{"id":20246642,"url":"https://github.com/civicdatalab/samoses","last_synced_at":"2026-03-07T17:01:14.990Z","repository":{"id":98523345,"uuid":"200446356","full_name":"CivicDataLab/Samoses","owner":"CivicDataLab","description":"wrapper for Moses","archived":false,"fork":false,"pushed_at":"2019-10-25T05:12:41.000Z","size":350,"stargazers_count":0,"open_issues_count":4,"forks_count":0,"subscribers_count":6,"default_branch":"master","last_synced_at":"2025-01-14T02:11:52.806Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"HTML","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/CivicDataLab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","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":"2019-08-04T03:46:48.000Z","updated_at":"2019-10-25T05:12:43.000Z","dependencies_parsed_at":"2023-04-18T11:58:24.173Z","dependency_job_id":null,"html_url":"https://github.com/CivicDataLab/Samoses","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/CivicDataLab%2FSamoses","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CivicDataLab%2FSamoses/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CivicDataLab%2FSamoses/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CivicDataLab%2FSamoses/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CivicDataLab","download_url":"https://codeload.github.com/CivicDataLab/Samoses/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":241692621,"owners_count":20004262,"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":"2024-11-14T09:31:35.461Z","updated_at":"2026-03-07T17:01:09.901Z","avatar_url":"https://github.com/CivicDataLab.png","language":"HTML","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Samoses\n[![License: MIT](https://img.shields.io/badge/License-MIT-lightgrey.svg)](https://github.com/CivicDataLab/Samoses/blob/master/LICENSE)\n\nWrapper for Moses\n\n\n## Setup\n\n### Installation of Moses\n\nClone the Moses repository [here](https://github.com/moses-smt/mosesdecoder.git)\n\nFollow the instructions [here](http://www.statmt.org/moses/?n=Development.GetStarted) to install Moses\n\n## DATASET\n\nFind the nyu corpus for English-Hindi [here](https://drive.google.com/drive/u/2/folders/16Yjgq_osF2j-Ws0vWBp2i59kA094nFWP)\n\n## Pipeline Creation Language (PCL)\n\nPCL is a Domain Specific Language to construct non-recurrent software pipelines.\nWe are using PCL to build pipeline for the Statistical Machine Translation.\n\n\n## RUN\n\n```\nsudo nice experiment.perl -config config_nyu -exec\n```\n\nThe phrase table generated is `phrase-table.1.gz` and not `phrase-table.1`. Convert the phrase table to the compact format using:\n\n```\nsudo nice $WORKSPACE/mosesdecoder/bin/processPhraseTableMin -in $WORKSPACE/experiment/model/phrase-table.1.gz -nscores 4 -out $WORKSPACE/experiment/model/phrase-table\n```\n\nSimilarly convert the reodering table:\n\n```\nsudo nice $WORKSPACE/mosesdecoder/bin/processLexicalTableMin -in $WORKSPACE/experiment/model/reordering-table.1.wbe-msd-bidirectional-fe.gz -out $WORKSPACE/experiment/model/reordering-table\n```\n\nModify `moses.tuned.ini.1` under `tuning` directory with:\n\n```\n# PhraseDictionaryMemory name=TranslationModel0 num-features=4 path=/home/ubuntu/mosesdecoder/experiment/model/phrase-table.1 input-factor=0 output-factor=0\n\nPhraseDictionaryCompact name=TranslationModel0 num-features=4 path=/home/ubuntu/mosesdecoder/experiment/model/phrase-table.minphr input-factor=0 output-factor=0\n\n#LexicalReordering name=LexicalReordering0 num-features=6 type=wbe-msd-bidirectional-fe-allff input-factor=0 output-factor=0 path=/home/ubuntu/mosesdecoder/experiment/model/reordering-table.1.wbe-msd-bidirectional-fe.gz\n\nLexicalReordering name=LexicalReordering0 num-features=6 type=wbe-msd-bidirectional-fe-allff input-factor=0 output-factor=0 path=/home/ubuntu/mosesdecoder/experiment/model/reordering-table\n```\n\n### Translate\n\n```\n$WORKSPACE/mosesdecoder/bin/moses -f $WORKSPACE/experiment/tuning/moses.tuned.ini.1\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcivicdatalab%2Fsamoses","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcivicdatalab%2Fsamoses","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcivicdatalab%2Fsamoses/lists"}