Osama-Rakan-Al-Mraikhat commited on
Commit
9ab51a4
·
verified ·
1 Parent(s): 77f3f47

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -0
README.md CHANGED
@@ -1,3 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  # NeoAraBERT
2
  NeoAraBERT is a state-of-the-art open-source Arabic text-embedding model built on the NeoBERT architecture. We pretrain NeoAraBERT on diverse open-source and internal datasets covering modern standard, classical, and dialectal Arabic. We guided our design choices with Arabic tailored ablation studies including text normalization, light stemming, and diacritics-aware tokenization handling. We also performed POS-aware token masking and learning-rate scheduling ablation studies. We benchmarked NeoAraBERT against five top-performing Arabic models on 23 tasks, including a synonym-based task, [Muradif](https://huggingface.co/datasets/U4RASD/Muradif), that directly assesses embedding quality with no additional fine-tuning. NeoAraBERT variants rank first in 18 tasks and improve average performance across the full benchmark suite.
3
 
 
1
+ ---
2
+ license: cc-by-sa-4.0
3
+ language:
4
+ - ar
5
+ base_model:
6
+ - U4RASD/NeoAraBERT
7
+ tags:
8
+ - NeoAraBERT
9
+ - NeoBERT
10
+ - BERT
11
+ - MSA
12
+ - dialect-arabic
13
+ - masked-language-model
14
+ pipeline_tag: feature-extraction
15
+ ---
16
  # NeoAraBERT
17
  NeoAraBERT is a state-of-the-art open-source Arabic text-embedding model built on the NeoBERT architecture. We pretrain NeoAraBERT on diverse open-source and internal datasets covering modern standard, classical, and dialectal Arabic. We guided our design choices with Arabic tailored ablation studies including text normalization, light stemming, and diacritics-aware tokenization handling. We also performed POS-aware token masking and learning-rate scheduling ablation studies. We benchmarked NeoAraBERT against five top-performing Arabic models on 23 tasks, including a synonym-based task, [Muradif](https://huggingface.co/datasets/U4RASD/Muradif), that directly assesses embedding quality with no additional fine-tuning. NeoAraBERT variants rank first in 18 tasks and improve average performance across the full benchmark suite.
18