{"id":17031393,"url":"https://github.com/breandan/cubit","last_synced_at":"2025-03-22T20:44:25.491Z","repository":{"id":233856503,"uuid":"787927909","full_name":"breandan/cubit","owner":"breandan","description":"Rescued from https://web.archive.org/web/20150918204917/http://www.cis.upenn.edu/~lhuang3/cubit/cubit-v0.8.tgz","archived":false,"fork":false,"pushed_at":"2024-05-15T02:08:22.000Z","size":500,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-28T00:42:02.689Z","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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/breandan.png","metadata":{"files":{"readme":"README","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2024-04-17T12:58:39.000Z","updated_at":"2024-05-15T02:08:26.000Z","dependencies_parsed_at":"2024-04-17T14:03:11.191Z","dependency_job_id":"2fd3799e-bbd7-4ff7-bf38-555f895f2ffa","html_url":"https://github.com/breandan/cubit","commit_stats":null,"previous_names":["breandan/cubit"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/breandan%2Fcubit","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/breandan%2Fcubit/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/breandan%2Fcubit/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/breandan%2Fcubit/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/breandan","download_url":"https://codeload.github.com/breandan/cubit/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245020314,"owners_count":20548156,"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":"2024-10-14T08:23:59.220Z","updated_at":"2025-03-22T20:44:25.460Z","avatar_url":"https://github.com/breandan.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"this is an unofficial release of Cubit -- USE AT YOUR OWN RISK!\n-----------------------------------------------------------------------------\n\nCubit -- A Cube Pruning Decoder of Phrase-based Translation\n\ndescribed in Section 5.1 of:\n\nLiang Huang and David Huang (2007). \nForest Rescoring: Faster Decoding with Integrated Language Models.\nIn Proceedings of ACL, Prague, Czech Rep.\n\nThe related research was conducted at the University of Pennsylvania (Philadelphia, PA)\nand the Information Sciences Institute, University of Southern California (Marina del Rey, CA).\n\nAuthor: Liang Huang (lhuang3@cis.upenn.edu)\n\nIf you used or referred to this software for the implementation of cube pruning I request your citing of the above paper.\n\n-----------------------------------------------------------------------------\n\nTo run Cubit you need the following packages:\n\n1. Python \u003e= 2.5\n2. SRILM, a C++ toolkit of language modeling.\n3. psrilm, a python port of SRILM by David Chiang (chiang@isi.edu)\n\nand a Pharaoh-style phrase-table.\n\n-----------------------------------------------------------------------------\n\nMain file: cubit.py\n\ndecoder.py:\n\timplements various decoding algorithms, which include:\n\t\t1) a faithful clone of Pharaoh-style forward update beam-search with per-bin threshold beams. \n\t\t\tin function forward_search(lattice) \n\n\t\t2) the backward-star version of 1), which provides the backbone of cube pruning.\n\t\t\tin function backward_search(lattice)\n\n\t\t3) (online version) of cube pruning. the core implementation has only 20 lines of code.\n\t\t\tin function online_cube(lattice)\n\n\tThe code for the above three decoders are short and meant to be easily accessible.\n\n\tthe search(lattice, ff=None) is the function which calls one of the above decoders. \n\t\tff is the \"forced-decoding\" option [for advanced debugging].\n\n\talso provides an important datastructure, class Bin, which is the collection of hypotheses \n\t\tcovering a same number of (translated) foreign words. Field \"id\" is the bin id, \n\t\te.g. bin #5 includes all hypotheses with 5 words translated. \n\t\tThere is some histogram and threshold pruning built-in (both borrowed from Pharaoh).\n\n\t\n----------------------------------------------------------------------\n\nquestions/comments: email me at lhuang3@cis.upenn.edu.\n\nThanks for your interest.\n\n----------------------------------------------------------------------\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbreandan%2Fcubit","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbreandan%2Fcubit","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbreandan%2Fcubit/lists"}