{"payload":{"pageCount":1,"repositories":[{"type":"Public","name":"giawarc","owner":"paracrawl","isFork":false,"description":"Processing utilities for Internet Archive","allTopics":[],"primaryLanguage":{"name":"C++","color":"#f34b7d"},"pullRequestCount":1,"issueCount":4,"starsCount":1,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-19T12:45:13.572Z"}},{"type":"Public","name":"corset","owner":"paracrawl","isFork":false,"description":"Corset is a web-based data selection portal that helps you getting relevant data from massive amounts of parallel data.","allTopics":[],"primaryLanguage":{"name":"SCSS","color":"#c6538c"},"pullRequestCount":0,"issueCount":1,"starsCount":17,"forksCount":4,"license":"GNU General Public License v3.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-11-06T11:57:34.601Z"}},{"type":"Public","name":"keops","owner":"paracrawl","isFork":false,"description":"Tool for manual evaluation of parallel sentences.","allTopics":[],"primaryLanguage":{"name":"PHP","color":"#4F5D95"},"pullRequestCount":0,"issueCount":0,"starsCount":12,"forksCount":4,"license":"GNU General Public License v3.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-10-19T06:07:21.034Z"}},{"type":"Public","name":"cirrus-scripts","owner":"paracrawl","isFork":false,"description":"Scripts for running bitextor/paracrawl/europat jobs on cirrus.ac.uk","allTopics":[],"primaryLanguage":{"name":"Shell","color":"#89e051"},"pullRequestCount":1,"issueCount":8,"starsCount":7,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-07-18T11:01:58.170Z"}},{"type":"Public","name":"giashard","owner":"paracrawl","isFork":false,"description":"Sharding program for Paracrawl","allTopics":[],"primaryLanguage":{"name":"Go","color":"#00ADD8"},"pullRequestCount":0,"issueCount":1,"starsCount":1,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-05-10T13:54:19.950Z"}},{"type":"Public","name":"europat-scripts","owner":"paracrawl","isFork":false,"description":"Scripts for obtaining patent data","allTopics":[],"primaryLanguage":{"name":"Java","color":"#b07219"},"pullRequestCount":1,"issueCount":1,"starsCount":4,"forksCount":2,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-04-14T17:57:00.069Z"}},{"type":"Public","name":"tmxutil","owner":"paracrawl","isFork":false,"description":"Tools to generate & filter Europat tmx files.","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":3,"forksCount":1,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-01-17T15:46:28.550Z"}},{"type":"Public","name":"synthesis","owner":"paracrawl","isFork":false,"description":"Data synthesis by contextualizing glossary translations","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":5,"forksCount":3,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2021-07-01T07:57:02.031Z"}},{"type":"Public","name":"opus-train","owner":"paracrawl","isFork":false,"description":"Automate download and training with OPUS corpora","allTopics":[],"primaryLanguage":{"name":"Shell","color":"#89e051"},"pullRequestCount":0,"issueCount":0,"starsCount":2,"forksCount":2,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2021-01-28T11:51:01.958Z"}},{"type":"Public","name":"human-evaluations","owner":"paracrawl","isFork":false,"description":"Results of the human evaluation","allTopics":[],"primaryLanguage":{"name":"Rich Text Format","color":"#ccc"},"pullRequestCount":0,"issueCount":0,"starsCount":5,"forksCount":3,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-12-09T15:45:24.739Z"}},{"type":"Public","name":"corpus-issues","owner":"paracrawl","isFork":false,"description":"Open here any Paracrawl corpus related issue","allTopics":[],"primaryLanguage":null,"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-11-18T10:28:20.271Z"}},{"type":"Public","name":"multilingual-ted","owner":"paracrawl","isFork":false,"description":"","allTopics":[],"primaryLanguage":null,"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":"Creative Commons Zero v1.0 Universal","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-11-13T17:01:47.714Z"}},{"type":"Public archive","name":"b64filter","owner":"paracrawl","isFork":false,"description":"Program for operating on one document per Base 64 encoded line files","allTopics":[],"primaryLanguage":{"name":"Go","color":"#00ADD8"},"pullRequestCount":0,"issueCount":1,"starsCount":1,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-08-04T19:31:41.421Z"}},{"type":"Public","name":"Domain_Adaptation","owner":"paracrawl","isFork":false,"description":"InDomain detection is a tool designed to extract in-domain data from a large collections of data.","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":1,"forksCount":1,"license":"GNU General Public License v3.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-06-05T20:24:16.552Z"}},{"type":"Public","name":"url_language_analysis","owner":"paracrawl","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-03-06T16:14:16.056Z"}},{"type":"Public","name":"targeted-crawling","owner":"paracrawl","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-03-06T16:10:20.561Z"}},{"type":"Public","name":"go-warc","owner":"paracrawl","isFork":true,"description":"A golang library to work with WARC files from the common crawl","allTopics":[],"primaryLanguage":{"name":"Go","color":"#00ADD8"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":7,"license":"GNU General Public License v2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2019-08-04T15:56:01.776Z"}},{"type":"Public","name":"extractor","owner":"paracrawl","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"C++","color":"#f34b7d"},"pullRequestCount":0,"issueCount":1,"starsCount":23,"forksCount":4,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2017-11-29T13:57:10.779Z"}},{"type":"Public","name":"embedding","owner":"paracrawl","isFork":false,"description":"Mine parallel corpora with embeddings","allTopics":[],"primaryLanguage":{"name":"Perl","color":"#0298c3"},"pullRequestCount":0,"issueCount":0,"starsCount":4,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2017-09-02T10:56:30.653Z"}},{"type":"Public","name":"DataCollection","owner":"paracrawl","isFork":true,"description":"Data collection, alignment and TAUS repository","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":3,"starsCount":8,"forksCount":8,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2017-08-01T13:17:38.000Z"}}],"repositoryCount":20,"userInfo":null,"searchable":true,"definitions":[],"typeFilters":[{"id":"all","text":"All"},{"id":"public","text":"Public"},{"id":"source","text":"Sources"},{"id":"fork","text":"Forks"},{"id":"archived","text":"Archived"},{"id":"template","text":"Templates"}],"compactMode":false},"title":"Repositories"}