README.md

metadata

language: pt
license: mit
tags:
  - msmarco
  - miniLM
  - pytorch
  - tensorflow
  - pt
  - pt-br
datasets:
  - msmarco
widget:
  - text: Texto de exemplo em português
inference: false

multilingual-MiniLM-L6-v2-en-pt-msmarco Reranker finetuned on mMARCO

Introduction

multilingual-MiniLM-L6-v2-en-pt-msmarco is a multilingual miniLM-based model finetuned on a bilingual version of MS MARCO passage dataset. This bilingual dataset version is formed by the original MS MARCO dataset (in English) and a Portuguese translated version. Further information about the dataset or the translation method can be found on our Cross-Lingual repository.

Usage

from transformers import AutoTokenizer, AutoModel

model_name = 'unicamp-dl/multilingual-MiniLM-L6-v2-en-pt-msmarco'
tokenizer  = AutoTokenizer.from_pretrained(model_name)
model      = AutoModel.from_pretrained(model_name)

Citation

If you use mt5-base-en-pt-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}
}