metadata

language: pt
license: mit
tags:
  - msmarco
  - t5
  - pytorch
  - tensorflow
  - pt
  - pt-br
datasets:
  - msmarco
widget:
  - text: Texto de exemplo em portuguÃªs
inference: false

mt5-base-multi-msmarco Reranker finetuned on Multi MS MARCO

Introduction

mT5-base is a mT5-based model finetuned on a multilingual translated version of MS MARCO passage dataset. This dataset, named Multi MS MARCO, is formed by 12 complete MS MARCO passages collection in 12 different languages. Further information about the dataset or the translation method can be found on our paper mMARCO: A Multilingual Version of MS MARCO Passage Ranking Dataset and mMARCO repository.

Usage


from transformers import T5Tokenizer, MT5ForConditionalGeneration

model_name = 'unicamp-dl/mt5-base-multi-msmarco'
tokenizer  = T5Tokenizer.from_pretrained(model_name)
model      = MT5ForConditionalGeneration.from_pretrained(model_name)

Citation

If you use ptt5-base-msmarco-pt-100k, please cite:

@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}

}