{"id":18541841,"url":"https://github.com/cltk/latin_proper_names_cltk","last_synced_at":"2025-04-09T18:31:15.316Z","repository":{"id":22710126,"uuid":"26054298","full_name":"cltk/latin_proper_names_cltk","owner":"cltk","description":"A list of ~40K Classical Latin proper names","archived":false,"fork":false,"pushed_at":"2015-09-27T05:24:24.000Z","size":528,"stargazers_count":8,"open_issues_count":0,"forks_count":6,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-03-24T10:12:40.473Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/cltk.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":"2014-11-01T15:27:36.000Z","updated_at":"2024-09-26T12:44:34.000Z","dependencies_parsed_at":"2022-09-12T18:51:44.465Z","dependency_job_id":null,"html_url":"https://github.com/cltk/latin_proper_names_cltk","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cltk%2Flatin_proper_names_cltk","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cltk%2Flatin_proper_names_cltk/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cltk%2Flatin_proper_names_cltk/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cltk%2Flatin_proper_names_cltk/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/cltk","download_url":"https://codeload.github.com/cltk/latin_proper_names_cltk/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248087703,"owners_count":21045570,"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","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":"2024-11-06T20:06:28.665Z","updated_at":"2025-04-09T18:31:13.549Z","avatar_url":"https://github.com/cltk.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# About\nThe file `proper_names.txt` contains a newline-delimited file which contains all of the words in the PHI5 which are likely proper names (persons, places, etc.). The value of this list is that, since everything is a noun, it may be used as a default POS tagger for these unusual words. \n\n`build_proper_names_list.py` shows how this file was made. `proper_names.txt` contains 40,683 unique, alphabetized words.\n\n# Important notes:\n\n* This list contains some words that are not proper nouns, and is currently being hand-checked to remove these.  It is currently hand-checked to EOF.\n* Some processing artifacts remain in the text, esp forms w/ a trailing _ (underscore) character. These will be removed later via automatic processing.\n* Similarly, there are a number of doublets as a result of a lexeme + underscore + additional lexeme; e.g., 'Alexandro' vs 'Alexandro_erat'.\n* A certain number of forms with attached clitics (e.g., -que, -ve) are present in the corpus; the host lexemes of these clitics are often doublets of non-cliticized lexemes.\n* A number of apparent abbreviations have been left intact; e.g., 'Achil'.\n* There is a certain amount of orthographic doubling as the result of u/v or i/j spellings; e.g., 'Achivis' vs. 'Achiuis', or '-que' vs '-qve'.  Similarly, in Greek words there are a number of doublets from variant y/u spellings; e.g., 'Amphitruone' vs. 'Amphitryone'.\n* Roman numeral notation has also been removed.\n\n\n# License\nCopyright (c) 2014 Kyle P. Johnson, under the MIT License. See 'LICENSE' for details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcltk%2Flatin_proper_names_cltk","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcltk%2Flatin_proper_names_cltk","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcltk%2Flatin_proper_names_cltk/lists"}