Iztok Kosem
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Iztok Kosem has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Špela Arhar Holdt
University of Ljubljana, Slovenia
4 shared publications - Carole Tiberius
Dutch Language Institute
2 shared publications - Kristina Koppel
Eesti Keele Instituut / Institute of the Estonian Language
2 shared publications - Tanara Zingano Kuhn
Centre for General and Applied Linguistics Studies (CELGA-ILTEC), University of Coimbra
2 shared publications - Ana R. Luis
Universidade de Coimbra
1 shared publication - Branislava Šandrih Todorović
Faculty of Philology, University of Belgrade, Studentski Trg 3, 11000 Belgrade, Serbia
1 shared publication
Latest Publications
- Open Access
- 22 December 2025
- Published by Institut za novejso zgodovino in Contributions to Contemporary History
- Vol. 65 (3)
Potencial ChatGPT pri razvoju Slovarja sopomenk sodobne slovenščine
In this study, we examine how well ChatGPT-4 performs in two lexicographic tasks: (a) cleaning the list of automatically retrieved synonym candidates and assigning synonymic material to lexical senses, and (b) generating dictionary entries, including sense division, definitions, and examples, based on different input data. As a gold standard, we consider the lexicographic decisions recorded in the Digital Dictionary Database for Slovene. In the first experiment, we analyse the results for 246 dictionary entries and find that ChatGPT processed the data identically to lexicographers in 41.9 % of cases, while in 58.1 % of cases, it made different decisions. When assessing the relevance of synonym candidates, ChatGPT was more permissive than the gold standard. Differences in synonym placement (assignment to a different sense in 14.6 % of entries, missing placement in 19.9 %) can be partly attributed to input data characteristics, such as task complexity and the brevity of semantic indicators. In the second experiment, we test ChatGPT’s ability to autonomously generate dictionary entries for 116 headwords. The analysis of generated sense divisions and definitions reveals that the system performs moderately well: in 57 % of cases, it identified all senses, almost 80 % of generated entries received an average score of 3.5 or higher, and 19 % received the highest score from both evaluators. The main challenges include excessive splitting of senses, failure to recognise figurative meanings, and reduced predictability of results. We conclude that ChatGPT has potential for speeding up manual lexicographic work if its results are properly monitored and refined.
- 22 December 2025
- Published by Institut za novejso zgodovino in Contributions to Contemporary History
- Vol. 65 (3)
Open AccessPotencial ChatGPT pri razvoju Slovarja sopomenk sodobne slovenščine
In this study, we examine how well ChatGPT-4 performs in two lexicographic tasks: (a) cleaning the list of automatically retrieved synonym candidates and assigning synonymic material to lexical senses, and (b) generating dictionary entries, including sense division, definitions, and examples, based on different input data. As a gold standard, we consider the lexicographic decisions recorded in the Digital Dictionary Database for Slovene. In the first experiment, we analyse the results for 246 dictionary entries and find that ChatGPT processed the data identically to lexicographers in 41.9 % of cases, while in 58.1 % of cases, it made different decisions. When assessing the relevance of synonym candidates, ChatGPT was more permissive than the gold standard. Differences in synonym placement (assignment to a different sense in 14.6 % of entries, missing placement in 19.9 %) can be partly attributed to input data characteristics, such as task complexity and the brevity of semantic indicators. In the second experiment, we test ChatGPT’s ability to autonomously generate dictionary entries for 116 headwords. The analysis of generated sense divisions and definitions reveals that the system performs moderately well: in 57 % of cases, it identified all senses, almost 80 % of generated entries received an average score of 3.5 or higher, and 19 % received the highest score from both evaluators. The main challenges include excessive splitting of senses, failure to recognise figurative meanings, and reduced predictability of results. We conclude that ChatGPT has potential for speeding up manual lexicographic work if its results are properly monitored and refined.
- Open Access
- 14 December 2025
- Published by Elsevier in Journal of Responsible Technology
- Vol. 25
Corplus: A new concordancer for exploring authentic texts with language corrections
- 14 December 2025
- Published by Elsevier in Journal of Responsible Technology
- Vol. 25
Open AccessCorplus: A new concordancer for exploring authentic texts with language corrections
- Open Access
- 31 October 2025
- Published by Zveza društev pedagoških delavcev Slovenije in Sodobna Pedagogika
- Vol. 76 (3) , 9-38
Prvi koraki do seznama temeljnega šolskega besedišča
V prispevku obravnavamo izdelavo seznama temeljnega šolskega besedišča za slovenski jezik, ki bi bil primerljiv s podobnimi seznami, kot jih poznamo za angleščino in druge jezike. Takšni seznami ne služijo le za izboljšavo učnih gradiv in jezikovnih orodij za slovenščino, temveč lahko prispevajo tudi k nadgradnji učnih gradiv za druge predmete in k oblikovanju učnih ciljev. V uvodnem delu najprej ponudimo pregled obstoječih seznamov besed za tuje jezike, nato pa predstavimo relevantne obstoječe sezname za slovenščino, s poudarkom na referenčnem seznamu splošnega besedišča in dveh seznamih učbeniškega besedišča. Sledi podrobna predstavitev relevantnih aktualnih korpusnih virov na področju slovenščine v šolskem okolju. Nato izvedemo analizo obstoječih seznamov besed za slovenščino, v kateri jih primerjamo med sabo in s seznami besed iz relevantnih korpusov, pri čemer preučujemo skladnosti in razlike v zajetju ključnih besed. Izkaže se, da ima vsak seznam določene pomanjkljivosti, poleg tega pa je treba upoštevati razliko med recepcijo in produkcijo. Opravimo tudi diahrono analizo izbranega vzorca besed iz korpusov učbenikov in šolskih izdelkov, ki razkrije spremembe v rabi besed ne zgolj na časovni, temveč tudi na pomenski ravni. V zaključku povzamemo glavne ugotovitve raziskave in izpostavimo predloge za nadaljnje raziskave, ki bi lahko prispevale k izdelavi celovitega in funkcionalnega seznama temeljnega šolskega besedišča za slovenski jezik.
- 31 October 2025
- Published by Zveza društev pedagoških delavcev Slovenije in Sodobna Pedagogika
- Vol. 76 (3) , 9-38
Open AccessPrvi koraki do seznama temeljnega šolskega besedišča
V prispevku obravnavamo izdelavo seznama temeljnega šolskega besedišča za slovenski jezik, ki bi bil primerljiv s podobnimi seznami, kot jih poznamo za angleščino in druge jezike. Takšni seznami ne služijo le za izboljšavo učnih gradiv in jezikovnih orodij za slovenščino, temveč lahko prispevajo tudi k nadgradnji učnih gradiv za druge predmete in k oblikovanju učnih ciljev. V uvodnem delu najprej ponudimo pregled obstoječih seznamov besed za tuje jezike, nato pa predstavimo relevantne obstoječe sezname za slovenščino, s poudarkom na referenčnem seznamu splošnega besedišča in dveh seznamih učbeniškega besedišča. Sledi podrobna predstavitev relevantnih aktualnih korpusnih virov na področju slovenščine v šolskem okolju. Nato izvedemo analizo obstoječih seznamov besed za slovenščino, v kateri jih primerjamo med sabo in s seznami besed iz relevantnih korpusov, pri čemer preučujemo skladnosti in razlike v zajetju ključnih besed. Izkaže se, da ima vsak seznam določene pomanjkljivosti, poleg tega pa je treba upoštevati razliko med recepcijo in produkcijo. Opravimo tudi diahrono analizo izbranega vzorca besed iz korpusov učbenikov in šolskih izdelkov, ki razkrije spremembe v rabi besed ne zgolj na časovni, temveč tudi na pomenski ravni. V zaključku povzamemo glavne ugotovitve raziskave in izpostavimo predloge za nadaljnje raziskave, ki bi lahko prispevale k izdelavi celovitega in funkcionalnega seznama temeljnega šolskega besedišča za slovenski jezik.
- Open Access
- 18 July 2024
- Published by Springer Nature in Language Resources and Evaluation
- Vol. 59 (2) , 1151-1177
Šolar, the developmental corpus of Slovene
The paper presents the Šolar developmental corpus of Slovene, comprising the written language production of students in Slovene elementary and secondary schools, along with teacher feedback. The corpus consists of 5485 texts (1,635,407 words) and includes linguistically categorized teacher corrections, making the corpus unique in reflecting authentic classroom correction practices. The paper addresses the corpus compilation, content and format, annotation, availability, and its applicative value. While learner corpora are abundant, developmental corpora are less common. The paper bridges the gap by introducing the evolution from Šolar 1.0 to 3.0, emphasizing improvements in text collection, error and correction annotation, and categorization methodology. It also underlines the challenges and unresolved issues of compiling developmental corpora, most notably the lack of openly available tools and standards for different steps of the compilation process. Overall, the Šolar corpus offers valuable insights into language learning and teaching, contributing to teacher training, empirical studies in applied linguistics, and natural language processing tasks.
- 18 July 2024
- Published by Springer Nature in Language Resources and Evaluation
- Vol. 59 (2) , 1151-1177
Open AccessŠolar, the developmental corpus of Slovene
The paper presents the Šolar developmental corpus of Slovene, comprising the written language production of students in Slovene elementary and secondary schools, along with teacher feedback. The corpus consists of 5485 texts (1,635,407 words) and includes linguistically categorized teacher corrections, making the corpus unique in reflecting authentic classroom correction practices. The paper addresses the corpus compilation, content and format, annotation, availability, and its applicative value. While learner corpora are abundant, developmental corpora are less common. The paper bridges the gap by introducing the evolution from Šolar 1.0 to 3.0, emphasizing improvements in text collection, error and correction annotation, and categorization methodology. It also underlines the challenges and unresolved issues of compiling developmental corpora, most notably the lack of openly available tools and standards for different steps of the compilation process. Overall, the Šolar corpus offers valuable insights into language learning and teaching, contributing to teacher training, empirical studies in applied linguistics, and natural language processing tasks.
- Open Access
- 13 December 2021
- Published by Research-Publishing.net
- p. 312-317
Developing pedagogically appropriate language corpora through crowdsourcing and gamification
Despite the unquestionable academic interest on corpus-based approaches to language education, the use of corpora by teachers in their everyday practice is still not very widespread. One way to promote usage of corpora in language teaching is by making pedagogically appropriate corpora, labelled with different types of problems (for instance, sensitive content, offensive language, structural problems), so that teachers can select authentic examples according to their needs. Because manually labelling corpora is extremely time-consuming, we propose to use crowdsourcing for this task. After a first exploratory phase, we are currently developing a multimode, multilanguage game in which players first identify problematic sentences and then classify them.
- 13 December 2021
- Published by Research-Publishing.net
- p. 312-317
Open AccessDeveloping pedagogically appropriate language corpora through crowdsourcing and gamification
Despite the unquestionable academic interest on corpus-based approaches to language education, the use of corpora by teachers in their everyday practice is still not very widespread. One way to promote usage of corpora in language teaching is by making pedagogically appropriate corpora, labelled with different types of problems (for instance, sensitive content, offensive language, structural problems), so that teachers can select authentic examples according to their needs. Because manually labelling corpora is extremely time-consuming, we propose to use crowdsourcing for this task. After a first exploratory phase, we are currently developing a multimode, multilanguage game in which players first identify problematic sentences and then classify them.
- 17 August 2018
- Published by Oxford University Press (OUP) in International Journal of Lexicography
- Vol. 32 (2) , 119-137
Identification and automatic extraction of good dictionary examples: the case(s) of GDEX
- 17 August 2018
- Published by Oxford University Press (OUP) in International Journal of Lexicography
- Vol. 32 (2) , 119-137
Identification and automatic extraction of good dictionary examples: the case(s) of GDEX