Repository files navigation

This the repository for thispaper.

Find extensions of this work and new pre-trained models here:code,paper

Install OpenNMT-py (1.0) and subword-nmt.

pip install OpenNMT-pypip install subword-nmt

We release JASS models on 2 language pairs: ja+en, ja+ru. For Japanese seq2seq pretraining, we use our proposed JASS methods while MASS is utilized for English and Russian.

Run the bpe precrocessing for the dataset to be finetuned. After setting up the downloaded vocabulary for src and tgt sentences during the preprocessing phase bypreprocess.py of OpenNMT, usetrain_from argument oftrain.py in OpenNMT to implement the finetuning for the pretrained model.

We will update the current Japanese--English pre-trained model and release pretrained models on Japanese--Chinese and Japanese--Korean. We released new models here:code

[1] Zhuoyuan Mao, Fabien Cromieres, Raj Dabre, Haiyue Song, Sadao Kurohashi,JASS: Japanese-specific Sequence to Sequence Pre-training for Neural Machine Translation

@inproceedings{mao-etal-2020-jass,    title = "{JASS}: {J}apanese-specific Sequence to Sequence Pre-training for Neural Machine Translation",    author = "Mao, Zhuoyuan  and      Cromieres, Fabien  and      Dabre, Raj  and      Song, Haiyue  and      Kurohashi, Sadao",    booktitle = "Proceedings of The 12th Language Resources and Evaluation Conference",    month = may,    year = "2020",    address = "Marseille, France",    publisher = "European Language Resources Association",    url = "https://www.aclweb.org/anthology/2020.lrec-1.454",    pages = "3683--3691",    language = "English",    ISBN = "979-10-95546-34-4",}