{"id":17959919,"url":"https://github.com/dargones/sentence_alignment_tools","last_synced_at":"2025-10-11T06:33:13.401Z","repository":{"id":104892426,"uuid":"136245262","full_name":"Dargones/sentence_alignment_tools","owner":"Dargones","description":"A collection of tools for sentence alignement","archived":false,"fork":false,"pushed_at":"2019-01-18T14:54:13.000Z","size":108,"stargazers_count":6,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-05T01:51:12.324Z","etag":null,"topics":["alignment","complex-word-identification","cwi","newsela","nlp","text-simplification"],"latest_commit_sha":null,"homepage":"","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/Dargones.png","metadata":{"files":{"readme":"README.md","changelog":"newselautil.py","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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2018-06-05T23:20:10.000Z","updated_at":"2022-11-23T16:04:56.000Z","dependencies_parsed_at":null,"dependency_job_id":"c4c35fd5-6c1c-44ed-abc7-e638573a6a5c","html_url":"https://github.com/Dargones/sentence_alignment_tools","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Dargones/sentence_alignment_tools","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Dargones%2Fsentence_alignment_tools","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Dargones%2Fsentence_alignment_tools/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Dargones%2Fsentence_alignment_tools/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Dargones%2Fsentence_alignment_tools/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Dargones","download_url":"https://codeload.github.com/Dargones/sentence_alignment_tools/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Dargones%2Fsentence_alignment_tools/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279006453,"owners_count":26084108,"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":"2025-10-11T02:00:06.511Z","response_time":55,"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":["alignment","complex-word-identification","cwi","newsela","nlp","text-simplification"],"created_at":"2024-10-29T11:04:46.449Z","updated_at":"2025-10-11T06:33:13.394Z","avatar_url":"https://github.com/Dargones.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Sentence Alignment Tools\n\nThis repository contains the code that can be used to align sentences accross articles adopted to different readability levels.\nThe current code is designed to be used specifically with the [Newsela Data](https://newsela.com/data/). The code is an implementation of a modified version of the algorithm described by [Paetzold and Specia](https://arxiv.org/pdf/1612.04113.pdf) can be used to obtain datasets for CWI (Complex Word Identification) tasks. Please, note that the \nnewer version of this code is now a part of [another repository](https://github.com/seanderson/lexical-simplification/tree/master/src).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdargones%2Fsentence_alignment_tools","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdargones%2Fsentence_alignment_tools","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdargones%2Fsentence_alignment_tools/lists"}