{"id":29795461,"url":"https://github.com/ubisoft/ubisoft-laforge-binaryalignwordalignementasbinarysequencelabeling","last_synced_at":"2025-07-28T04:11:05.019Z","repository":{"id":252956093,"uuid":"807258215","full_name":"ubisoft/ubisoft-laforge-BinaryAlignWordAlignementasBinarySequenceLabeling","owner":"ubisoft","description":"repo on the BinaryAlign: Word Alignment as Binary Sequence Labeling","archived":false,"fork":false,"pushed_at":"2024-08-08T19:07:11.000Z","size":23,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-08-13T17:06:32.175Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ubisoft.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"license.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-05-28T18:53:37.000Z","updated_at":"2024-08-13T17:06:38.276Z","dependencies_parsed_at":"2024-08-13T17:20:00.408Z","dependency_job_id":null,"html_url":"https://github.com/ubisoft/ubisoft-laforge-BinaryAlignWordAlignementasBinarySequenceLabeling","commit_stats":null,"previous_names":["ubisoft/ubisoft-laforge-binaryalignwordalignementasbinarysequencelabeling"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ubisoft/ubisoft-laforge-BinaryAlignWordAlignementasBinarySequenceLabeling","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ubisoft%2Fubisoft-laforge-BinaryAlignWordAlignementasBinarySequenceLabeling","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ubisoft%2Fubisoft-laforge-BinaryAlignWordAlignementasBinarySequenceLabeling/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ubisoft%2Fubisoft-laforge-BinaryAlignWordAlignementasBinarySequenceLabeling/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ubisoft%2Fubisoft-laforge-BinaryAlignWordAlignementasBinarySequenceLabeling/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ubisoft","download_url":"https://codeload.github.com/ubisoft/ubisoft-laforge-BinaryAlignWordAlignementasBinarySequenceLabeling/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ubisoft%2Fubisoft-laforge-BinaryAlignWordAlignementasBinarySequenceLabeling/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":267459928,"owners_count":24090782,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-07-28T02:00:09.689Z","response_time":68,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-07-28T04:11:04.255Z","updated_at":"2025-07-28T04:11:05.005Z","avatar_url":"https://github.com/ubisoft.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"© [2024] Ubisoft Entertainment. All Rights Reserved\n# BinaryAlign: Word Alignment as Binary Sequence Labeling\n\n## Introduction\n**BinaryAlign** reformulates word alignment as a set of binary sequence labeling tasks. It outperforms existing approaches in both high and low-resource language settings, providing a unified approach to word alignment. This repository contains the code and models for BinaryAlign as described in [our paper](https://arxiv.org/pdf/2407.12881) accepted to the main conference of ACL 2024.\n\n## Datasets\n\n### Format\n\n* source (.src)\n```\nHe has a sofa .\n```\n\n* target (.tgt)\n```\nIl a un canapé .\n```\n\n* gold alignment (.talp)\n```\n1-1 2-2 3-3 4-4 5-5 \n```\n\n### Data\n\nWe used the same datasets as https://github.com/sufenlp/AccAlign.\n\n## Training\n\n```shell\nbash train.sh\n```\n\n## Evaluation\n\n```shell\nbash eval.sh\n```\n\n## Checkpoints\n\n| Training Languages |Link |\n| ------------- | ------------- |\n| Align6 |  models/align6 |\n| deen |   models/deen |\n| roen |   models/roen |\n| fren |   models/fren |\n| zhen |   models/zhen |\n| jaen |   models/jaen |\n\n## Citation\n\n```\n@article{latouche2024binaryalign,\n  title={BinaryAlign: Word Alignment as Binary Sequence Labeling},\n  author={Latouche, Gaetan Lopez and Carbonneau, Marc-Andr{\\'e} and Swanson, Ben},\n  journal={arXiv preprint arXiv:2407.12881},\n  year={2024}\n}\n```\n\n\n\n## License\n\nSee Licence File - CC4.0 non commercial\n\n© [2024] Ubisoft Entertainment. All Rights Reserved\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fubisoft%2Fubisoft-laforge-binaryalignwordalignementasbinarysequencelabeling","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fubisoft%2Fubisoft-laforge-binaryalignwordalignementasbinarysequencelabeling","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fubisoft%2Fubisoft-laforge-binaryalignwordalignementasbinarysequencelabeling/lists"}