{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T16:29:13Z","timestamp":1771518553274,"version":"3.50.1"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Projects \u201cEmbeddings-Based Techniques for Media Monitoring Applications\u201d co-funded by the Kliping d.o.o. Agency and the Slovenian Research and Innovation Agency","award":["L2-50070"],"award-info":[{"award-number":["L2-50070"]}]},{"name":"\u201cLarge Language Models for Digital Humanities\u201d funded by ARIS","award":["GC-0002"],"award-info":[{"award-number":["GC-0002"]}]},{"name":"Research Programme \u201cLanguage Resources and Technologies for Slovene\u201d funded by ARIS","award":["P6-0411"],"award-info":[{"award-number":["P6-0411"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3544814","type":"journal-article","created":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T18:41:32Z","timestamp":1740422492000},"page":"35621-35633","source":"Crossref","is-referenced-by-count":10,"title":["LLM Teacher-Student Framework for Text Classification With No Manually Annotated Data: A Case Study in IPTC News Topic Classification"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7436-9896","authenticated-orcid":false,"given":"Taja","family":"Kuzman","sequence":"first","affiliation":[{"name":"Department of Knowledge Technologies, Jožef Stefan Institute, Ljubljana, Slovenia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7169-9152","authenticated-orcid":false,"given":"Nikola","family":"Ljube\u0161i\u0107","sequence":"additional","affiliation":[{"name":"Department of Knowledge Technologies, Jožef Stefan Institute, Ljubljana, Slovenia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/make5030059"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.77"},{"issue":"240","key":"ref3","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref4","volume-title":"Media Topics","year":"2024"},{"key":"ref5","first-page":"301","article-title":"MaCoCu: Massive collection and curation of monolingual and bilingual data: Focus on under-resourced languages","volume-title":"Proc. 23rd Annu. Conf. Eur. Assoc. Mach. Transl.","author":"Ba\u00f1\u00f3n"},{"key":"ref6","volume-title":"NewsCodes","year":"2024"},{"key":"ref7","volume-title":"What is IPTC, ?","year":"2024"},{"key":"ref8","volume-title":"Groups of NewsCodes","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v15i1.18127"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCITechn.2014.6997369"},{"key":"ref11","first-page":"25","article-title":"An evaluation of BERT and Doc2Vec model on the IPTC subject codes prediction dataset","volume-title":"Proc. 24th Int. Multiconference Inf. Soc., Data Mining Data Warehouses Conf.","author":"Pranjic"},{"key":"ref12","article-title":"News category dataset","author":"Misra","year":"2022","journal-title":"arXiv:2209.11429"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.4312\/slo2.0.2023.1.161-188"},{"key":"ref14","article-title":"Distributed representations of words and phrases and their compositionality","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Mikolov"},{"key":"ref15","volume-title":"Finnish News Agency Archive 1992\u20132018, Source","year":"2024"},{"key":"ref16","volume-title":"NewsCodes Guidelines","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/data8050074"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-022-09623-2"},{"key":"ref19","first-page":"37","article-title":"News topic classification as a first step towards diverse news recommendation","volume":"10","author":"Clercq","year":"2020","journal-title":"Comput. Linguistics Netherlands J."},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3345414"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v13i01.3261"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.vardial-1.7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3543873.3587368"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.54"},{"key":"ref25","article-title":"Learning reward for robot skills using large language models via self-alignment","author":"Zeng","year":"2024","journal-title":"arXiv:2405.07162"},{"key":"ref26","first-page":"2511","article-title":"Principle-driven self-alignment of language models from scratch with minimal human supervision","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Sun"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.626"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.235"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.385"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.754"},{"key":"ref31","first-page":"462","article-title":"Generating training data with language models: Towards zero-shot language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Meng"},{"key":"ref32","first-page":"5221","article-title":"Do language models care about text quality? Evaluating web-crawled corpora across 11 languages","volume-title":"Proc. Joint Int. Conf. Comput. Linguistics, Lang. Resour. Eval.","author":"van Noord"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.vardial-1.9"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.vardial-1.18"},{"key":"ref35","volume-title":"Hello GPT-4o","year":"2024"},{"key":"ref36","volume-title":"Catalan Web Corpus MaCoCu-Ca 1.0","author":"Ba\u00f1\u00f3n","year":"2023"},{"key":"ref37","volume-title":"Croatian Web Corpus MaCoCu-HR 2.0","author":"Ba\u00f1\u00f3n","year":"2023"},{"key":"ref38","volume-title":"Greek Web Corpus MaCoCu-EL 1.0","author":"Ba\u00f1\u00f3n","year":"2023"},{"key":"ref39","volume-title":"Slovene Web Corpus MaCoCu-SL 2.0","author":"Ba\u00f1\u00f3n","year":"2023"},{"key":"ref40","volume-title":"Genre-enriched Web Corpora MaCoCu-Genre","author":"Kuzman","year":"2024"},{"key":"ref41","volume-title":"Multilingual Text Genre Classification Model X-GENRE","author":"Kuzman","year":"2023"},{"key":"ref42","volume-title":"Multilingual IPTC Media Topic Dataset EMMediaTopic 1.0","author":"Kuzman","year":"2024"},{"key":"ref43","volume-title":"IPTC Media Topic NewsCodes Tree View","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.4135\/9781071878781"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11135-004-8107-7"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00516"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-023-09695-8"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1080\/19312458.2020.1869198"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1080\/19312458.2017.1317338"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3390\/app10175993"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.aacl-main.91"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-27947-9_9"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12752"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"ref55","article-title":"Evaluation of contextual embeddings on less-resourced languages","author":"Ul\u010dar","year":"2021","journal-title":"arXiv:2107.10614"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10900365.pdf?arnumber=10900365","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T18:35:05Z","timestamp":1741026905000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10900365\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3544814","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}