Update README.md

README.md

@@ -17,7 +17,7 @@ inference: false
 # multilingual-MiniLM-L6-v2-multi-msmarco Reranker finetuned on mMARCO
 ## Introduction
 multilingual-MiniLM-L6-v2-multi-msmarco is a multilingual miniLM-based model finetuned on a multilingual version of MS MARCO passage dataset. This dataset, named mMARCO, is formed by passages in 8 different languages, translated from English MS MARCO passages collection.
-Further information about the dataset or the translation method can be found on our [Cross-Lingual repository](https://github.com/unicamp-dl/cross-lingual-analysis).
+Further information about the dataset or the translation method can be found on our [**mMARCO: A Multilingual Version of MS MARCO Passage Ranking Dataset**](https://arxiv.org/abs/2108.13897) and [mMARCO](https://github.com/unicamp-dl/mMARCO) repository.
 ## Usage
 ```python
 from transformers import AutoTokenizer, AutoModel
@@ -30,10 +30,12 @@ model      = AutoModel.from_pretrained(model_name)
 # Citation
 If you use multilingual-MiniLM-L6-v2-multi-msmarco, please cite:
 
-    @article{rosa2021cost,
-      title={A cost-benefit analysis of cross-lingual transfer methods},
-      author={Rosa, Guilherme Moraes and Bonifacio, Luiz Henrique and de Souza, Leandro Rodrigues and Lotufo, Roberto and Nogueira, Rodrigo},
-      journal={arXiv preprint arXiv:2105.06813},
-      year={2021}
-    }
+    @misc{bonifacio2021mmarco,
+      title={mMARCO: A Multilingual Version of MS MARCO Passage Ranking Dataset}, 
+      author={Luiz Henrique Bonifacio and Israel Campiotti and Roberto Lotufo and Rodrigo Nogueira},
+      year={2021},
+      eprint={2108.13897},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}