From d81d55e6778f5f6db4f76356ed8fd3f6b235bf62 Mon Sep 17 00:00:00 2001 From: Kudela <kudem94@fu-berlin.de> Date: Tue, 14 Jun 2022 16:37:14 +0200 Subject: [PATCH] add: new project - multi_cast --- PROJECTS.json | 4 + .../b37c6bd1-90d3-4718-ab58-fb1d60873186.json | 214 ++++++++++++++++++ 2 files changed, 218 insertions(+) create mode 100644 PROJECTS/multi_cast/b37c6bd1-90d3-4718-ab58-fb1d60873186.json diff --git a/PROJECTS.json b/PROJECTS.json index 8f14c2d..ed6d492 100644 --- a/PROJECTS.json +++ b/PROJECTS.json @@ -247,6 +247,10 @@ "title": "Methoden der Manuskriptanalyse zur Wiedergewinnung verlorener Schrift", "path": "/PROJECTS/methoden_der_manuskriptanalyse_zur_wiedergewinnung_verlorener_schrift/" }, + "b37c6bd1-90d3-4718-ab58-fb1d60873186": { + "title": "Multilingual Corpus of Annotated Spoken Texts", + "path": "/PROJECTS/multi_cast/" + }, "e050deba-6e1d-4d82-851b-cf6c1f7187a5": { "title": "NoMansLand: Nomads' Manuscripts Landscape", "path": "/PROJECTS/nomansland/" diff --git a/PROJECTS/multi_cast/b37c6bd1-90d3-4718-ab58-fb1d60873186.json b/PROJECTS/multi_cast/b37c6bd1-90d3-4718-ab58-fb1d60873186.json new file mode 100644 index 0000000..a4edf18 --- /dev/null +++ b/PROJECTS/multi_cast/b37c6bd1-90d3-4718-ab58-fb1d60873186.json @@ -0,0 +1,214 @@ +{ + "schema_version": "0.1.5", + "record_metadata": { + "uuid": "b37c6bd1-90d3-4718-ab58-fb1d60873186", + "record_created": "2002-06-16", + "record_created_by": "Kudela, Xenia Monika", + "record_modified": [ + { + "record_modified_on": "", + "record_modified_by": "" + } + ] + }, + "project": { + "title": "Multilingual Corpus of Annotated Spoken Texts", + "abbr": "Multi-CAST", + "type": "project", + "ref": [], + "date": [ + { + "from": "2000", + "to": "2021" + } + ], + "websites": [ + "https://multicast.aspra.uni-bamberg.de/#references", + "https://www.uni-bamberg.de/aspra/forschung/projekte/multi-cast-multilingual-corpus-of-annotated-spoken-texts/" + ], + "project_desc": "Mulit_Cast is a collection of annotated texts from a typologically diverse section of 15 languages including endangered once. The corpus is freely accessible via an online platform which provides multiple levels of parallel annotations, time-aligned with audio recordings, chiefly monologic, natural narrative texts from 15 languages, encompassing roughly 25 000 clause units available in multiple file formats, including as EAF files for the linguistic annotation software ELAN, as XML and TSV files, and via the multicastR package for R.", + "places": [ + { + "place_name": { + "text": "Bamberg", + "ref": [ + "https://www.geonames.org/2952984/bamberg.html" + ] + }, + "coordinates": { + "lat": "49.89873", + "lng": "10.90067" + } + } + ], + "lang": [ + "eng", + "ger" + ], + "topic_relations": { + "nls": true, + "dh": true, + "meta": false, + "rdm": false, + "infrastructure": false + }, + "parents": [ + { + "type": "organisation", + "org_name": { + "text": "University of Bamberg", + "ref": [ + "https://www.grid.ac/institutes/grid.7359.8" + ] + }, + "websites": [ + "https://www.uni-bamberg.de/" + ], + "places": [ + { + "place_name": { + "text": "Bamberg", + "ref": [ + "https://www.geonames.org/2952984/bamberg.html" + ] + } + } + ], + "parents": [], + "siblings": [], + "children": [] + } + ], + "children": [], + "siblings": [], + "contacts": [ + { + "pers_name": { + "text": "Haig, Geoffrey", + "ref": [ + "https://d-nb.info/gnd/1016008090" + ] + }, + "role": 0, + "websites": [ + "https://www.uni-bamberg.de/aspra/team/aktuelles-team/prof-dr-geoffrey-haig/" + ] + } + ], + "research_data": { + "lang": [ + "atz", + "cmn", + "dar", + "eng", + "erk", + "gre", + "kac", + "kgv", + "kmr", + "per", + "tab", + "tdn", + "tio", + "tuh", + "vra" + ], + "publications": { + "access": { + "open": 0.0, + "closed": 100.0, + "margin": 0.0 + }, + "licensing": [ + "" + ] + }, + "data": { + "raw": { + "datatypes": [ + { + "label": "", + "licensing": [ + "" + ], + "access": { + "open": 0.0, + "closed": 100.0, + "margin": 0.0 + } + } + ], + "repositories": [ + { + "type": "local", + "accessibility": "restricted", + "description": "folder-based data storage" + }, + { + "type": "remote", + "accessibility": "open", + "ref": "", + "description": "github" + } + ] + }, + "refined": {}, + "final": {} + } + }, + "stack": { + "database": [ + "sql", + "xml", + "json", + "nosql" + ], + "backend": [ + "laravel" + ], + "frontend": [ + "vue" + ], + "tools": [ + { + "label": "mallet", + "self_developed": false, + "ref": "https://...", + "purpose": "Zeit schinden" + } + ], + "languages": [ + "php", + "javascript", + "python" + ] + }, + "policies": [ + { + "type": "", + "uri": "" + } + ], + "keywords": [ + "atz", + "cmn", + "corpus_linguistics", + "dar", + "eng", + "erk", + "gre", + "kac", + "kgv", + "kmr", + "language_resources", + "multilingual_corpus", + "per", + "tab", + "tdn", + "tio", + "tuh", + "vra" + ], + "comment": "" + } +} \ No newline at end of file -- GitLab