{"id":34567923,"url":"https://github.com/unbabel/wmt21-qe-task","last_synced_at":"2025-12-24T09:12:10.940Z","repository":{"id":42430645,"uuid":"419743539","full_name":"Unbabel/wmt21-qe-task","owner":"Unbabel","description":"MBART Quality Estimator proposed in IST-Unbabel 2021 Submission for the Quality Estimation Shared Task","archived":false,"fork":false,"pushed_at":"2022-04-06T13:17:22.000Z","size":195,"stargazers_count":9,"open_issues_count":1,"forks_count":2,"subscribers_count":10,"default_branch":"main","last_synced_at":"2023-10-06T20:32:50.115Z","etag":null,"topics":["machine-translation","quality-estimation","uncertainty"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Unbabel.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-10-21T13:53:12.000Z","updated_at":"2022-09-09T20:39:28.000Z","dependencies_parsed_at":"2022-09-10T09:31:31.062Z","dependency_job_id":null,"html_url":"https://github.com/Unbabel/wmt21-qe-task","commit_stats":null,"previous_names":[],"tags_count":0,"template":null,"template_full_name":null,"purl":"pkg:github/Unbabel/wmt21-qe-task","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Unbabel%2Fwmt21-qe-task","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Unbabel%2Fwmt21-qe-task/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Unbabel%2Fwmt21-qe-task/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Unbabel%2Fwmt21-qe-task/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Unbabel","download_url":"https://codeload.github.com/Unbabel/wmt21-qe-task/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Unbabel%2Fwmt21-qe-task/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":27999517,"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":"2025-12-24T02:00:07.193Z","response_time":83,"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":["machine-translation","quality-estimation","uncertainty"],"created_at":"2025-12-24T09:12:10.680Z","updated_at":"2025-12-24T09:12:10.923Z","avatar_url":"https://github.com/Unbabel.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# WMT21 QE Shared Task\n\nCode for the MBART QE Estimator (M2) from [IST-Unbabel 2021 Submission for the Quality Estimation Shared Task](http://statmt.org/wmt21/pdf/2021.wmt-1.102.pdf)\n\n![nmt-model](images/m2-upd.png)\n\nFor XLMR Estimators (M1) please take a look at [OpenKiwi](https://github.com/Unbabel/OpenKiwi)\n\n## Citation:\n\n```\n@inproceedings{Zerva-etal-2021-ist,\n\ttitle        = {{IST-Unbabel 2021 Submission for the Quality Estimation Shared Task}},\n\tauthor       = {Zerva, Chrysoula  and van Stigt, Daan  and Rei, Ricardo  and C Farinha, Ana and Souza, José G. C. de and Glushkova, Taisiya and Vera, Miguel and Kepler, Fabio and Martins, André},\n\tyear         = 2021,\n\tmonth        = nov,\n\tbooktitle    = {Proceedings of the Sixth Conference on Machine Translation},\n\tpublisher    = {Association for Computational Linguistics},\n\taddress      = {Online},\n}\n```\n\n### Installation:\n\n```bash\npip install -r requirements.txt\npip install -e .\n```\n\n### Data:\nDownload the MLQE-PE with Glass-Box features:\n\n```bash\ncd data\nwget https://unbabel-experimental-data-sets.s3.eu-west-1.amazonaws.com/wmt21/glassbox-MLQE-PE.tar.gz\ntar -xf glassbox-MLQE-PE.tar.gz\n```\n\n**NOTE:**\nIf you use this data please cite the [original MLQE-PE corpus](https://github.com/sheffieldnlp/mlqe-pe)!\n\n### Training:\n\n```bash\npython cli.py train -f configs/mbart50-m2m.yaml\n```\n\n### Hyperparameter search_\n\n```bash\npython cli.py search -f configs/mbart50-m2m.yaml\n```\n\n### Testing:\n\n```bash\npython evaluate.py --checkpoint {path/to/checkpoint}.ckpt\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Funbabel%2Fwmt21-qe-task","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Funbabel%2Fwmt21-qe-task","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Funbabel%2Fwmt21-qe-task/lists"}