{"payload":{"pageCount":1,"repositories":[{"type":"Public","name":"common-crawl-utils","owner":"tokenmill","isFork":false,"description":"Various Common Crawl utilities in Clojure.","allTopics":["clojure","clojure-library","warc","common-crawl","cdx-api"],"primaryLanguage":{"name":"Clojure","color":"#db5855"},"pullRequestCount":1,"issueCount":2,"starsCount":6,"forksCount":1,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-12-05T22:22:56.334Z"}},{"type":"Public","name":"dictionary-annotator","owner":"tokenmill","isFork":false,"description":"Fast and configurable UIMA dictionary annotator.","allTopics":["nlp","csv","dictionary","ruta","dkpro","annotators"],"primaryLanguage":{"name":"Java","color":"#b07219"},"pullRequestCount":2,"issueCount":1,"starsCount":7,"forksCount":0,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-04-17T15:52:33.927Z"}},{"type":"Public","name":"crawling-framework","owner":"tokenmill","isFork":false,"description":"Easily crawl news portals or blog sites using Storm Crawler.","allTopics":["storm","scraping","crawling","vaadin","java","elasticsearch","crawler","crawling-framework","storm-crawler"],"primaryLanguage":{"name":"Java","color":"#b07219"},"pullRequestCount":11,"issueCount":10,"starsCount":21,"forksCount":3,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-11-15T23:31:06.427Z"}},{"type":"Public","name":"unsupervised-keyphrase-extraction","owner":"tokenmill","isFork":true,"description":"EmbedRank: Unsupervised Keyphrase Extraction using Sentence Embeddings (official implementation)","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":87,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2021-09-08T15:29:08.430Z"}},{"type":"Public","name":"beagle","owner":"tokenmill","isFork":false,"description":"Beagle helps you identify keywords, phrases, regexes, and complex search queries of interest in streams of text documents.","allTopics":["java","nlp","clojure","lucene","luwak","stemming","stream-search","stored-query-engine","real-time-search"],"primaryLanguage":{"name":"Clojure","color":"#db5855"},"pullRequestCount":0,"issueCount":13,"starsCount":52,"forksCount":3,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2021-06-30T12:18:14.658Z"}},{"type":"Public","name":"clojure-graalvm-aws-lambda-template","owner":"tokenmill","isFork":false,"description":"Leiningen template for AWS Lambda custom runtime with GraalVM native image compiled Clojure projects. ","allTopics":["docker","clojure","aws-lambda","graalvm","lein-template","aws-lambda-clojure","aws-lambda-custom-runtime"],"primaryLanguage":{"name":"Clojure","color":"#db5855"},"pullRequestCount":0,"issueCount":4,"starsCount":44,"forksCount":2,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-10-05T08:13:19.481Z"}},{"type":"Public","name":"doccano","owner":"tokenmill","isFork":true,"description":"Open source text annotation tool for machine learning practitioner.","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":1681,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-07-15T12:45:08.841Z"}},{"type":"Public","name":"gf-wordnet","owner":"tokenmill","isFork":true,"description":"A WordNet in GF","allTopics":[],"primaryLanguage":{"name":"Grammatical Framework","color":"#ff0000"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":10,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-03-01T11:04:34.334Z"}},{"type":"Public","name":"openccg","owner":"tokenmill","isFork":true,"description":"OpenCCG library for parsing and realization with CCG","allTopics":[],"primaryLanguage":{"name":"Java","color":"#b07219"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":44,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2019-10-24T12:38:42.822Z"}},{"type":"Public","name":"beagle-performance-benchmarks","owner":"tokenmill","isFork":false,"description":"Performance benchmarks for the Beagle library, and comparisons with other stored-query solutions.","allTopics":[],"primaryLanguage":{"name":"Clojure","color":"#db5855"},"pullRequestCount":0,"issueCount":0,"starsCount":1,"forksCount":0,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2019-10-01T08:41:48.149Z"}},{"type":"Public","name":"snowball","owner":"tokenmill","isFork":false,"description":"Snowball version of the Porter stemmer for the Lithuanian language.","allTopics":["nlp","snowball","stemmer","porter-stemmer","lithuanian-language"],"primaryLanguage":null,"pullRequestCount":0,"issueCount":0,"starsCount":7,"forksCount":3,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2019-09-04T10:59:45.748Z"}},{"type":"Public","name":"docx-utils","owner":"tokenmill","isFork":false,"description":"Easily work with .docx files from Clojure (a wrapper on Apache POI library).","allTopics":["clojure","docx","poi","clojars"],"primaryLanguage":{"name":"Clojure","color":"#db5855"},"pullRequestCount":0,"issueCount":5,"starsCount":11,"forksCount":3,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2019-09-04T10:54:45.654Z"}},{"type":"Public","name":"es-utils","owner":"tokenmill","isFork":false,"description":"Clojure helper functions for Elasticsearch.","allTopics":["elasticsearch","clojure"],"primaryLanguage":{"name":"Clojure","color":"#db5855"},"pullRequestCount":0,"issueCount":1,"starsCount":1,"forksCount":0,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2019-09-04T10:51:44.556Z"}},{"type":"Public","name":"crawling-framework-example","owner":"tokenmill","isFork":false,"description":"Demonstration on how to use the Crawling Framework to setup a simple science news crawler and store results in ElasticSearch. Use this configuration to set up your own crawler.","allTopics":["elasticsearch","crawler","crawling-framework","storm-crawler"],"primaryLanguage":{"name":"Java","color":"#b07219"},"pullRequestCount":0,"issueCount":0,"starsCount":3,"forksCount":0,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2019-09-04T10:48:45.067Z"}},{"type":"Public","name":"docker-images","owner":"tokenmill","isFork":false,"description":"Docker configurations, images, and examples of Dockerfiles for various TokenMill products and projects.Official source for Docker configurations, images, and examples of Dockerfiles for TokenMill products and projects","allTopics":["docker","clojure","graalvm","dockerfiles","docker-images","docker-configurations"],"primaryLanguage":{"name":"Dockerfile","color":"#384d54"},"pullRequestCount":0,"issueCount":1,"starsCount":5,"forksCount":0,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2019-09-04T10:46:15.932Z"}},{"type":"Public","name":"fast-url-access-checker","owner":"tokenmill","isFork":false,"description":"Easily run HTTP GET requests against a list of URLs to check their HTTP status.","allTopics":["java","clojure","http-redirect","url-cleaning","http-status","url-checker"],"primaryLanguage":{"name":"Clojure","color":"#db5855"},"pullRequestCount":0,"issueCount":4,"starsCount":12,"forksCount":4,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2019-09-04T09:36:26.812Z"}},{"type":"Public","name":"timewords","owner":"tokenmill","isFork":false,"description":"Multilingual library to easily parse date strings to java.util.Date objects.","allTopics":["java","natural-language-processing","clojure","date-time","date-parser","parsing"],"primaryLanguage":{"name":"Clojure","color":"#db5855"},"pullRequestCount":0,"issueCount":6,"starsCount":30,"forksCount":1,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2019-09-04T08:53:40.841Z"}},{"type":"Public","name":"spaCy","owner":"tokenmill","isFork":true,"description":"💫 Industrial-strength Natural Language Processing (NLP) with Python and Cython","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":4315,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2019-07-02T16:40:38.211Z"}},{"type":"Public","name":"faraday","owner":"tokenmill","isFork":true,"description":"DynamoDB client for Clojure","allTopics":[],"primaryLanguage":{"name":"Clojure","color":"#db5855"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":84,"license":"Eclipse Public License 1.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2019-06-03T12:44:20.118Z"}},{"type":"Public archive","name":"metadata-detector","owner":"tokenmill","isFork":false,"description":"Library to detect metadata from html files.","allTopics":[],"primaryLanguage":{"name":"HTML","color":"#e34c26"},"pullRequestCount":0,"issueCount":1,"starsCount":0,"forksCount":0,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2016-12-16T15:08:16.405Z"}},{"type":"Public archive","name":"ltlangpack","owner":"tokenmill","isFork":true,"description":"Tools for Lithuanian language processing","allTopics":[],"primaryLanguage":{"name":"Shell","color":"#89e051"},"pullRequestCount":0,"issueCount":0,"starsCount":15,"forksCount":7,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2016-06-15T09:10:06.847Z"}}],"repositoryCount":21,"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"}