{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/contrastive-learning-for-many-to-many","title":"Contrastive Learning for Many-to-many Multilingual Neural Machine Translation","arxiv_id":"2105.09501","date":"2021-05-20","proceeding":"ACL 2021 5","authors":["Xiao Pan","Mingxuan Wang","Liwei Wu","Lei LI"],"abstract":"Existing multilingual machine translation approaches mainly focus on English-centric directions, while the non-English directions still lag behind. In this work, we aim to build a many-to-many translation system with an emphasis on the quality of non-English language directions. Our intuition is based on the hypothesis that a universal cross-language representation leads to better multilingual translation performance. To this end, we propose mRASP2, a training method to obtain a single unified multilingual translation model. mRASP2 is empowered by two techniques: a) a contrastive learning scheme to close the gap among representations of different languages, and b) data augmentation on both multiple parallel and monolingual data to further align token representations. For English-centric directions, mRASP2 outperforms existing best unified model and achieves competitive or even better performance than the pre-trained and fine-tuned model mBART on tens of WMT's translation directions. For non-English directions, mRASP2 achieves an improvement of average 10+ BLEU compared with the multilingual Transformer baseline. Code, data and trained models are available at https://github.com/PANXiao1994/mRASP2.","url_abs":"https://arxiv.org/abs/2105.09501v3","url_pdf":"https://arxiv.org/pdf/2105.09501v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"contrastive-learning-for-many-to-many","repo_url":"https://github.com/PANXiao1994/mCOLT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"contrastive-learning-for-many-to-many","repo_url":"https://github.com/PANXiao1994/mRASP2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"contrastive-learning-for-many-to-many","repo_url":"https://github.com/linzehui/mRASP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"mbart","method_name":"mBART"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2105.09501","atlas_url":"https://app.syntology.ai/?focus=2105.09501","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}