| { |
| "title": "KorAP/KorAP-Tokenizer", |
| "description": "DFA tokenizer with character offset output, large abbreviation tables and CMC support.", |
| "license": "Apache-2.0", |
| "upload_type": "software", |
| "access_right": "open", |
| "creators": [ |
| { |
| "name": "Kupietz, Marc", |
| "affiliation": "Leibniz-Institut für Deutsche Sprache" |
| }, |
| { |
| "name": "Diewald, Nils", |
| "affiliation": "Leibniz-Institut für Deutsche Sprache" |
| } |
| ], |
| "communities": [ |
| { |
| "identifier": "natural-language-processing" |
| } |
| ], |
| "keywords": [ |
| "tokenizer", |
| "NLP", |
| "natural language processing", |
| "DFA", |
| "German", |
| "English", |
| "French", |
| "KorAP" |
| ] |
| } |