{"id":30181857,"url":"https://github.com/apertium/apertium-eval-translator","last_synced_at":"2025-08-12T09:14:24.631Z","repository":{"id":146363008,"uuid":"157837349","full_name":"apertium/apertium-eval-translator","owner":"apertium","description":"Evaluate machine translation output against reference: WER, PER, TER, BLEU","archived":false,"fork":false,"pushed_at":"2021-01-26T09:45:52.000Z","size":47,"stargazers_count":1,"open_issues_count":3,"forks_count":4,"subscribers_count":12,"default_branch":"master","last_synced_at":"2025-08-05T01:33:34.778Z","etag":null,"topics":["apertium","evaluation","mt"],"latest_commit_sha":null,"homepage":"http://wiki.apertium.org/wiki/Evaluation","language":"Perl","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/apertium.png","metadata":{"files":{"readme":"README","changelog":null,"contributing":null,"funding":null,"license":"COPYING","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2018-11-16T08:35:46.000Z","updated_at":"2021-01-26T09:45:55.000Z","dependencies_parsed_at":null,"dependency_job_id":"446a9d7a-b5b4-4fde-b986-c9600ff2ca87","html_url":"https://github.com/apertium/apertium-eval-translator","commit_stats":{"total_commits":27,"total_committers":9,"mean_commits":3.0,"dds":0.7777777777777778,"last_synced_commit":"3ae719575ef306b299281a525fdc30f94f9e66a8"},"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/apertium/apertium-eval-translator","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/apertium%2Fapertium-eval-translator","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/apertium%2Fapertium-eval-translator/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/apertium%2Fapertium-eval-translator/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/apertium%2Fapertium-eval-translator/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/apertium","download_url":"https://codeload.github.com/apertium/apertium-eval-translator/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/apertium%2Fapertium-eval-translator/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":269583148,"owners_count":24442103,"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":"2025-08-09T02:00:10.424Z","response_time":111,"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":["apertium","evaluation","mt"],"created_at":"2025-08-12T09:14:20.895Z","updated_at":"2025-08-12T09:14:24.620Z","avatar_url":"https://github.com/apertium.png","language":"Perl","funding_links":[],"categories":[],"sub_categories":[],"readme":"apertium-eval-translator.pl\n-------------------------------------------------------------------\n\nSimple Perl script to evaluate Apertium-based machine translation\nsystems.\n\nThis software calculates (at document level) the word error rate (WER)\nand the position-independent word error rate (PER) between a\ntranslation performed by the Apertium MT system and a reference\ntranslation obtained by post-editing the system output.\n\nFor more information execute the script (after installation)\nwithout arguments\n\n$ apertium-eval-translator\n\napertium-eval-translator-line.pl\n-------------------------------------------------------------------\nSimilar to apertium-eval-translator but it assumes that test and reference\nfiles has the same number of sentences and are in the one-sentence-per-line format\n\nbootstrap_resampling.pl\n-------------------------------------------------------------------\nComputes confidence intervals for MT evaluation. See paper\nhttp://acl.ldc.upenn.edu/acl2004/emnlp/pdf/Koehn.pdf\n\nScripts wer.sh, ter.sh and bleu.sh ares provided as examples of\nthe script that needs to be supplied to\nbootstrap_resampling.pl to evaluate MT performance.\nNote: ter.sh and bleu.sh need software not distributed in this package.\n\n-------------------------------------------------------------------\n\nSuggestions are very welcome. Please write to Felipe Sánchez Martínez\nat fsanchez@dlsi.ua.es .\n\n===================================================================\n===================================================================\n\napertium-eval\n-------------------------------------------------------------------\nThis is not intended to be a substitute for Felipe Sanchez's\napertium-eval-translator. It just provides an alternative way\nto approximate the word error rate by processing the output of \"diff -d\".\nRun apertium-eval without arguments for a usage message.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fapertium%2Fapertium-eval-translator","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fapertium%2Fapertium-eval-translator","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fapertium%2Fapertium-eval-translator/lists"}