkamali/spacy-nlp new activity 16 days ago
omneity-labs/lid-benchmark:Add CommonLinguaOrganizations
