代码拉取完成,页面将自动刷新
https://arxiv.org/pdf/2006.09526.pdf
CRISS is a multilingual sequence-to-sequnce pretraining method where mining and training processes are applied iteratively, improving cross-lingual alignment and translation ability at the same time.
cd examples/criss
wget https://dl.fbaipublicfiles.com/criss/criss_3rd_checkpoints.tar.gz
tar -xf criss_checkpoints.tar.gz
Make sure to run all scripts from examples/criss directory
bash download_and_preprocess_flores_test.sh
bash unsupervised_mt/eval.sh
bash download_and_preprocess_tatoeba.sh
bash sentence_retrieval/sentence_retrieval_tatoeba.sh
Follow instructions on https://github.com/facebookresearch/faiss/blob/master/INSTALL.md
bash mining/mine_example.sh
@article{tran2020cross,
title={Cross-lingual retrieval for iterative self-supervised training},
author={Tran, Chau and Tang, Yuqing and Li, Xian and Gu, Jiatao},
journal={arXiv preprint arXiv:2006.09526},
year={2020}
}
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。