Multilingual Word Embedding and Linguistic Linked Open Data for Tracing Semantic Change

Armaselu, Florentina; McGillivray, Barbara; Liebeskind, Chaya; Marongiu, Paola; Valūnaitė Oleškevičienė, Giedrė; Apostol, Elena-Simona; Truică, Ciprian-Octavian

doi:10.31724/rihjj.50.2.1

Rasprave Instituta za hrvatski jezik, Vol. 50 No. 2, 2024.

Izvorni znanstveni članak

https://doi.org/10.31724/rihjj.50.2.1

Multilingual Word Embedding and Linguistic Linked Open Data for Tracing Semantic Change

Florentina Armaselu orcid.org/0000-0003-2386-6889 ; University of Luxembourg, Luxembourg
Barbara McGillivray orcid.org/0000-0003-3426-8200 ; King’s College London, United Kingdom
Chaya Liebeskind ; Jerusalem College of Technology, Israel
Paola Marongiu orcid.org/0000-0002-5060-3307 ; Institute of Computational Linguistics “Antonio Zampolli”, National Research Council (ILC-CNR), Italy
Giedrė Valūnaitė Oleškevičienė ; Mykolas Romeris University, Lithuania
Elena-Simona Apostol orcid.org/0000-0001-6397-4951 ; National University of Science and Technology Politehnica Bucharest, Romania
Ciprian-Octavian Truică orcid.org/0000-0001-7292-4462 ; National University of Science and Technology Politehnica Bucharest, Romania

Puni tekst: engleski pdf 1.873 Kb

verzije

str. 219-257

preuzimanja: 0

citiraj

APA 6th Edition

Armaselu, F., McGillivray, B., Liebeskind, C., Marongiu, P., Valūnaitė Oleškevičienė, G., Apostol, E. i Truică, C. (2024). Multilingual Word Embedding and Linguistic Linked Open Data for Tracing Semantic Change. Rasprave Instituta za hrvatski jezik, 50 (2), 219-257. https://doi.org/10.31724/rihjj.50.2.1

MLA 8th Edition

Armaselu, Florentina, et al. "Multilingual Word Embedding and Linguistic Linked Open Data for Tracing Semantic Change." Rasprave Instituta za hrvatski jezik, vol. 50, br. 2, 2024, str. 219-257. https://doi.org/10.31724/rihjj.50.2.1. Citirano 02.04.2025.

Chicago 17th Edition

Armaselu, Florentina, Barbara McGillivray, Chaya Liebeskind, Paola Marongiu, Giedrė Valūnaitė Oleškevičienė, Elena-Simona Apostol i Ciprian-Octavian Truică. "Multilingual Word Embedding and Linguistic Linked Open Data for Tracing Semantic Change." Rasprave Instituta za hrvatski jezik 50, br. 2 (2024): 219-257. https://doi.org/10.31724/rihjj.50.2.1

Harvard

Armaselu, F., et al. (2024). 'Multilingual Word Embedding and Linguistic Linked Open Data for Tracing Semantic Change', Rasprave Instituta za hrvatski jezik, 50(2), str. 219-257. https://doi.org/10.31724/rihjj.50.2.1

Vancouver

Armaselu F, McGillivray B, Liebeskind C, Marongiu P, Valūnaitė Oleškevičienė G, Apostol E i sur. Multilingual Word Embedding and Linguistic Linked Open Data for Tracing Semantic Change. Rasprave Instituta za hrvatski jezik [Internet]. 2024 [pristupljeno 02.04.2025.];50(2):219-257. https://doi.org/10.31724/rihjj.50.2.1

IEEE

F. Armaselu, et al., "Multilingual Word Embedding and Linguistic Linked Open Data for Tracing Semantic Change", Rasprave Instituta za hrvatski jezik, vol.50, br. 2, str. 219-257, 2024. [Online]. https://doi.org/10.31724/rihjj.50.2.1

Sažetak

This article proposes a methodology for combining natural language processing techniques for diachronic analysis and linguistic linked open data models to detect and represent semantic change. The change in meaning over time of words, phrases, or concepts encompasses complex phenomena that cannot be fully explained by distributional methods alone. We argue that by joining corpus-based and lexicographical evidence and modelling the results in an interoperable format can provide more solid ground for drawing conclusions and possibilities of re-use by other applications. We define a basic schema for a resource aggregator and a model called LLODIA (Linguistic Linked Open Data for Diachronic Analysis). To illustrate our approach, we use a multilingual dataset, in French, Latin, Hebrew, Old Lithuanian, and Romanian, and build a sample derived from word embeddings and dictionary resources, encoded by means of the proposed model.