{"payload":{"pageCount":2,"repositories":[{"type":"Public","name":"ucto","owner":"LanguageMachines","isFork":false,"description":"Unicode tokeniser. Ucto tokenizes text files: it separates words from punctuation, and splits sentences. It offers several other basic preprocessing steps such as changing case that you can all use to make your text suited for further processing such as indexing, part-of-speech tagging, or machine translation. Ucto comes with tokenisation rules …","topicNames":["nlp","computational-linguistics","folia","language","natural-language-processing","punctuation","tokeniser"],"topicsNotShown":0,"primaryLanguage":{"name":"C++","color":"#f34b7d"},"pullRequestCount":0,"issueCount":12,"starsCount":62,"forksCount":13,"license":"GNU General Public License v3.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-14T11:51:56.214Z"}},{"type":"Public","name":"libfolia","owner":"LanguageMachines","isFork":false,"description":"FoLiA library for C++","topicNames":["nlp","natural-language-processing","library","folia"],"topicsNotShown":0,"primaryLanguage":{"name":"C++","color":"#f34b7d"},"pullRequestCount":0,"issueCount":5,"starsCount":14,"forksCount":7,"license":"GNU General Public License v3.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-14T10:15:20.077Z"}},{"type":"Public","name":"foliatest","owner":"LanguageMachines","isFork":false,"description":"Test suite for libfolia","topicNames":["cpp","folia","linguistic-analysis"],"topicsNotShown":0,"primaryLanguage":{"name":"C++","color":"#f34b7d"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":1,"license":"GNU General Public License v3.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-14T10:00:08.425Z"}},{"type":"Public","name":"timbltests","owner":"LanguageMachines","isFork":false,"description":"Unit tests for Timbl","topicNames":[],"topicsNotShown":0,"primaryLanguage":{"name":"Euphoria","color":"#FF790B"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-13T11:10:24.109Z"}},{"type":"Public","name":"foliautils","owner":"LanguageMachines","isFork":false,"description":"Command-line utilities for working with the Format for Linguistic Annotation (FoLiA), powered by libfolia (C++), written by Ko van der Sloot (CLST, Radboud University)","topicNames":["nlp","computational-linguistics","folia"],"topicsNotShown":0,"primaryLanguage":{"name":"C++","color":"#f34b7d"},"pullRequestCount":0,"issueCount":12,"starsCount":4,"forksCount":3,"license":"GNU General Public License v3.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-13T11:09:16.127Z"}},{"type":"Public","name":"frog","owner":"LanguageMachines","isFork":false,"description":"Frog is an integration of memory-based natural language processing (NLP) modules developed for Dutch. All NLP modules are based on Timbl, the Tilburg memory-based learning software package.","topicNames":["syntax","morphology","named-entity-recognition","computational-linguistics","text-processing","dependency-parser","pos-tagger","folia","lemmatiser","morphological-analyser"],"topicsNotShown":3,"primaryLanguage":{"name":"C++","color":"#f34b7d"},"pullRequestCount":0,"issueCount":13,"starsCount":73,"forksCount":11,"license":"GNU General Public License v3.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-12T10:29:35.023Z"}},{"type":"Public","name":"timbl","owner":"LanguageMachines","isFork":false,"description":" TiMBL implements several memory-based learning algorithms.","topicNames":["c-plus-plus","machine-learning","learning-algorithm","knn","ib1","igtree","k-nearest-neighbours","nearest-neighbours","classification","decision-tree"],"topicsNotShown":3,"primaryLanguage":{"name":"C++","color":"#f34b7d"},"pullRequestCount":0,"issueCount":1,"starsCount":46,"forksCount":9,"license":"GNU General Public License v3.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-07T15:18:44.373Z"}},{"type":"Public","name":"timblserver","owner":"LanguageMachines","isFork":false,"description":" TiMBL implements several memory-based learning algorithms. This is the server part.","topicNames":[],"topicsNotShown":0,"primaryLanguage":{"name":"C++","color":"#f34b7d"},"pullRequestCount":0,"issueCount":0,"starsCount":3,"forksCount":0,"license":"GNU General Public License v3.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-07T14:30:22.679Z"}},{"type":"Public","name":"ticcltools","owner":"LanguageMachines","isFork":false,"description":"Tools for TICCL","topicNames":[],"topicsNotShown":0,"primaryLanguage":{"name":"C++","color":"#f34b7d"},"pullRequestCount":0,"issueCount":17,"starsCount":13,"forksCount":3,"license":"GNU General Public License v3.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-03T13:30:03.778Z"}},{"type":"Public","name":"ticcutils","owner":"LanguageMachines","isFork":false,"description":"Ticcutils, a generic utility library shared by our software.","topicNames":[],"topicsNotShown":0,"primaryLanguage":{"name":"C++","color":"#f34b7d"},"pullRequestCount":0,"issueCount":1,"starsCount":6,"forksCount":8,"license":"GNU General Public License v3.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-03T07:37:25.944Z"}},{"type":"Public","name":"mbtserver","owner":"LanguageMachines","isFork":false,"description":"","topicNames":[],"topicsNotShown":0,"primaryLanguage":{"name":"C++","color":"#f34b7d"},"pullRequestCount":0,"issueCount":0,"starsCount":1,"forksCount":2,"license":"GNU General Public License v3.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-03T07:24:22.312Z"}},{"type":"Public","name":"mbttests","owner":"LanguageMachines","isFork":false,"description":"Unit tests for Mbt","topicNames":[],"topicsNotShown":0,"primaryLanguage":{"name":"Lex","color":"#DBCA00"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-02T16:20:01.154Z"}},{"type":"Public","name":"mbt","owner":"LanguageMachines","isFork":false,"description":"MBT: Memory-based tagger generation and tagging MBT is a memory-based tagger-generator and tagger in one.","topicNames":["nlp","machine-learning","natural-language-processing","c-plus-plus","tagger","timbl"],"topicsNotShown":0,"primaryLanguage":{"name":"C++","color":"#f34b7d"},"pullRequestCount":0,"issueCount":1,"starsCount":9,"forksCount":1,"license":"GNU General Public License v3.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-02T16:01:34.158Z"}},{"type":"Public","name":"uctodata","owner":"LanguageMachines","isFork":false,"description":"Datafiles for the tokenizer ucto. ","topicNames":[],"topicsNotShown":0,"primaryLanguage":{"name":"Shell","color":"#89e051"},"pullRequestCount":0,"issueCount":3,"starsCount":9,"forksCount":5,"license":"GNU General Public License v3.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-26T10:21:42.972Z"}},{"type":"Public","name":"frogtests","owner":"LanguageMachines","isFork":false,"description":"Unit tests for Frog","topicNames":[],"topicsNotShown":0,"primaryLanguage":{"name":"Lex","color":"#DBCA00"},"pullRequestCount":0,"issueCount":1,"starsCount":0,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-25T21:33:37.020Z"}},{"type":"Public","name":"toad","owner":"LanguageMachines","isFork":false,"description":"Toad: Trainer Of All Data, the Frog training collection","topicNames":[],"topicsNotShown":0,"primaryLanguage":{"name":"C++","color":"#f34b7d"},"pullRequestCount":0,"issueCount":1,"starsCount":1,"forksCount":2,"license":"GNU General Public License v3.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-12T09:13:44.612Z"}},{"type":"Public","name":"frogdata","owner":"LanguageMachines","isFork":false,"description":"Data for Frog, mandatory","topicNames":[],"topicsNotShown":0,"primaryLanguage":{"name":"Lex","color":"#DBCA00"},"pullRequestCount":1,"issueCount":1,"starsCount":1,"forksCount":5,"license":"GNU General Public License v3.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-07T09:56:41.618Z"}},{"type":"Public","name":"dimbl","owner":"LanguageMachines","isFork":false,"description":"Distributed Tilburg Memory Based Learner","topicNames":["cpp","multithreading","memory-based-learning"],"topicsNotShown":0,"primaryLanguage":{"name":"C++","color":"#f34b7d"},"pullRequestCount":0,"issueCount":0,"starsCount":2,"forksCount":2,"license":"GNU General Public License v3.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-02-06T10:52:19.898Z"}},{"type":"Public","name":"wopr","owner":"LanguageMachines","isFork":false,"description":" Memory Based Word Predictor/Language Model <a href=\"http://ilk.uvt.nl/wopr/\" rel=\"nofollow\">http://ilk.uvt.nl/wopr/</a>","topicNames":["nlp","lm","language-modelling"],"topicsNotShown":0,"primaryLanguage":{"name":"C++","color":"#f34b7d"},"pullRequestCount":0,"issueCount":1,"starsCount":5,"forksCount":0,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-09-27T11:22:12.831Z"}},{"type":"Public","name":"travistest","owner":"LanguageMachines","isFork":false,"description":"small program to test travis issues. Like OSX and Clang OpenMP support","topicNames":[],"topicsNotShown":0,"primaryLanguage":{"name":"M4","color":"#ccc"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-10-04T11:28:40.330Z"}},{"type":"Public","name":"PICCL","owner":"LanguageMachines","isFork":false,"description":"A set of workflows for corpus building through OCR, post-correction and normalisation","topicNames":["nlp","computational-linguistics","corpus-linguistics","corpus-tools","workflow","ocr","folia"],"topicsNotShown":0,"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":3,"starsCount":46,"forksCount":6,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-09-07T12:28:13.493Z"}},{"type":"Public","name":"JASMIN-BLISS-Negation","owner":"LanguageMachines","isFork":false,"description":"Documentation of a corpus sample of Dutch human-computer dialogues annotated with negation cues.","topicNames":[],"topicsNotShown":0,"primaryLanguage":null,"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-04-28T09:01:19.011Z"}},{"type":"Public","name":"releasereport","owner":"LanguageMachines","isFork":false,"description":"","topicNames":[],"topicsNotShown":0,"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":1,"forksCount":2,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2021-10-13T17:10:45.129Z"}},{"type":"Public","name":"news-pt","owner":"LanguageMachines","isFork":false,"description":"","topicNames":[],"topicsNotShown":0,"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2021-06-16T08:44:33.708Z"}},{"type":"Public","name":"CLIN28-website","owner":"LanguageMachines","isFork":false,"description":"","topicNames":[],"topicsNotShown":0,"primaryLanguage":{"name":"CSS","color":"#563d7c"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2021-06-08T08:56:52.774Z"}},{"type":"Public","name":"clariah-plus-tasks","owner":"LanguageMachines","isFork":false,"description":"An overview of CLARIAH-PLUS tasks at CLST, Radboud University, Nijmegen","topicNames":[],"topicsNotShown":0,"primaryLanguage":{"name":"Makefile","color":"#427819"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2021-04-26T12:54:58.887Z"}},{"type":"Public","name":"dialect2keywords","owner":"LanguageMachines","isFork":false,"description":"Webinterface designed to convert words in Dutch dialects (\"dialectopgaven\") into standard Dutch keywords (\"vernederlandste trefwoorden\").","topicNames":[],"topicsNotShown":0,"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":1,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2021-02-12T14:20:42.517Z"}},{"type":"Public","name":"bioport","owner":"LanguageMachines","isFork":false,"description":"Scrape pages about persons ('biographies') from Wikipedia.","topicNames":[],"topicsNotShown":0,"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":1,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-11-03T13:54:10.239Z"}},{"type":"Public","name":"lexiconenrichment","owner":"LanguageMachines","isFork":false,"description":"","topicNames":[],"topicsNotShown":0,"primaryLanguage":{"name":"Shell","color":"#89e051"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-08-24T20:31:39.336Z"}},{"type":"Public","name":"json","owner":"LanguageMachines","isFork":true,"description":"JSON for Modern C++","topicNames":[],"topicsNotShown":0,"primaryLanguage":{"name":"C++","color":"#f34b7d"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":6520,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2019-11-18T14:51:35.008Z"}}],"repositoryCount":53,"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":"mirror","text":"Mirrors"},{"id":"template","text":"Templates"}],"compactMode":false},"title":"Repositories"}