m2m100 fine-tuned on the ca_zh_wikipedia dataset for machine translation

Table of Contents

<details> <summary>Click to expand</summary>

</details>

Model description

This model was obtained by fine-tuning the m2m100_418M model on a Ca-Zh machine translation task with the ca_zh_wikipedia dataset that has been created along with the model. We also evaluate it on a general-domain multilingual testset Flores-101.

Intended uses and limitations

You can use this model for machine translation from Catalan to Chinese.

How to use

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("projecte-aina/m2m100_418M_ft_zh_ca")

model = AutoModelForSeq2SeqLM.from_pretrained("projecte-aina/m2m100_418M_ft_zh_ca")

Training

Training data

As a data for fine-tuning we used the ca_zh_wikipedia dataset extracted from Wikipedia.

Training procedure

Tokenization

The original m2m100_418M model's sentencepiece tokenizer was used. The fine-tuning dataset that contained both simplified and traditional Chinese was reduced to its simplified form.

Hyperparameters

The model was trained for 15 epochs with the default parameters and \(LR = 2\mathrm{e}{-5}\).

Evaluation

Variable and metrics

We use the BLEU score for evaluation on test sets: Flores-101.

Evaluation results

Below are the evaluation results on the machine translation from Catalan to Chinese compared with the original m2m100 on a testset: Flores-101.

Test set Model BLEU
Flores-101 m2m100 24.6
m2m100_418M_ft_ca_zh 24.9

Additional information

Licensing Information

Apache License, Version 2.0

Funding

This work was funded by the [Departament de la Vicepresidència i de Polítiques Digitals i Territori de la Generalitat de Catalunya](https://politiquesdigitals.gencat.cat/ca/inici/index.html#googtrans(ca|en) within the framework of Projecte AINA.

Citation Information

@mastersthesis{MasterThesisZixuanLiu,
  author  = "Zixuan Liu",
  title   = "Improving Chinese-Catalan Machine Translation with Wikipedia Parallel",
  school  = "Universitat Pompeu Fabra",
  year    = 2022,
  address = "Barcelona",
  url= "https://repositori.upf.edu/handle/10230/54142"
}

@mastersthesis{MasterThesisChenuyeZhou,
  author  = "Chenuye Zhou",
  title   = "Building a Catalan-Chinese parallel corpus for use in MT",
  school  = "Universitat Pompeu Fabra",
  year    = 2022,
  address = "Barcelona",
  url = "https://repositori.upf.edu/handle/10230/54140"
}

Disclaimer

<details> <summary>Click to expand</summary>

The models published in this repository are intended for a generalist purpose and are available to third parties. These models may have bias and/or any other undesirable distortions.

When third parties, deploy or provide systems and/or services to other parties using any of these models (or using systems based on these models) or become users of the models, they should note that it is their responsibility to mitigate the risks arising from their use and, in any event, to comply with applicable regulations, including regulations regarding the use of Artificial Intelligence.

In no event shall the owner and creator of the models (BSC – Barcelona Supercomputing Center) be liable for any results arising from the use made by third parties of these models.

</details>