UBC-NLP/marbert
UBC ARBERT and MARBERT Deep Bidirectional Transformers for Arabic
This project offers advanced tools for understanding Arabic text, specifically two powerful language models called ARBERT and MARBERT. These models take raw Arabic text and can classify its sentiment, identify social meanings, determine topics, recognize dialects, or extract named entities. It is ideal for researchers and data scientists who work with large volumes of Arabic language data and need highly accurate text analysis.
114 stars. No commits in the last 6 months.
Use this if you need to perform state-of-the-art natural language understanding tasks on Arabic text, covering both Modern Standard Arabic and various dialects.
Not ideal if your primary focus is on languages other than Arabic or if you need a pre-built application rather than foundational models.
Stars
114
Forks
17
Language
—
License
—
Category
Last pushed
Sep 02, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/UBC-NLP/marbert"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
deepset-ai/FARM
:house_with_garden: Fast & easy transfer learning for NLP. Harvesting language models for the...
CAMeL-Lab/CAMeLBERT
Code and models for "The Interplay of Variant, Size, and Task Type in Arabic Pre-trained...
extreme-bert/extreme-bert
ExtremeBERT is a toolkit that accelerates the pretraining of customized language models on...
Grenzlinie/MgBERT_LLM_Classification_for_Materials_Science
Source code and result for Paper 'A Prompt-Engineered Large Language Model, Deep Learning...
LazerLambda/modern-bert-score
Re-implementation of BERTScore for evaluation of generated text, leveraging vLLM and...