diff --git a/DOCS/meetings_protocol.md b/DOCS/meetings_protocol.md index cb3bf86a2..4b94b1c5d 100644 --- a/DOCS/meetings_protocol.md +++ b/DOCS/meetings_protocol.md @@ -4,7 +4,7 @@ **Time**: 10:30 - 12:00 (Berlin) -**Participants** (alphabetical): Alieva, Aibaniz, Beatrice Gründler, Xenia Kudela, Jonas Müller-Laackman, Sido Bozan, Joudy +**Participants** (alphabetical): Alieva, Aibaniz, Beatrice Gründler, Xenia Kudela, Jonas Müller-Laackman, Sido Bozan, Joudy - Team @@ -13,20 +13,20 @@ - Tool´s list - - We will start a collaboration with the Scholarly Makerspace at the HU. They have a sustainable WikiData toolbox that could be linked to our list of tools. There are three cooperation scenarios: - - We both use the same tool and display a combination of our data and theirs. - - We enrich their toolbox with our tools and receive an authority file in return. - - We enrich our list with relevant tools from their database (to be discussed; the first two solutions are priorities). + - We will start a collaboration with the Scholarly Makerspace at the HU. They have a sustainable WikiData toolbox that could be linked to our list of tools. There are three cooperation scenarios: + - We both use the same tool and display a combination of our data and theirs. + - We enrich their toolbox with our tools and receive an authority file in return. + - We enrich our list with relevant tools from their database (to be discussed; the first two solutions are priorities). Data exchange should be done with SPARQL, which would be a good programming exercise for the SHKs. Next steps: contact the Scholarly Makerspace via email and visit their workshop. - Emails + - The emails to the contacts of the projects existing in our database need to be gathered manually. The process of sending them automatically can be done with Python. - Blog - - We have three upcoming posts for August/September (external contributor), October (Xenia), and December (external contributor). + - We have three upcoming posts for August/September (external contributor), October (Xenia), and December (external contributor). - Xenia, Joudy, and Aibaniz will also co-author a post about the upcoming Dariah workshop. - ##2024-08-05 diff --git a/PROJECTS/gumar/74b74185-081c-40f7-86da-52bdf9f53105.json b/PROJECTS/gumar/74b74185-081c-40f7-86da-52bdf9f53105.json index 13b4299c6..9c12a9f15 100644 --- a/PROJECTS/gumar/74b74185-081c-40f7-86da-52bdf9f53105.json +++ b/PROJECTS/gumar/74b74185-081c-40f7-86da-52bdf9f53105.json @@ -10,7 +10,7 @@ "project": { "title": "Gumar Corpus", "abbr": "", - "type": "project", + "type": "project", "ref": [], "date": [{ "from": "2018", "to": "" }], "maintained": true, @@ -18,8 +18,10 @@ "project_desc": "The aim of the GUMAR project is to automatically annotate a 100M-word Gulf Arabic corpus and develop gold standard data annotations for 200,000 words from eight novels, improving tools for Gulf Arabic automatic analysis.", "places": [ { - "place_name": { "text": "Abu Dabi", - "ref": ["https://www.geonames.org/292968/abu-dhabi.html"] }, + "place_name": { + "text": "Abu Dabi", + "ref": ["https://www.geonames.org/292968/abu-dhabi.html"] + }, "coordinates": { "lat": "0", "lng": "0" } } ], @@ -27,21 +29,23 @@ "related_institutions": [ { "relation_type": "host", - "org_name": { - "text": "New York University Abu Dhabi", + "org_name": { + "text": "New York University Abu Dhabi", "ref": [ "https://ror.org/00e5k0821", "https://www.wikidata.org/wiki/Q566189" - ] }, + ] + }, "websites": ["https://nyuad.nyu.edu/en/"] } ], "related_entities": [], "contacts": [ { - "pers_name": { - "text": "Habash, Nizar", - "ref": ["https://www.wikidata.org/wiki/Q93953901"] }, + "pers_name": { + "text": "Habash, Nizar", + "ref": ["https://www.wikidata.org/wiki/Q93953901"] + }, "roles": ["supervision"], "websites": ["https://www.nizarhabash.com"] } @@ -81,7 +85,7 @@ "corpus_output", "dialectology", "nlp" - ], + ], "category": "tools_and_analysis", "comment": "" } diff --git a/PROJECTS/madar/693b7383-6f97-46a6-9023-6aae878c25e7.json b/PROJECTS/madar/693b7383-6f97-46a6-9023-6aae878c25e7.json index 5bcffad83..51bcf7718 100644 --- a/PROJECTS/madar/693b7383-6f97-46a6-9023-6aae878c25e7.json +++ b/PROJECTS/madar/693b7383-6f97-46a6-9023-6aae878c25e7.json @@ -1,214 +1,149 @@ { - "schema_version": "0.2.4", - "record_metadata": { - "uuid": "693b7383-6f97-46a6-9023-6aae878c25e7", - "record_created_on": "2024-08-20", - "record_created_by": "Alieva, Aibaniz", - "last_edited_on": "", - "interviewed": false - }, - "project": { - "title": "Multi-Arabic Dialect Applications and Resources", - "abbr": "MADAR", - "type": "project", - "ref": [], - "date": [ - { - "from": "2016-02", - "to": "2019-01" - } - ], - "maintained": true, - "websites": [ - "https://sites.google.com/nyu.edu/madar/" - ], - "project_desc": - "The project aimed at improving dialectal Arabic processing by developing resources for Arabic dialect modeling, including a 25-city multi-dialect lexicon and parallel corpus, as well as creating machine translation systems between dialects, English, and Standard Arabic, and advancing dialect identification systems capable of operating at different levels of granularity.", - "places": [ - { - "place_name": { - "text": "Doha", - "ref": [ - "https://www.geonames.org/290030/doha.html" - ] - }, - "coordinates": { - "lat": "24.73677", - "lng": "81.44660" - } - }, - { - "place_name": { - "text": "Abu Dabi", - "ref": [ - "https://www.geonames.org/292968/abu-dhabi.html" - ] - }, - "coordinates": { - "lat": "0", - "lng": "0" - } - }, - { - "place_name": { - "text": "New York", - "ref": [ - "https://www.geonames.org/5128581/new-york-city.html" - ] - }, - "coordinates": { - "lat": "0", - "lng": "0" - } - } - ], - "lang": [ - "eng" - ], - "related_institutions": [ - { - "relation_type": "host", - "org_name": { - "text": "Carnegie Mellon University Qatar", - "ref": [ - "https://ror.org/00az5dt38", - "https://www.wikidata.org/wiki/Q890704" - ] - }, - "websites": [ - "https://www.qatar.cmu.edu" - ] - }, - { - "relation_type": "host", - "org_name": { - "text": "New York University Abu Dhabi", - "ref": [ - "https://ror.org/00e5k0821", - "https://www.wikidata.org/wiki/Q566189" - ] - }, - "websites": [ - "https://nyuad.nyu.edu/en/" - ] - }, - { - "relation_type": "host", - "org_name": { - "text": "Columbia University", - "ref": [ - "https://ror.org/00hj8s172", - "https://www.wikidata.org/wiki/Q49088" - ] - }, - "websites": [ - "https://www.columbia.edu" - ] - }, - { - "relation_type": "cooperation", - "org_name": { - "text": "University of Bahrain", - "ref": [ - "https://ror.org/0317ekv86", - "https://www.wikidata.org/wiki/Q1707779" - ] - }, - "websites": [ - "https://www.uob.edu.bh" - ] - } - ], - "related_entities": [], - "contacts": [ - { - "pers_name": { - "text": "Habash, Nizar", - "ref": [ - "https://www.wikidata.org/wiki/Q93953901" - ] - }, - "roles": [ - "supervision" - ], - "websites": [ - "https://www.nizarhabash.com" - ] - }, - { - "pers_name": { - "text": "Oflazer, Kemal", - "ref": [ - "https://www.wikidata.org/wiki/Q102215353" - ] - }, - "roles": [ - "supervision" - ], - "websites": [ - "https://sites.google.com/andrew.cmu.edu/kemal-oflazer/" - ] - } - ], - "research_data": { - "lang": [ - "ara" - ], - "sustainability_plan": null, - "publications": { - "open_access": 0, - "licensing": [] - }, - "data": { - "datatypes": [ - { - "label": "", - "stage": "raw", - "licensing": [], - "open_access": 0 - } - ], - "repositories": [ - { - "label": "", - "accessibility": "public", - "ref": [], - "licensing": [], - "description": "" - } - ] - } + "schema_version": "0.2.4", + "record_metadata": { + "uuid": "693b7383-6f97-46a6-9023-6aae878c25e7", + "record_created_on": "2024-08-20", + "record_created_by": "Alieva, Aibaniz", + "last_edited_on": "", + "interviewed": false + }, + "project": { + "title": "Multi-Arabic Dialect Applications and Resources", + "abbr": "MADAR", + "type": "project", + "ref": [], + "date": [{ "from": "2016-02", "to": "2019-01" }], + "maintained": true, + "websites": ["https://sites.google.com/nyu.edu/madar/"], + "project_desc": "The project aimed at improving dialectal Arabic processing by developing resources for Arabic dialect modeling, including a 25-city multi-dialect lexicon and parallel corpus, as well as creating machine translation systems between dialects, English, and Standard Arabic, and advancing dialect identification systems capable of operating at different levels of granularity.", + "places": [ + { + "place_name": { + "text": "Doha", + "ref": ["https://www.geonames.org/290030/doha.html"] }, - "stack": { - "database": [], - "backend": [], - "frontend": [], - "tools": [ - { - "label": "", - "self_developed": false, - "ref": [], - "description": "" - } - ], - "languages": [] + "coordinates": { "lat": "24.73677", "lng": "81.44660" } + }, + { + "place_name": { + "text": "Abu Dabi", + "ref": ["https://www.geonames.org/292968/abu-dhabi.html"] }, - "policies": [ - { - "description": "", - "ref": [] - } - ], - "keywords": [ - "arabic_studies", - "corpus_output", - "dialectology", - "lexicon", - "nlp", - "translation", - "translation_studies" + "coordinates": { "lat": "0", "lng": "0" } + }, + { + "place_name": { + "text": "New York", + "ref": ["https://www.geonames.org/5128581/new-york-city.html"] + }, + "coordinates": { "lat": "0", "lng": "0" } + } + ], + "lang": ["eng"], + "related_institutions": [ + { + "relation_type": "host", + "org_name": { + "text": "Carnegie Mellon University Qatar", + "ref": [ + "https://ror.org/00az5dt38", + "https://www.wikidata.org/wiki/Q890704" + ] + }, + "websites": ["https://www.qatar.cmu.edu"] + }, + { + "relation_type": "host", + "org_name": { + "text": "New York University Abu Dhabi", + "ref": [ + "https://ror.org/00e5k0821", + "https://www.wikidata.org/wiki/Q566189" + ] + }, + "websites": ["https://nyuad.nyu.edu/en/"] + }, + { + "relation_type": "host", + "org_name": { + "text": "Columbia University", + "ref": [ + "https://ror.org/00hj8s172", + "https://www.wikidata.org/wiki/Q49088" + ] + }, + "websites": ["https://www.columbia.edu"] + }, + { + "relation_type": "cooperation", + "org_name": { + "text": "University of Bahrain", + "ref": [ + "https://ror.org/0317ekv86", + "https://www.wikidata.org/wiki/Q1707779" + ] + }, + "websites": ["https://www.uob.edu.bh"] + } + ], + "related_entities": [], + "contacts": [ + { + "pers_name": { + "text": "Habash, Nizar", + "ref": ["https://www.wikidata.org/wiki/Q93953901"] + }, + "roles": ["supervision"], + "websites": ["https://www.nizarhabash.com"] + }, + { + "pers_name": { + "text": "Oflazer, Kemal", + "ref": ["https://www.wikidata.org/wiki/Q102215353"] + }, + "roles": ["supervision"], + "websites": ["https://sites.google.com/andrew.cmu.edu/kemal-oflazer/"] + } + ], + "research_data": { + "lang": ["ara"], + "sustainability_plan": null, + "publications": { "open_access": 0, "licensing": [] }, + "data": { + "datatypes": [ + { "label": "", "stage": "raw", "licensing": [], "open_access": 0 } ], - "category": "tools_and_analysis", - "comment": "" - } -} \ No newline at end of file + "repositories": [ + { + "label": "", + "accessibility": "public", + "ref": [], + "licensing": [], + "description": "" + } + ] + } + }, + "stack": { + "database": [], + "backend": [], + "frontend": [], + "tools": [ + { "label": "", "self_developed": false, "ref": [], "description": "" } + ], + "languages": [] + }, + "policies": [{ "description": "", "ref": [] }], + "keywords": [ + "arabic_studies", + "corpus_output", + "dialectology", + "lexicon", + "nlp", + "translation", + "translation_studies" + ], + "category": "tools_and_analysis", + "comment": "" + } +} diff --git a/PROJECTS/samer/dfb3ca8b-20cb-484a-bd3c-d84821ca97af.json b/PROJECTS/samer/dfb3ca8b-20cb-484a-bd3c-d84821ca97af.json index 2edbc38ab..21b22ab9b 100644 --- a/PROJECTS/samer/dfb3ca8b-20cb-484a-bd3c-d84821ca97af.json +++ b/PROJECTS/samer/dfb3ca8b-20cb-484a-bd3c-d84821ca97af.json @@ -1,144 +1,99 @@ { - "schema_version": "0.2.4", - "record_metadata": { - "uuid": "dfb3ca8b-20cb-484a-bd3c-d84821ca97af", - "record_created_on": "2024-08-21", - "record_created_by": "Alieva, Aibaniz", - "last_edited_on": "2024-08-22", - "interviewed": false - }, - "project": { - "title": "Simplification of Arabic Masterpieces for Extensive Reading", - "abbr": "SAMER", - "type": "project", - "ref": [], - "date": [ - { - "from": "2016", - "to": "2018" - } - ], - "maintained": true, - "websites": [ - "http://samer.camel-lab.com/" - ], - "project_desc": "The aim of the SAMER project is to create standards and tools for simplifying modern Arabic fiction for school-age learners, including a readability scale, a curated readability list, a 36k-word thesaurus, and a simplification platform for Google Docs.", - "places": [ - { - "place_name": { - "text": "Abu Dabi", - "ref": [ - "https://www.geonames.org/292968/abu-dhabi.html" - ] - }, - "coordinates": { - "lat": "0", - "lng": "0" - } - } - ], - "lang": [], - "related_institutions": [ - { - "relation_type": "host", - "org_name": { - "text": "New York University Abu Dhabi", - "ref": [ - "https://ror.org/00e5k0821", - "https://www.wikidata.org/wiki/Q566189" - ] - }, - "websites": [ - "https://nyuad.nyu.edu/en/" - ] - } - ], - "related_entities": [], - "contacts": [ - { - "pers_name": { - "text": "Muhamed Al Khalil", - "ref": [] - }, - "roles": [ - "supervision" - ], - "websites": [ - "https://nyuad.nyu.edu/en/academics/divisions/arts-and-humanities/faculty/muhamed-osman-al-khalil.html" - ] - }, - { - "pers_name": { - "text": "Habash, Nizar", - "ref": [ - "https://www.wikidata.org/wiki/Q93953901" - ] - }, - "roles": [ - "supervision" - ], - "websites": [ - "https://www.nizarhabash.com" - ] - } - ], - "research_data": { - "lang": [ - "ara" - ], - "sustainability_plan": null, - "publications": { - "open_access": 0, - "licensing": [] - }, - "data": { - "datatypes": [ - { - "label": "", - "stage": "raw", - "licensing": [], - "open_access": 0 - } - ], - "repositories": [ - { - "label": "", - "accessibility": "public", - "ref": [], - "licensing": [], - "description": "" - } - ] - } + "schema_version": "0.2.4", + "record_metadata": { + "uuid": "dfb3ca8b-20cb-484a-bd3c-d84821ca97af", + "record_created_on": "2024-08-21", + "record_created_by": "Alieva, Aibaniz", + "last_edited_on": "2024-08-22", + "interviewed": false + }, + "project": { + "title": "Simplification of Arabic Masterpieces for Extensive Reading", + "abbr": "SAMER", + "type": "project", + "ref": [], + "date": [{ "from": "2016", "to": "2018" }], + "maintained": true, + "websites": ["http://samer.camel-lab.com/"], + "project_desc": "The aim of the SAMER project is to create standards and tools for simplifying modern Arabic fiction for school-age learners, including a readability scale, a curated readability list, a 36k-word thesaurus, and a simplification platform for Google Docs.", + "places": [ + { + "place_name": { + "text": "Abu Dabi", + "ref": ["https://www.geonames.org/292968/abu-dhabi.html"] }, - "stack": { - "database": [], - "backend": [], - "frontend": [], - "tools": [ - { - "label": "", - "self_developed": false, - "ref": [], - "description": "" - } - ], - "languages": [] + "coordinates": { "lat": "0", "lng": "0" } + } + ], + "lang": [], + "related_institutions": [ + { + "relation_type": "host", + "org_name": { + "text": "New York University Abu Dhabi", + "ref": [ + "https://ror.org/00e5k0821", + "https://www.wikidata.org/wiki/Q566189" + ] }, - "policies": [ - { - "description": "", - "ref": [] - } - ], - "keywords": [ - "arabic_studies", - "corpus_output", - "e_learning", - "lexicon", - "nlp" + "websites": ["https://nyuad.nyu.edu/en/"] + } + ], + "related_entities": [], + "contacts": [ + { + "pers_name": { "text": "Muhamed Al Khalil", "ref": [] }, + "roles": ["supervision"], + "websites": [ + "https://nyuad.nyu.edu/en/academics/divisions/arts-and-humanities/faculty/muhamed-osman-al-khalil.html" + ] + }, + { + "pers_name": { + "text": "Habash, Nizar", + "ref": ["https://www.wikidata.org/wiki/Q93953901"] + }, + "roles": ["supervision"], + "websites": ["https://www.nizarhabash.com"] + } + ], + "research_data": { + "lang": ["ara"], + "sustainability_plan": null, + "publications": { "open_access": 0, "licensing": [] }, + "data": { + "datatypes": [ + { "label": "", "stage": "raw", "licensing": [], "open_access": 0 } ], - "category": "tools_and_analysis", - "comment": "" - } -} \ No newline at end of file + "repositories": [ + { + "label": "", + "accessibility": "public", + "ref": [], + "licensing": [], + "description": "" + } + ] + } + }, + "stack": { + "database": [], + "backend": [], + "frontend": [], + "tools": [ + { "label": "", "self_developed": false, "ref": [], "description": "" } + ], + "languages": [] + }, + "policies": [{ "description": "", "ref": [] }], + "keywords": [ + "arabic_studies", + "corpus_output", + "e_learning", + "lexicon", + "nlp" + ], + "category": "tools_and_analysis", + "comment": "" + } +}