update all ref of chinese to arabic

README.md

@@ -77,18 +77,18 @@ We will add more details here.
 
 <center>
   <img src="./ar_metrics_2.png" width=120%/>
-  <b><p>Table 2: Detailed Chinese retrieval performance on the MIRACL dev set (measured by nDCG@10)</p></b>
+  <b><p>Table 2: Detailed Arabic retrieval performance on the MIRACL dev set (measured by nDCG@10)</p></b>
   
 </center>
 
 Full set of evaluation numbers for our model
 
 ```python
-{'NDCG@1': 0.43511, 'NDCG@3': 0.42434, 'NDCG@5': 0.45298, 'NDCG@10': 0.50914, 'NDCG@100': 0.5815, 'NDCG@1000': 0.59392}
-{'MAP@1': 0.21342, 'MAP@3': 0.32967, 'MAP@5': 0.36798, 'MAP@10': 0.39908, 'MAP@100': 0.42592, 'MAP@1000': 0.42686}
-{'Recall@10': 0.63258, 'Recall@50': 0.85, 'Recall@100': 0.91595, 'Recall@200': 0.942, 'Recall@500': 0.96924, 'Recall@1000': 0.9857}
-{'P@1': 0.43511, 'P@3': 0.29177, 'P@5': 0.22545, 'P@10': 0.14758, 'P@100': 0.02252, 'P@1000': 0.00249}
-{'MRR@10': 0.55448, 'MRR@100': 0.56288, 'MRR@1000': 0.56294}
+{'NDCG@1': 0.50449, 'NDCG@3': 0.52437, 'NDCG@5': 0.55649, 'NDCG@10': 0.60599, 'NDCG@100': 0.64745, 'NDCG@1000': 0.65717}
+{'MAP@1': 0.34169, 'MAP@3': 0.45784, 'MAP@5': 0.48922, 'MAP@10': 0.51316, 'MAP@100': 0.53012, 'MAP@1000': 0.53069}
+{'Recall@10': 0.72479, 'Recall@50': 0.87686, 'Recall@100': 0.91178, 'Recall@200': 0.93593, 'Recall@500': 0.96254, 'Recall@1000': 0.97557}
+{'P@1': 0.50449, 'P@3': 0.29604, 'P@5': 0.21581, 'P@10': 0.13149, 'P@100': 0.01771, 'P@1000': 0.0019}
+{'MRR@10': 0.61833, 'MRR@100': 0.62314, 'MRR@1000': 0.62329}
 ```
 
 <br/>
@@ -109,7 +109,7 @@ from sentence_transformers import SentenceTransformer
 import scipy.spatial
 
 
-model = SentenceTransformer('prithivida/miniMiracle_zh_v1')
+model = SentenceTransformer('prithivida/miniDense_arabic_v1')
 
 corpus = [
     '一个男人正在吃东西',
@@ -167,19 +167,19 @@ for query, query_embedding in zip(queries, query_embeddings):
 
 #### How do I offer hybrid search to improve accuracy ?
 MIRACL paper shows simply combining BM25 is a good starting point for a Hybrid option: 
-The below numbers are with mDPR model, but miniMiracle_zh_v1 should give a even better hybrid performance.
+The below numbers are with mDPR model, but miniDense_arabic_v1 should give a even better hybrid performance.
 
 | Language  | ISO | nDCG@10 BM25 | nDCG@10 mDPR | nDCG@10 Hybrid |
 |-----------|-----|--------------|--------------|----------------|
-| **Chinese**     | **zh**  | **0.175**        | **0.512**        | **0.526**          |
+| **Arabic**     | **zh**  | **0.175**        | **0.512**        | **0.526**          |
 
-*Note: MIRACL paper shows a different (higher) value for BM25 Chinese, So we are taking that value from BGE-M3 paper, rest all are form the MIRACL paper.*
+*Note: MIRACL paper shows a different (higher) value for BM25 Arabic, So we are taking that value from BGE-M3 paper, rest all are form the MIRACL paper.*
 
 #### cMTEB numbers:
 CMTEB is a general purpose embedding evaluation benchmark covering wide range of tasks, but like BGE-M3, miniMiracle models are predominantly tuned for retireval tasks aimed at search & IR based usecases.
 We ran the retrieval slice of the cMTEB.
 
-We compared the performance few top general purpose embedding models on the C-MTEB benchmark. please refer to the C-MTEB leaderboard. Almost all models below are bert-chinese based so they have no notion of any other languages.
+We compared the performance few top general purpose embedding models on the C-MTEB benchmark. please refer to the C-MTEB leaderboard. Almost all models below are bert-Arabic based so they have no notion of any other languages.
 
 <center>
   <img src="./ar_metrics_3.png" width=150%/>