[ { "key": "K9FRQSEZ", "version": 8267, "library": { "type": "group", "id": 562080, "name": "CLARIN", "links": { "alternate": { "href": "https://www.zotero.org/groups/clarin", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/562080/items/K9FRQSEZ", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/clarin/items/K9FRQSEZ", "type": "text/html" } }, "meta": { "createdByUser": { "id": 15561362, "username": "l.gusan", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/l.gusan", "type": "text/html" } } }, "creatorSummary": "Pahor de Maiti Tekavčič et al.", "parsedDate": "2025-09-20", "numChildren": 0 }, "data": { "key": "K9FRQSEZ", "version": 8267, "itemType": "book", "title": "Tour de CLARIN Volume Five", "creators": [ { "creatorType": "editor", "firstName": "Kristina", "lastName": "Pahor de Maiti Tekavčič" }, { "creatorType": "editor", "firstName": "Jakob", "lastName": "Lenardič" }, { "creatorType": "editor", "firstName": "Karina", "lastName": "Berger" }, { "creatorType": "contributor", "firstName": "Karlheinz", "lastName": "Mörth" }, { "creatorType": "contributor", "firstName": "Walter", "lastName": "Scholger" }, { "creatorType": "contributor", "firstName": "Martina", "lastName": "Scholger" }, { "creatorType": "contributor", "firstName": "Hannes", "lastName": "Pirker" }, { "creatorType": "contributor", "firstName": "Sabrina", "lastName": "Melcher" }, { "creatorType": "contributor", "firstName": "Amelie", "lastName": "Dorn" }, { "creatorType": "contributor", "firstName": "Starkaður", "lastName": "Barkarson" }, { "creatorType": "contributor", "firstName": "Jurgita", "lastName": "Vaičenonienė" }, { "creatorType": "contributor", "firstName": "Sigríður", "lastName": "Ólafsdóttir" }, { "creatorType": "contributor", "firstName": "Virginijus", "lastName": "Dadurkevičius" }, { "creatorType": "contributor", "firstName": "Sigita", "lastName": "Rackevičienė" }, { "creatorType": "contributor", "firstName": "Erika", "lastName": "Rimkutė" }, { "creatorType": "contributor", "firstName": "Krzysztof", "lastName": "Hwaszcz" }, { "creatorType": "contributor", "firstName": "Agnieszka", "lastName": "Hess" }, { "creatorType": "contributor", "firstName": "Cristina", "lastName": "Grisot" }, { "creatorType": "contributor", "firstName": "Clemens", "lastName": "Lutz" }, { "creatorType": "contributor", "firstName": "Seraina", "lastName": "Nadig" }, { "creatorType": "contributor", "firstName": "Alexandru", "lastName": "Craevschi" }, { "creatorType": "contributor", "firstName": "Jannis", "lastName": "Vamvas" }, { "creatorType": "contributor", "firstName": "Costanza", "lastName": "Navarretta" }, { "creatorType": "contributor", "firstName": "Sidsel", "lastName": "Boldsen" }, { "creatorType": "contributor", "firstName": "Kerstin", "lastName": "Klenke" }, { "creatorType": "contributor", "firstName": "Fayrouz", "lastName": "Kaddal" }, { "creatorType": "contributor", "firstName": "Arne", "lastName": "Jönsson" }, { "creatorType": "contributor", "firstName": "Andrea", "lastName": "Fried" }, { "creatorType": "contributor", "firstName": "Inguna", "lastName": "Skadiņa" }, { "creatorType": "contributor", "firstName": "Kristīna", "lastName": "Korneliusa" } ], "abstractNote": "", "series": "", "seriesNumber": "", "volume": "", "numberOfVolumes": "", "edition": "", "date": "2025-09-20", "publisher": "", "place": "", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "numPages": "", "ISBN": "978-90-829909-4-2", "DOI": "", "citationKey": "pahordemaititekavcic-EtAl:2025:TourCLARINVolume", "url": "https://zenodo.org/records/17406535", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "English", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "DIRMCTJC" ], "relations": {}, "dateAdded": "2025-10-21T12:04:16Z", "dateModified": "2026-03-12T13:02:40Z" } }, { "key": "A4EU3CW2", "version": 8221, "library": { "type": "group", "id": 562080, "name": "CLARIN", "links": { "alternate": { "href": "https://www.zotero.org/groups/clarin", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/562080/items/A4EU3CW2", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/clarin/items/A4EU3CW2", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3167571, "username": "dietervu", "name": "Dieter Van Uytvanck", "links": { "alternate": { "href": "https://www.zotero.org/dietervu", "type": "text/html" } } }, "lastModifiedByUser": { "id": 332053, "username": "iiegn", "name": "egon stemle", "links": { "alternate": { "href": "https://www.zotero.org/iiegn", "type": "text/html" } } }, "creatorSummary": "Fan et al.", "parsedDate": "2025-08-05", "numChildren": 1 }, "data": { "key": "A4EU3CW2", "version": 8221, "itemType": "preprint", "title": "Can Performant LLMs Be Ethical? Quantifying the Impact of Web Crawling Opt-Outs", "creators": [ { "creatorType": "author", "firstName": "Dongyang", "lastName": "Fan" }, { "creatorType": "author", "firstName": "Vinko", "lastName": "Sabolčec" }, { "creatorType": "author", "firstName": "Matin", "lastName": "Ansaripour" }, { "creatorType": "author", "firstName": "Ayush Kumar", "lastName": "Tarun" }, { "creatorType": "author", "firstName": "Martin", "lastName": "Jaggi" }, { "creatorType": "author", "firstName": "Antoine", "lastName": "Bosselut" }, { "creatorType": "author", "firstName": "Imanol", "lastName": "Schlag" } ], "abstractNote": "The increasing adoption of web crawling opt-outs by copyright holders of online content raises critical questions about the impact of data compliance on large language model (LLM) performance. However, little is known about how these restrictions (and the resultant filtering of pretraining datasets) affect the capabilities of models trained using these corpora. In this work, we conceptualize this effect as the $\\textit{data compliance gap}$ (DCG), which quantifies the performance difference between models trained on datasets that comply with web crawling opt-outs, and those that do not. We measure the data compliance gap in two settings: pretraining models from scratch and continual pretraining from existing compliant models (simulating a setting where copyrighted data could be integrated later in pretraining). Our experiments with 1.5B models show that, as of January 2025, compliance with web data opt-outs does not degrade general knowledge acquisition (close to 0\\% DCG). However, in specialized domains such as biomedical research, excluding major publishers leads to performance declines. These findings suggest that while general-purpose LLMs can be trained to perform equally well using fully open data, performance in specialized domains may benefit from access to high-quality copyrighted sources later in training. Our study provides empirical insights into the long-debated trade-off between data compliance and downstream model performance, informing future discussions on AI training practices and policy decisions. Our website is available at https://data-compliance.github.io/.", "genre": "", "repository": "arXiv", "archiveID": "arXiv:2504.06219", "place": "", "date": "2025-08-05", "series": "", "seriesNumber": "", "DOI": "10.48550/arXiv.2504.06219", "citationKey": "fan-EtAl:2025:CanPerformantLLMs", "url": "http://arxiv.org/abs/2504.06219", "accessDate": "2026-01-22T12:50:43Z", "archive": "", "archiveLocation": "", "shortTitle": "Can Performant LLMs Be Ethical?", "language": "", "libraryCatalog": "arXiv.org", "callNumber": "", "rights": "", "extra": "arXiv:2504.06219 [cs]", "tags": [ { "tag": "Computer Science - Computation and Language", "type": 1 }, { "tag": "Computer Science - Machine Learning", "type": 1 } ], "collections": [ "KKRWCCB7" ], "relations": {}, "dateAdded": "2026-01-22T12:50:43Z", "dateModified": "2026-01-22T12:50:43Z" } }, { "key": "B9MXLXDG", "version": 7816, "library": { "type": "group", "id": 562080, "name": "CLARIN", "links": { "alternate": { "href": "https://www.zotero.org/groups/clarin", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/562080/items/B9MXLXDG", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/clarin/items/B9MXLXDG", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/562080/items/A4EU3CW2", "type": "application/json" } }, "meta": { "createdByUser": { "id": 3167571, "username": "dietervu", "name": "Dieter Van Uytvanck", "links": { "alternate": { "href": "https://www.zotero.org/dietervu", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "B9MXLXDG", "version": 7816, "parentItem": "A4EU3CW2", "itemType": "note", "note": "Comment: COLM 2025 Camera Ready version", "tags": [], "relations": {}, "dateAdded": "2026-01-22T12:50:43Z", "dateModified": "2026-01-22T12:50:43Z" } }, { "key": "AX96UVCC", "version": 8221, "library": { "type": "group", "id": 562080, "name": "CLARIN", "links": { "alternate": { "href": "https://www.zotero.org/groups/clarin", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/562080/items/AX96UVCC", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/clarin/items/AX96UVCC", "type": "text/html" } }, "meta": { "createdByUser": { "id": 17573607, "username": "GrietDepoorter", "name": "Griet Depoorter", "links": { "alternate": { "href": "https://www.zotero.org/grietdepoorter", "type": "text/html" } } }, "lastModifiedByUser": { "id": 332053, "username": "iiegn", "name": "egon stemle", "links": { "alternate": { "href": "https://www.zotero.org/iiegn", "type": "text/html" } } }, "creatorSummary": "Nijs", "parsedDate": "2025", "numChildren": 0 }, "data": { "key": "AX96UVCC", "version": 8221, "itemType": "thesis", "title": "Optimization of the Dutch Corpus of Contemporary and late Modern Periodicals (C-CLAMP)", "creators": [ { "creatorType": "author", "firstName": "Julie", "lastName": "Nijs" } ], "abstractNote": "", "thesisType": "", "university": "KU Leuven", "place": "Leuven", "date": "2025", "series": "", "seriesNumber": "", "numPages": "29", "DOI": "", "ISBN": "", "citationKey": "nijs:2025:OptimizationDutchCorpus", "url": "https://taalmaterialen.ivdnt.org/wp-content/uploads/documentatie/C-CLAMP_Internship_Final_Report.pdf", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "English", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "AR3LQ524" ], "relations": {}, "dateAdded": "2025-12-18T09:31:16Z", "dateModified": "2025-12-18T10:32:51Z" } }, { "key": "I3LNPI3W", "version": 8220, "library": { "type": "group", "id": 562080, "name": "CLARIN", "links": { "alternate": { "href": "https://www.zotero.org/groups/clarin", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/562080/items/I3LNPI3W", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/clarin/items/I3LNPI3W", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3167571, "username": "dietervu", "name": "Dieter Van Uytvanck", "links": { "alternate": { "href": "https://www.zotero.org/dietervu", "type": "text/html" } } }, "lastModifiedByUser": { "id": 332053, "username": "iiegn", "name": "egon stemle", "links": { "alternate": { "href": "https://www.zotero.org/iiegn", "type": "text/html" } } }, "creatorSummary": "Prochác", "parsedDate": "2025", "numChildren": 0 }, "data": { "key": "I3LNPI3W", "version": 8220, "itemType": "thesis", "title": "A Chatbot to the CLARIN help", "creators": [ { "creatorType": "author", "firstName": "Filip", "lastName": "Prochác" } ], "abstractNote": "", "thesisType": "", "university": "Masaryk University, Faculty of Informatics", "place": "", "date": "2025", "series": "", "seriesNumber": "", "numPages": "", "DOI": "", "ISBN": "", "citationKey": "prochac:2025:ChatbotCLARINHelp", "url": "https://is.muni.cz/th/v75an/?studium=616837;lang=en", "accessDate": "2025-10-17T13:54:15Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "eng", "libraryCatalog": "is.muni.cz", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "KKRWCCB7" ], "relations": {}, "dateAdded": "2025-10-17T13:54:15Z", "dateModified": "2025-11-04T13:02:16Z" } }, { "key": "224BAC8R", "version": 8220, "library": { "type": "group", "id": 562080, "name": "CLARIN", "links": { "alternate": { "href": "https://www.zotero.org/groups/clarin", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/562080/items/224BAC8R", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/clarin/items/224BAC8R", "type": "text/html" } }, "meta": { "createdByUser": { "id": 12953323, "username": "Thalassia_Kontino", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/thalassia_kontino", "type": "text/html" } } }, "lastModifiedByUser": { "id": 332053, "username": "iiegn", "name": "egon stemle", "links": { "alternate": { "href": "https://www.zotero.org/iiegn", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "224BAC8R", "version": 8220, "itemType": "conferencePaper", "title": "", "creators": [], "abstractNote": "", "proceedingsTitle": "", "conferenceName": "", "publisher": "", "place": "", "date": "", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "::d", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "4KMR4F9N" ], "relations": {}, "dateAdded": "2025-10-30T17:47:33Z", "dateModified": "2025-10-30T17:47:53Z" } }, { "key": "J26K7RN8", "version": 8220, "library": { "type": "group", "id": 562080, "name": "CLARIN", "links": { "alternate": { "href": "https://www.zotero.org/groups/clarin", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/562080/items/J26K7RN8", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/clarin/items/J26K7RN8", "type": "text/html" } }, "meta": { "createdByUser": { "id": 14048329, "username": "Jakoblenardic", "name": "Jakob Lenardič", "links": { "alternate": { "href": "https://www.zotero.org/jakoblenardic", "type": "text/html" } } }, "lastModifiedByUser": { "id": 332053, "username": "iiegn", "name": "egon stemle", "links": { "alternate": { "href": "https://www.zotero.org/iiegn", "type": "text/html" } } }, "creatorSummary": "Kosem", "parsedDate": "2022", "numChildren": 0 }, "data": { "key": "J26K7RN8", "version": 8220, "itemType": "journalArticle", "title": "Trendi: a monitor corpus of Slovene", "creators": [ { "creatorType": "author", "firstName": "Iztok", "lastName": "Kosem" } ], "abstractNote": "In this paper we present Trendi, a monitor corpus of written Slovene, which has been com piled recently as part of the SLED (Monitor corpus and related resources) project. The methodology and the contents of the corpus are presented, as well as the findings of the survey that aimed to identify the needs of potential users related to topical language use. The Trendi corpus currently contains news articles and other web content from 110 different sources, with the texts being collected and linguistically anno tated on a daily basis. The corpus complements Gigafida 2.0, a 1.13billionword reference corpus of stand ard written Slovene. Also discussed are the ways in which the corpus will be integrated into various lexi cographic projects, helping not only in the identification of neologisms but also in monitoring changes in already identified language phenomena.", "publicationTitle": "", "publisher": "", "place": "", "date": "2022", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "kosem:2022:TrendiMonitorCorpus", "url": "", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "Zotero", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "/unread", "type": 1 } ], "collections": [ "7NK8V235" ], "relations": {}, "dateAdded": "2025-10-23T13:06:54Z", "dateModified": "2025-10-23T13:07:12Z" } }, { "key": "KGRWUJI9", "version": 8221, "library": { "type": "group", "id": 562080, "name": "CLARIN", "links": { "alternate": { "href": "https://www.zotero.org/groups/clarin", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/562080/items/KGRWUJI9", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/clarin/items/KGRWUJI9", "type": "text/html" } }, "meta": { "createdByUser": { "id": 6849179, "username": "kreetrapper", "name": "Alexander König", "links": { "alternate": { "href": "https://www.zotero.org/kreetrapper", "type": "text/html" } } }, "lastModifiedByUser": { "id": 332053, "username": "iiegn", "name": "egon stemle", "links": { "alternate": { "href": "https://www.zotero.org/iiegn", "type": "text/html" } } }, "creatorSummary": "Xu and Ingason", "parsedDate": "2021", "numChildren": 0 }, "data": { "key": "KGRWUJI9", "version": 8221, "itemType": "conferencePaper", "title": "Developing flashcards for learning Icelandic", "creators": [ { "creatorType": "author", "firstName": "Xindan", "lastName": "Xu" }, { "creatorType": "author", "firstName": "Anton Karl", "lastName": "Ingason" } ], "abstractNote": "", "proceedingsTitle": "Proceedings of the 10th Workshop on NLP for Computer Assisted Language Learning", "conferenceName": "", "publisher": "", "place": "", "date": "2021", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "55–61", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "xu-ingason:2021:DevelopingFlashcardsLearning", "url": "https://aclanthology.org/2021.nlp4call-1.5.pdf", "accessDate": "2025-10-23T12:52:09Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "Google Scholar", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "RMKAZV79" ], "relations": {}, "dateAdded": "2025-10-23T12:52:10Z", "dateModified": "2025-10-23T12:52:10Z" } }, { "key": "9ZBD55I4", "version": 8218, "library": { "type": "group", "id": 562080, "name": "CLARIN", "links": { "alternate": { "href": "https://www.zotero.org/groups/clarin", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/562080/items/9ZBD55I4", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/clarin/items/9ZBD55I4", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3167571, "username": "dietervu", "name": "Dieter Van Uytvanck", "links": { "alternate": { "href": "https://www.zotero.org/dietervu", "type": "text/html" } } }, "lastModifiedByUser": { "id": 332053, "username": "iiegn", "name": "egon stemle", "links": { "alternate": { "href": "https://www.zotero.org/iiegn", "type": "text/html" } } }, "creatorSummary": "Matthiesen and Lenardič", "parsedDate": "2025", "numChildren": 0 }, "data": { "key": "9ZBD55I4", "version": 8218, "itemType": "journalArticle", "title": "CLARIN Data Citation Guidelines", "creators": [ { "creatorType": "author", "firstName": "Martin", "lastName": "Matthiesen" }, { "creatorType": "author", "firstName": "Jakob", "lastName": "Lenardič" } ], "abstractNote": "", "publicationTitle": "", "publisher": "Common Language Resources and Technology Infrastructure", "place": "", "date": "2025", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.34733/DOC-189", "citationKey": "matthiesen-lenardic:2025:CLARINDataCitation", "url": "https://www.clarin.eu/content/clarin-data-citation-guidelines", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "", "callNumber": "", "rights": "Creative Commons Attribution 4.0 International", "extra": "", "tags": [], "collections": [ "FUDDFV9P" ], "relations": {}, "dateAdded": "2025-10-08T15:24:27Z", "dateModified": "2025-10-08T15:24:50Z" } }, { "key": "6H5GVU83", "version": 8219, "library": { "type": "group", "id": 562080, "name": "CLARIN", "links": { "alternate": { "href": "https://www.zotero.org/groups/clarin", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/562080/items/6H5GVU83", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/clarin/items/6H5GVU83", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3167571, "username": "dietervu", "name": "Dieter Van Uytvanck", "links": { "alternate": { "href": "https://www.zotero.org/dietervu", "type": "text/html" } } }, "lastModifiedByUser": { "id": 332053, "username": "iiegn", "name": "egon stemle", "links": { "alternate": { "href": "https://www.zotero.org/iiegn", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "6H5GVU83", "version": 8219, "itemType": "webpage", "title": "CLARIN-ERIC", "creators": [], "abstractNote": "CLARIN is a European Research Infrastructure for the Humanities and Social Sciences, focusing on language resources (data and tools). It is being implemented and constantly improved at leading institutions in a large and growing number of European countries, aiming at improving Europe's multi-linguality competence. CLARIN provides several services, such as access to language data and tools to analyze data, and offers to deposit research data, as well as direct access to knowledge about relevant topics in relation to (research on and with) language resources. The main tool is the 'Virtual Language Observatory' providing metadata and access to the different national CLARIN centers and their data.", "websiteTitle": "DataCite Fabrica", "websiteType": "", "date": "", "publisher": "", "place": "", "DOI": "", "citationKey": "::CLARINERIC", "url": "https://doi.datacite.org/dois/10.34733%2Fdoc-189", "accessDate": "2025-10-08T15:23:36Z", "shortTitle": "", "language": "en-us", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2025-10-08T15:23:36Z", "dateModified": "2025-10-08T15:23:36Z" } }, { "key": "YCGJAD87", "version": 8219, "library": { "type": "group", "id": 562080, "name": "CLARIN", "links": { "alternate": { "href": "https://www.zotero.org/groups/clarin", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/562080/items/YCGJAD87", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/clarin/items/YCGJAD87", "type": "text/html" } }, "meta": { "createdByUser": { "id": 14048329, "username": "Jakoblenardic", "name": "Jakob Lenardič", "links": { "alternate": { "href": "https://www.zotero.org/jakoblenardic", "type": "text/html" } } }, "lastModifiedByUser": { "id": 332053, "username": "iiegn", "name": "egon stemle", "links": { "alternate": { "href": "https://www.zotero.org/iiegn", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "YCGJAD87", "version": 8219, "itemType": "webpage", "title": "e-LIS: Electronic Bilingual Dictionary Italian Sign Language-Italian - -", "creators": [], "abstractNote": "", "websiteTitle": "", "websiteType": "", "date": "", "publisher": "", "place": "", "DOI": "", "citationKey": "::ELISElectronicBilingual", "url": "https://bia.unibz.it/esploro/outputs/991005773425101241", "accessDate": "2025-10-03T09:20:26Z", "shortTitle": "", "language": "", "rights": "", "extra": "", "tags": [ { "tag": "/unread", "type": 1 } ], "collections": [ "VH5KZA3F" ], "relations": {}, "dateAdded": "2025-10-03T09:20:26Z", "dateModified": "2025-10-03T09:20:27Z" } }, { "key": "MB6Q7I2E", "version": 8219, "library": { "type": "group", "id": 562080, "name": "CLARIN", "links": { "alternate": { "href": "https://www.zotero.org/groups/clarin", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/562080/items/MB6Q7I2E", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/clarin/items/MB6Q7I2E", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3167571, "username": "dietervu", "name": "Dieter Van Uytvanck", "links": { "alternate": { "href": "https://www.zotero.org/dietervu", "type": "text/html" } } }, "lastModifiedByUser": { "id": 332053, "username": "iiegn", "name": "egon stemle", "links": { "alternate": { "href": "https://www.zotero.org/iiegn", "type": "text/html" } } }, "creatorSummary": "CLARIN ERIC Strategy Taskforce", "parsedDate": "2023", "numChildren": 0 }, "data": { "key": "MB6Q7I2E", "version": 8219, "itemType": "journalArticle", "title": "CLARIN Strategy", "creators": [ { "creatorType": "author", "name": "CLARIN ERIC Strategy Taskforce" } ], "abstractNote": "", "publicationTitle": "", "publisher": "CLARIN", "place": "", "date": "2023", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.34733/DOC-188", "citationKey": "clarinericstrategytaskforce:2023:CLARINStrategy", "url": "https://www.clarin.eu/content/clarin-strategy", "accessDate": "2025-09-25T13:13:27Z", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "DOI.org (Datacite)", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "FUDDFV9P" ], "relations": {}, "dateAdded": "2025-09-25T13:13:27Z", "dateModified": "2025-09-25T13:13:27Z" } }, { "key": "7VQZFFWZ", "version": 8219, "library": { "type": "group", "id": 562080, "name": "CLARIN", "links": { "alternate": { "href": "https://www.zotero.org/groups/clarin", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/562080/items/7VQZFFWZ", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/clarin/items/7VQZFFWZ", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3167571, "username": "dietervu", "name": "Dieter Van Uytvanck", "links": { "alternate": { "href": "https://www.zotero.org/dietervu", "type": "text/html" } } }, "lastModifiedByUser": { "id": 332053, "username": "iiegn", "name": "egon stemle", "links": { "alternate": { "href": "https://www.zotero.org/iiegn", "type": "text/html" } } }, "creatorSummary": "CLARIN ERIC Strategy Taskforce", "parsedDate": "2023", "numChildren": 0 }, "data": { "key": "7VQZFFWZ", "version": 8219, "itemType": "document", "title": "CLARIN Strategy", "creators": [ { "creatorType": "author", "name": "CLARIN ERIC Strategy Taskforce" } ], "abstractNote": "", "type": "", "date": "2023", "publisher": "CLARIN", "place": "", "DOI": "", "citationKey": "clarinericstrategytaskforce:2023:CLARINStrategya", "url": "https://www.clarin.eu/content/clarin-strategy", "accessDate": "2025-09-25T13:11:52Z", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2025-09-25T13:11:52Z", "dateModified": "2025-09-25T13:13:13Z" } }, { "key": "TEL6UPXY", "version": 8166, "library": { "type": "group", "id": 562080, "name": "CLARIN", "links": { "alternate": { "href": "https://www.zotero.org/groups/clarin", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/562080/items/TEL6UPXY", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/clarin/items/TEL6UPXY", "type": "text/html" } }, "meta": { "createdByUser": { "id": 4330862, "username": "maria.eskevich", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/maria.eskevich", "type": "text/html" } } }, "lastModifiedByUser": { "id": 332053, "username": "iiegn", "name": "egon stemle", "links": { "alternate": { "href": "https://www.zotero.org/iiegn", "type": "text/html" } } }, "creatorSummary": "Fišer et al.", "parsedDate": "2021-11-01", "numChildren": 0 }, "data": { "key": "TEL6UPXY", "version": 8166, "itemType": "book", "title": "Tour de CLARIN Volume Four", "creators": [ { "creatorType": "author", "firstName": "Darja", "lastName": "Fišer" }, { "creatorType": "author", "firstName": "Jakob", "lastName": "Lenardič" }, { "creatorType": "author", "firstName": "Francesca", "lastName": "Frontini" }, { "creatorType": "author", "firstName": "Erik", "lastName": "Axelson" }, { "creatorType": "author", "firstName": "Tomaž", "lastName": "Erjavec" }, { "creatorType": "author", "firstName": "Maria", "lastName": "Gavriilidou" }, { "creatorType": "author", "firstName": "Krzysztof", "lastName": "Hwaszcz" }, { "creatorType": "author", "firstName": "Taja", "lastName": "Kuzman" }, { "creatorType": "author", "firstName": "Krister", "lastName": "Lindén" }, { "creatorType": "author", "firstName": "Therese", "lastName": "Lindström Tiedemann" }, { "creatorType": "author", "firstName": "Nikola", "lastName": "Ljubešić" }, { "creatorType": "author", "firstName": "Sjur", "lastName": "Moshagen" }, { "creatorType": "author", "firstName": "Petya", "lastName": "Osenova" }, { "creatorType": "author", "firstName": "João", "lastName": "Silva" }, { "creatorType": "author", "firstName": "Inguna", "lastName": "Skadina" }, { "creatorType": "author", "firstName": "Eva", "lastName": "Soroli" }, { "creatorType": "author", "firstName": "Martina", "lastName": "Trognitz" }, { "creatorType": "author", "firstName": "Iro", "lastName": "Tsiouli" }, { "creatorType": "author", "firstName": "Jurgita", "lastName": "Vaičenonienė" } ], "abstractNote": "Since 2016, the Tour de CLARIN initiative has been periodically highlighting prominent user involvement activities in the CLARIN network in order to increase the visibility of its members, reveal the richness of the CLARIN landscape, and display the full range of activities that show what CLARIN has to offer to researchers, teachers, students, professionals, and the general public interested in using and processing language data in various forms. Originally only focussing on CLARIN consortia, this initiative was expanded twice, first in 2019 to also feature the work of CLARIN Knowledge Centres (or K-centres), which offer knowledge and expertise in specific areas to researchers, educators, and developers alike, and second in 2021 to feature Service Providing Centres (or B-centres), which serve as the technical backbone of the CLARIN infrastructure. For almost five years, Tour de CLARIN has been one of the flagship outreach initiatives, thus far released in the form of three printed volumes.\n\nThe fourth volume is organized in two parts. In Part 1, we present CLARIN Portugal in five chapters: an introduction to the consortium, its members, and their work; a description of one of their key resources; the presentation of an outstanding tool; an account of a successful event for the researchers and students in their network; and an interview with a renowned researcher from the Digital Humanities or Social Sciences who has successfully used the consortium’s infrastructure in their work.\n\nIn Part 2, we present the work of six K-centres and two B-centres that have been visited since the publication of the second volume in November 2020: the K-centre for morphologically rich languages SAFMORIL, the French CORLI K-centre, the K-centre for South Slavic languages CLASSLA, the NLP:EL K-centre for Greek, the Austrian B-centre ARCHE, and the CLARIN-PL B-centre. Each centre is presented in two chapters: a presentation of what the centre offers to researchers and an interview with a renowned researcher who has benefited from the collaboration with the centre.\n\nThe volume would not have been possible without the contributions and dedication of the CLARIN national coordinators and user involvement coordinators, and centre representatives: Antonio Branco, João Silva, Erik Axelson, Eva Soroli, Nikola Ljubešić, Maria Gavriilidou, Martina Trognitz, and Jan Wieczorek.\n\nWe would also like to thank all the researchers who have kindly agreed to be interviewed for their time and invaluable insights: Pilar Barbosa, Jack Rueter, Thomas Gaillat, Zrinka Kolaković, Titika Dimitroulia, Peter Andorfer, Stephan Kurz, Martin Anton Müller, and Olga Czeranowska.", "series": "", "seriesNumber": "", "volume": "", "numberOfVolumes": "", "edition": "", "date": "11-01-2021", "publisher": "", "place": "", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "numPages": "", "ISBN": "978-90-829909-3-5", "DOI": "", "citationKey": "fiser-EtAl:2021:TourCLARINVolume", "url": "https://zenodo.org/record/7019259", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "Engish", "libraryCatalog": "zenodo.org", "callNumber": "", "rights": "", "extra": "https://doi.org/10.5281/zenodo.7019259\nCitation Key: fiser-EtAl:2021:TourCLARINVolume", "tags": [], "collections": [ "DIRMCTJC", "QRQ8RTX5" ], "relations": {}, "dateAdded": "2022-08-24T14:52:59Z", "dateModified": "2025-09-25T13:08:46Z" } }, { "key": "HUPFZLIW", "version": 8219, "library": { "type": "group", "id": 562080, "name": "CLARIN", "links": { "alternate": { "href": "https://www.zotero.org/groups/clarin", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/562080/items/HUPFZLIW", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/clarin/items/HUPFZLIW", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3167571, "username": "dietervu", "name": "Dieter Van Uytvanck", "links": { "alternate": { "href": "https://www.zotero.org/dietervu", "type": "text/html" } } }, "lastModifiedByUser": { "id": 332053, "username": "iiegn", "name": "egon stemle", "links": { "alternate": { "href": "https://www.zotero.org/iiegn", "type": "text/html" } } }, "creatorSummary": "Ecker et al.", "parsedDate": "2024", "numChildren": 0 }, "data": { "key": "HUPFZLIW", "version": 8219, "itemType": "journalArticle", "title": "Unlocking the Corpus: Enriching Metadata with State-of-the-Art NLP Methodology and Linked Data", "creators": [ { "creatorType": "author", "firstName": "Jennifer", "lastName": "Ecker" }, { "creatorType": "author", "firstName": "Stefan", "lastName": "Fischer" }, { "creatorType": "author", "firstName": "Pia", "lastName": "Schwarz" }, { "creatorType": "author", "firstName": "Thorsten", "lastName": "Trippel" }, { "creatorType": "author", "firstName": "Antonina", "lastName": "Werthmann" }, { "creatorType": "author", "firstName": "Rebecca", "lastName": "Wilm" } ], "abstractNote": "In research data management, metadata are indispensable to describing data and are a key element in preparing data according to the FAIR principles. Metadata in catalogues and registries are usually recorded either by archivists or subject matter experts, i.e. researchers involved in the creation or assembling of the data, or provided in the data preparation workflow. Extracting metadata from textual research data is currently not part of most metadata workflows, even more so if a research data set can be subdivided into smaller parts, such as a newspaper corpus containing multiple newspaper articles. If we look at descriptive metadata from a large corpus of newspapers, the basic metadata may consist of information, for example, about the title, or year of publication. Our  approach is to add semantic metadata on the text level to facilitate the search over data. We show how to enrich metadata with three methods: named entity recognition, keyword extraction, and topic modeling. The goal is to make it possible to searchfor texts that are about certain topics or described using certain keywords or to identify people, places, and organisations mentioned in texts without actually having to read them.", "publicationTitle": "CLARIN Annual Conference", "publisher": "", "place": "", "date": "2024", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "127-161", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.3384/ecp216.11", "citationKey": "ecker-EtAl:2024:UnlockingCorpusEnriching", "url": "https://ecp.ep.liu.se/index.php/clarin/article/view/1230", "accessDate": "2025-09-25T12:29:07Z", "PMID": "", "PMCID": "", "ISSN": "1650-3740", "archive": "", "archiveLocation": "", "shortTitle": "Unlocking the Corpus", "language": "en", "libraryCatalog": "ecp.ep.liu.se", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "DeReKo", "type": 1 }, { "tag": "German Reference Corpus", "type": 1 }, { "tag": "Keyword Extraction", "type": 1 }, { "tag": "Knowledge Base", "type": 1 }, { "tag": "NER", "type": 1 }, { "tag": "Named Entity Recognition", "type": 1 }, { "tag": "Semantic Metadata Enrichment", "type": 1 }, { "tag": "Topic Modeling", "type": 1 } ], "collections": [ "EIB3URH4" ], "relations": {}, "dateAdded": "2025-09-25T12:29:07Z", "dateModified": "2025-09-25T12:34:13Z" } }, { "key": "BMIQMX3P", "version": 8219, "library": { "type": "group", "id": 562080, "name": "CLARIN", "links": { "alternate": { "href": "https://www.zotero.org/groups/clarin", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/562080/items/BMIQMX3P", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/clarin/items/BMIQMX3P", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3167571, "username": "dietervu", "name": "Dieter Van Uytvanck", "links": { "alternate": { "href": "https://www.zotero.org/dietervu", "type": "text/html" } } }, "lastModifiedByUser": { "id": 332053, "username": "iiegn", "name": "egon stemle", "links": { "alternate": { "href": "https://www.zotero.org/iiegn", "type": "text/html" } } }, "creatorSummary": "Daza and Fokkens", "parsedDate": "2024", "numChildren": 0 }, "data": { "key": "BMIQMX3P", "version": 8219, "itemType": "journalArticle", "title": "Choosing the Right Tool for You: Informed Evaluation of Text Analysis Tools", "creators": [ { "creatorType": "author", "firstName": "Angel", "lastName": "Daza" }, { "creatorType": "author", "firstName": "Antske", "lastName": "Fokkens" } ], "abstractNote": "Natural Language Processing (NLP) research showcases many promising tools and methods for text analysis. Scholars from diverse fields who want to use NLP for their research are confronted with a wide availability of ready-to-use models that claim excellent performance on standard benchmarks. Consequently, choosing an appropriate tool has become a task on its own. Our goal is to exemplify a methodology that stimulates critical evaluation and detailed analysis of automatic outputs of NLP tools. Particularly, we analyze the case of choosing the best Named Entity Recognition (NER) tool for a corpus of Dutch biographies. Our use case is an example of how to make informed decisions by considering different aspects of custom datasets at the instance and aggregated levels, improving the outcomes of the original research question.", "publicationTitle": "CLARIN Annual Conference", "publisher": "", "place": "", "date": "2024", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "112-125", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.3384/ecp216.10", "citationKey": "daza-fokkens:2024:ChoosingRightTool", "url": "https://ecp.ep.liu.se/index.php/clarin/article/view/1234", "accessDate": "2025-09-25T12:28:58Z", "PMID": "", "PMCID": "", "ISSN": "1650-3740", "archive": "", "archiveLocation": "", "shortTitle": "Choosing the Right Tool for You", "language": "en", "libraryCatalog": "ecp.ep.liu.se", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Evaluation", "type": 1 }, { "tag": "Historical Corpora", "type": 1 }, { "tag": "Named Entity Recognition", "type": 1 } ], "collections": [ "EIB3URH4" ], "relations": {}, "dateAdded": "2025-09-25T12:28:58Z", "dateModified": "2025-09-25T12:34:04Z" } }, { "key": "J9R6ZTPB", "version": 8219, "library": { "type": "group", "id": 562080, "name": "CLARIN", "links": { "alternate": { "href": "https://www.zotero.org/groups/clarin", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/562080/items/J9R6ZTPB", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/clarin/items/J9R6ZTPB", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3167571, "username": "dietervu", "name": "Dieter Van Uytvanck", "links": { "alternate": { "href": "https://www.zotero.org/dietervu", "type": "text/html" } } }, "lastModifiedByUser": { "id": 332053, "username": "iiegn", "name": "egon stemle", "links": { "alternate": { "href": "https://www.zotero.org/iiegn", "type": "text/html" } } }, "creatorSummary": "Illig et al.", "parsedDate": "2024", "numChildren": 0 }, "data": { "key": "J9R6ZTPB", "version": 8219, "itemType": "journalArticle", "title": "Managing Access to Language Resources in a Corpus Analysis Platform", "creators": [ { "creatorType": "author", "firstName": "Eliza Margaretha", "lastName": "Illig" }, { "creatorType": "author", "firstName": "Nils", "lastName": "Diewald" }, { "creatorType": "author", "firstName": "Paweł", "lastName": "Kamocki" }, { "creatorType": "author", "firstName": "Marc", "lastName": "Kupietz" } ], "abstractNote": "\"Corpus query tools are crucial to CLARIN’s mission of facilitating the sharing and use of language data for research. It is a huge challenge for online corpus platforms to manage user access rights for large corpora with complex licenses and heterogeneous restrictions on access methods and purposes. This paper presents an approach to maximize user access to corpus data while protecting rights holders’ legitimate interests. Query rewriting techniques and authorization procedures allow for modelling license terms in detail, enabling broader applications. This offers an alternative to methods that only model a greatest common denominator of licenses, thereby limiting the possibilities for using the data. Our approach constitutes a flexible and extensible corpus license and user rights management component applicable for other language research environments.\"", "publicationTitle": "CLARIN Annual Conference", "publisher": "", "place": "", "date": "2024", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "100-111", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.3384/ecp216.09", "citationKey": "illig-EtAl:2024:ManagingAccessLanguage", "url": "https://ecp.ep.liu.se/index.php/clarin/article/view/1238", "accessDate": "2025-09-25T12:28:49Z", "PMID": "", "PMCID": "", "ISSN": "1650-3740", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "ecp.ep.liu.se", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "authorization", "type": 1 }, { "tag": "corpus access", "type": 1 }, { "tag": "license management", "type": 1 }, { "tag": "query rewriting", "type": 1 }, { "tag": "user rights management", "type": 1 } ], "collections": [ "EIB3URH4" ], "relations": {}, "dateAdded": "2025-09-25T12:28:49Z", "dateModified": "2025-09-25T12:34:00Z" } }, { "key": "UXREP4JB", "version": 8219, "library": { "type": "group", "id": 562080, "name": "CLARIN", "links": { "alternate": { "href": "https://www.zotero.org/groups/clarin", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/562080/items/UXREP4JB", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/clarin/items/UXREP4JB", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3167571, "username": "dietervu", "name": "Dieter Van Uytvanck", "links": { "alternate": { "href": "https://www.zotero.org/dietervu", "type": "text/html" } } }, "lastModifiedByUser": { "id": 332053, "username": "iiegn", "name": "egon stemle", "links": { "alternate": { "href": "https://www.zotero.org/iiegn", "type": "text/html" } } }, "creatorSummary": "Navarretta et al.", "parsedDate": "2024", "numChildren": 0 }, "data": { "key": "UXREP4JB", "version": 8219, "itemType": "journalArticle", "title": "Policy Domains and the Speakers' Gender in ParlaMint-DK 4.1", "creators": [ { "creatorType": "author", "firstName": "Costanza", "lastName": "Navarretta" }, { "creatorType": "author", "firstName": "Dorte Haltrup", "lastName": "Hansen" }, { "creatorType": "author", "firstName": "Bart", "lastName": "Jongejan" } ], "abstractNote": "In this paper, we describe the ParlaMint-DK 4.1 corpus, which consists of the Danish parliament speeches from 2014 to 2022 annotated with 20 general policy domains mapped to the codebook of the Comparative Agendas Project. The policy domains were added to the speeches semiautomatically using the agenda titles under which the speeches occurred. In the paper, we also account for how some of the linguistic annotations of the corpus were improved using the Text Tonsorium and present some of our previous studies on parliament data. We also describe novwl investigations, based on the policy domain annotations in ParlaMint-DK aimed at determining which domains are most frequently addressed in the speeches, and the frequency by which policy areas are debated by female and male politicians during the various governments covered by the corpus.", "publicationTitle": "CLARIN Annual Conference", "publisher": "", "place": "", "date": "2024", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "86-99", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.3384/ecp216.08", "citationKey": "navarretta-EtAl:2024:PolicyDomainsSpeakers", "url": "https://ecp.ep.liu.se/index.php/clarin/article/view/1231", "accessDate": "2025-09-25T12:28:42Z", "PMID": "", "PMCID": "", "ISSN": "1650-3740", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "ecp.ep.liu.se", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Gender Differences", "type": 1 }, { "tag": "Parliament Corpus", "type": 1 }, { "tag": "Policy Domains", "type": 1 } ], "collections": [ "EIB3URH4" ], "relations": {}, "dateAdded": "2025-09-25T12:28:42Z", "dateModified": "2025-09-25T12:33:54Z" } }, { "key": "FPEDCPGD", "version": 8219, "library": { "type": "group", "id": 562080, "name": "CLARIN", "links": { "alternate": { "href": "https://www.zotero.org/groups/clarin", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/562080/items/FPEDCPGD", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/clarin/items/FPEDCPGD", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3167571, "username": "dietervu", "name": "Dieter Van Uytvanck", "links": { "alternate": { "href": "https://www.zotero.org/dietervu", "type": "text/html" } } }, "lastModifiedByUser": { "id": 332053, "username": "iiegn", "name": "egon stemle", "links": { "alternate": { "href": "https://www.zotero.org/iiegn", "type": "text/html" } } }, "creatorSummary": "Zinn and Trippel", "parsedDate": "2024", "numChildren": 0 }, "data": { "key": "FPEDCPGD", "version": 8219, "itemType": "journalArticle", "title": "On the Successful Migration of Research Data", "creators": [ { "creatorType": "author", "firstName": "Claus", "lastName": "Zinn" }, { "creatorType": "author", "firstName": "Thorsten", "lastName": "Trippel" } ], "abstractNote": "More than five years ago, we crafted a detailed scenario for migrating our research data from our locally-maintained, departmental repository to an external, institutional repository for which we had only little control over. Now, with the rising cost of updating and maintaining our repository software to the latest version, personnel fluctuation, and the opportunity to use data services of a newly founded Digital Humanities Center, we decided to put into practise the scenario step by step. This paper describes the actual challenges we encountered in the migration process, the deviations from the original scenario and the compromises we needed to make, and finally, how we succeeded to get all data transferred in a safe and information-preserving manner.", "publicationTitle": "CLARIN Annual Conference", "publisher": "", "place": "", "date": "2024", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "60-70", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.3384/ecp216.06", "citationKey": "zinn-trippel:2024:SuccessfulMigrationResearch", "url": "https://ecp.ep.liu.se/index.php/clarin/article/view/1239", "accessDate": "2025-09-25T12:28:18Z", "PMID": "", "PMCID": "", "ISSN": "1650-3740", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "ecp.ep.liu.se", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "migration of research data", "type": 1 }, { "tag": "repository", "type": 1 }, { "tag": "research data management", "type": 1 } ], "collections": [ "EIB3URH4" ], "relations": {}, "dateAdded": "2025-09-25T12:28:18Z", "dateModified": "2025-09-25T12:33:49Z" } }, { "key": "W2FYZ58E", "version": 8219, "library": { "type": "group", "id": 562080, "name": "CLARIN", "links": { "alternate": { "href": "https://www.zotero.org/groups/clarin", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/562080/items/W2FYZ58E", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/clarin/items/W2FYZ58E", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3167571, "username": "dietervu", "name": "Dieter Van Uytvanck", "links": { "alternate": { "href": "https://www.zotero.org/dietervu", "type": "text/html" } } }, "lastModifiedByUser": { "id": 332053, "username": "iiegn", "name": "egon stemle", "links": { "alternate": { "href": "https://www.zotero.org/iiegn", "type": "text/html" } } }, "creatorSummary": "Körner et al.", "parsedDate": "2024", "numChildren": 0 }, "data": { "key": "W2FYZ58E", "version": 8219, "itemType": "journalArticle", "title": "An Enhanced Federated Content Search Infrastructure for the Humanities and Social Sciences", "creators": [ { "creatorType": "author", "firstName": "Erik", "lastName": "Körner" }, { "creatorType": "author", "firstName": "Thomas", "lastName": "Eckart" }, { "creatorType": "author", "firstName": "Felix", "lastName": "Helfer" }, { "creatorType": "author", "firstName": "Uwe", "lastName": "Kretschmer" } ], "abstractNote": "The general idea and implementation of a federated search infrastructure component that allows querying both full text resources and their linguistic annotations is a prominent part of the CLARIN project and is closely interconnected with the other components of its decentralised European-scale research data infrastructure. Since its beginnings, the Federated Content Search (FCS) has been continuously improved and by now fulfils its original goals that were formulated more than 12 years ago. During the last years, development of the FCS has accelerated massively with newly formulated application scenarios, newly opened up user groups and newly developed tools and user interfaces. This paper gives a summary of the developments of recent years and the topics that are currently being worked on. In addition to the further development of existing modules, this includes in particular the consideration and implementation of new requirements reflecting a rapidly evolving research infrastructure landscape.", "publicationTitle": "CLARIN Annual Conference", "publisher": "", "place": "", "date": "2024", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "49-59", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.3384/ecp216.05", "citationKey": "korner-EtAl:2024:EnhancedFederatedContent", "url": "https://ecp.ep.liu.se/index.php/clarin/article/view/1232", "accessDate": "2025-09-25T12:28:07Z", "PMID": "", "PMCID": "", "ISSN": "1650-3740", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "ecp.ep.liu.se", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "AAI", "type": 1 }, { "tag": "Entity-oriented search", "type": 1 }, { "tag": "Federated Content Search", "type": 1 }, { "tag": "Fonts", "type": 1 }, { "tag": "Information Retrieval", "type": 1 }, { "tag": "Lexical Resources", "type": 1 }, { "tag": "Search infrastructure", "type": 1 } ], "collections": [ "EIB3URH4" ], "relations": {}, "dateAdded": "2025-09-25T12:28:07Z", "dateModified": "2025-09-25T12:33:45Z" } }, { "key": "R76GBNDM", "version": 8220, "library": { "type": "group", "id": 562080, "name": "CLARIN", "links": { "alternate": { "href": "https://www.zotero.org/groups/clarin", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/562080/items/R76GBNDM", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/clarin/items/R76GBNDM", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3167571, "username": "dietervu", "name": "Dieter Van Uytvanck", "links": { "alternate": { "href": "https://www.zotero.org/dietervu", "type": "text/html" } } }, "lastModifiedByUser": { "id": 332053, "username": "iiegn", "name": "egon stemle", "links": { "alternate": { "href": "https://www.zotero.org/iiegn", "type": "text/html" } } }, "creatorSummary": "Pedonese et al.", "parsedDate": "2024", "numChildren": 0 }, "data": { "key": "R76GBNDM", "version": 8220, "itemType": "journalArticle", "title": "Adapting UPSKILLS Learning Modules to the University Curricula: Best Practices and Lessons Learnt from the H2IOSC Training Experience at the University of Ferrara", "creators": [ { "creatorType": "author", "firstName": "Giulia", "lastName": "Pedonese" }, { "creatorType": "author", "firstName": "Francesca", "lastName": "Frontini" }, { "creatorType": "author", "firstName": "Dario Del", "lastName": "Fante" }, { "creatorType": "author", "firstName": "Eleonora", "lastName": "Federici" } ], "abstractNote": "This paper details the steps taken to adapt and integrate the training materials developed by CLARIN ERIC in two bachelor’s degree courses and one master’s degree course at the University of Ferrara. The workflow applies the shared methodology developed within the Humanities and Heritage Italian Open Science Cloud project. It modifies the training materials of the UPSKILLS course “Introduction to Language Data: Standards and Repositories” according to the needs of three target courses focusing on English to Italian translation: English Language Course for Tourism, English Language for Translation and English Language and Linguistics for Humanities, Arts and Archaeology. The result of this pilot is a documented example of how CLARIN services can be integrated into university teaching, including initial teacher training, and providing an opportunity to discuss the topic and a use case for trainers who intend to include CLARIN in their courses.", "publicationTitle": "CLARIN Annual Conference", "publisher": "", "place": "", "date": "2024", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "37-47", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.3384/ecp216.04", "citationKey": "pedonese-EtAl:2024:AdaptingUPSKILLSLearning", "url": "https://ecp.ep.liu.se/index.php/clarin/article/view/1236", "accessDate": "2025-09-25T12:27:58Z", "PMID": "", "PMCID": "", "ISSN": "1650-3740", "archive": "", "archiveLocation": "", "shortTitle": "Adapting UPSKILLS Learning Modules to the University Curricula", "language": "en", "libraryCatalog": "ecp.ep.liu.se", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "FAIR principles", "type": 1 }, { "tag": "Language Data", "type": 1 }, { "tag": "Learning resources", "type": 1 }, { "tag": "Research Infrastructures", "type": 1 }, { "tag": "Training", "type": 1 } ], "collections": [ "EIB3URH4" ], "relations": {}, "dateAdded": "2025-09-25T12:27:58Z", "dateModified": "2025-09-25T12:33:39Z" } }, { "key": "ACEH8M6N", "version": 8220, "library": { "type": "group", "id": 562080, "name": "CLARIN", "links": { "alternate": { "href": "https://www.zotero.org/groups/clarin", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/562080/items/ACEH8M6N", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/clarin/items/ACEH8M6N", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3167571, "username": "dietervu", "name": "Dieter Van Uytvanck", "links": { "alternate": { "href": "https://www.zotero.org/dietervu", "type": "text/html" } } }, "lastModifiedByUser": { "id": 332053, "username": "iiegn", "name": "egon stemle", "links": { "alternate": { "href": "https://www.zotero.org/iiegn", "type": "text/html" } } }, "creatorSummary": "Ahltorp and Skeppstedt", "parsedDate": "2024", "numChildren": 0 }, "data": { "key": "ACEH8M6N", "version": 8220, "itemType": "journalArticle", "title": "Word Rain as a Service: Making semantically structured word clouds available to everyone", "creators": [ { "creatorType": "author", "firstName": "Magnus", "lastName": "Ahltorp" }, { "creatorType": "author", "firstName": "Maria", "lastName": "Skeppstedt" } ], "abstractNote": "The Word Rain text visualisation technique is a novel approach to the classic word cloud that uses word embeddings to make the visualisation useful for exploring the word content of a text or corpus. Downloading and running code for generating word rain visualisations can, however, be prohibitively difficult or cumbersome for non-technical users and for casual evaluation. These use cases would consequently benefit greatly from a streamlined interface. We have therefore collected everything needed for generating word rain visualisations in a web-based service, and made it available as a SWELANG CLARIN K-centre resource. The web service, as well as the code for generating word rains, is made available as open source. The web service is deployed at: https://wordrain.isof.se.", "publicationTitle": "CLARIN Annual Conference", "publisher": "", "place": "", "date": "2024", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "25-36", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.3384/ecp216.03", "citationKey": "ahltorp-skeppstedt:2024:WordRainService", "url": "https://ecp.ep.liu.se/index.php/clarin/article/view/1235", "accessDate": "2025-09-25T12:27:45Z", "PMID": "", "PMCID": "", "ISSN": "1650-3740", "archive": "", "archiveLocation": "", "shortTitle": "Word Rain as a Service", "language": "en", "libraryCatalog": "ecp.ep.liu.se", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "swelang", "type": 1 }, { "tag": "text visualisation", "type": 1 }, { "tag": "word cloud", "type": 1 }, { "tag": "word rain", "type": 1 } ], "collections": [ "EIB3URH4" ], "relations": {}, "dateAdded": "2025-09-25T12:27:45Z", "dateModified": "2025-09-25T12:33:30Z" } }, { "key": "N6INDBSV", "version": 8220, "library": { "type": "group", "id": 562080, "name": "CLARIN", "links": { "alternate": { "href": "https://www.zotero.org/groups/clarin", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/562080/items/N6INDBSV", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/clarin/items/N6INDBSV", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3167571, "username": "dietervu", "name": "Dieter Van Uytvanck", "links": { "alternate": { "href": "https://www.zotero.org/dietervu", "type": "text/html" } } }, "lastModifiedByUser": { "id": 332053, "username": "iiegn", "name": "egon stemle", "links": { "alternate": { "href": "https://www.zotero.org/iiegn", "type": "text/html" } } }, "creatorSummary": "Steingrímsson and Sigurðsson", "parsedDate": "2024", "numChildren": 0 }, "data": { "key": "N6INDBSV", "version": 8220, "itemType": "journalArticle", "title": "Evaluating Capabilities of MT Systems in Translating Idiomatic Expressions Using a Specialized Dataset", "creators": [ { "creatorType": "author", "firstName": "Steinþór", "lastName": "Steingrímsson" }, { "creatorType": "author", "firstName": "Einar Freyr", "lastName": "Sigurðsson" } ], "abstractNote": "Multiword expressions (MWEs) are generally problematic for machine-translation systems. In this paper, we (i) describe a set, available on CLARIN-IS, of appr. 1,000 idiomatic MWEs which have been translated into English; (ii) use the set as a template for a hidden evaluation set, to be used in a new leaderboard for Icelandic language technology, and (iii) evaluate -- using both automatic and manual approaches -- four MT systems' abilities to translate MWEs from Icelandic to English using both datasets. We find that traditional transformer-based MT systems evaluated commonly fail when translating idiomatic expressions, while LLMs do much better.", "publicationTitle": "CLARIN Annual Conference", "publisher": "", "place": "", "date": "2024", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "13-24", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.3384/ecp216.02", "citationKey": "steingrimsson-sigurdsson:2024:EvaluatingCapabilitiesMT", "url": "https://ecp.ep.liu.se/index.php/clarin/article/view/1242", "accessDate": "2025-09-25T12:26:54Z", "PMID": "", "PMCID": "", "ISSN": "1650-3740", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "ecp.ep.liu.se", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Evaluation", "type": 1 }, { "tag": "Idiomatic Expressions", "type": 1 }, { "tag": "Idioms", "type": 1 }, { "tag": "MT Evaluation", "type": 1 }, { "tag": "Machine Translation", "type": 1 }, { "tag": "Multiword Expressions", "type": 1 } ], "collections": [ "EIB3URH4" ], "relations": {}, "dateAdded": "2025-09-25T12:26:54Z", "dateModified": "2025-09-25T12:33:19Z" } }, { "key": "YUMTKDYW", "version": 8220, "library": { "type": "group", "id": 562080, "name": "CLARIN", "links": { "alternate": { "href": "https://www.zotero.org/groups/clarin", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/562080/items/YUMTKDYW", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/clarin/items/YUMTKDYW", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3167571, "username": "dietervu", "name": "Dieter Van Uytvanck", "links": { "alternate": { "href": "https://www.zotero.org/dietervu", "type": "text/html" } } }, "lastModifiedByUser": { "id": 332053, "username": "iiegn", "name": "egon stemle", "links": { "alternate": { "href": "https://www.zotero.org/iiegn", "type": "text/html" } } }, "creatorSummary": "Wissik", "parsedDate": "2024", "numChildren": 0 }, "data": { "key": "YUMTKDYW", "version": 8220, "itemType": "journalArticle", "title": "An Infrastructural Approach to Terminology Work: The Case of Research Infrastructures", "creators": [ { "creatorType": "author", "firstName": "Tanja", "lastName": "Wissik" } ], "abstractNote": "This study explores the role of research infrastructures,in particular the role of CLARIN and DARIAH, with regard toterminology work in institutional settings (academic andnon-academic) by analyzing a body of qualitative interviewdata, collected in 2023 across Europe. The contribu-tionalso discusses how research infrastructures (RIs) couldreach out to new non-academic communities e.g., in thepublic sector.", "publicationTitle": "CLARIN Annual Conference", "publisher": "", "place": "", "date": "2024", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "1-12", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.3384/ecp216.01", "citationKey": "wissik:2024:InfrastructuralApproachTerminology", "url": "https://ecp.ep.liu.se/index.php/clarin/article/view/1241", "accessDate": "2025-09-25T12:26:06Z", "PMID": "", "PMCID": "", "ISSN": "1650-3740", "archive": "", "archiveLocation": "", "shortTitle": "An Infrastructural Approach to Terminology Work", "language": "en", "libraryCatalog": "ecp.ep.liu.se", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Research Infastructures", "type": 1 }, { "tag": "non-academic users", "type": 1 }, { "tag": "terminology work", "type": 1 }, { "tag": "user groups", "type": 1 }, { "tag": "user study", "type": 1 } ], "collections": [ "EIB3URH4" ], "relations": {}, "dateAdded": "2025-09-25T12:26:06Z", "dateModified": "2025-09-25T12:33:14Z" } }, { "key": "KYYYZSR9", "version": 8220, "library": { "type": "group", "id": 562080, "name": "CLARIN", "links": { "alternate": { "href": "https://www.zotero.org/groups/clarin", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/562080/items/KYYYZSR9", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/clarin/items/KYYYZSR9", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3167571, "username": "dietervu", "name": "Dieter Van Uytvanck", "links": { "alternate": { "href": "https://www.zotero.org/dietervu", "type": "text/html" } } }, "lastModifiedByUser": { "id": 332053, "username": "iiegn", "name": "egon stemle", "links": { "alternate": { "href": "https://www.zotero.org/iiegn", "type": "text/html" } } }, "creatorSummary": "Gompel and Windhouwer", "parsedDate": "2024", "numChildren": 0 }, "data": { "key": "KYYYZSR9", "version": 8220, "itemType": "journalArticle", "title": "FAIR Tool Discovery: an automated software metadata harvesting pipeline for CLARIAH", "creators": [ { "creatorType": "author", "firstName": "Maarten van", "lastName": "Gompel" }, { "creatorType": "author", "firstName": "Menzo", "lastName": "Windhouwer" } ], "abstractNote": "We present the Tool Discovery pipeline, a core component of the CLARIAH infrastructure in the Netherlands. This pipeline harvests software metadata from the source, detects existing heterogeneous metadata formats already in use by software developers, and converts them to a single uniform representation based on schema.org and codemeta. The resulting data is then made available for further ingestion into other user-facing catalogue/portal systems.", "publicationTitle": "CLARIN Annual Conference", "publisher": "", "place": "", "date": "2024", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "141-150", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.3384/ecp216.12", "citationKey": "gompel-windhouwer:2024:FAIRToolDiscovery", "url": "https://ecp.ep.liu.se/index.php/clarin/article/view/1233", "accessDate": "2025-09-25T12:29:15Z", "PMID": "", "PMCID": "", "ISSN": "1650-3740", "archive": "", "archiveLocation": "", "shortTitle": "FAIR Tool Discovery", "language": "en", "libraryCatalog": "ecp.ep.liu.se", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "linked open data", "type": 1 }, { "tag": "metadata harvesting", "type": 1 }, { "tag": "software metadata", "type": 1 } ], "collections": [ "EIB3URH4" ], "relations": {}, "dateAdded": "2025-09-25T12:29:15Z", "dateModified": "2025-09-25T12:32:51Z" } } ]