This paper presents a new set of lemma embeddings for the Latin language. Embeddings are trained on a manually annotated corpus of texts belonging to the Classical era: different models, architectures and dimensions are tested and evaluated using a novel benchmark for the synonym selection task. A qualitative evaluation is also performed on the embeddings of rare lemmas. In addition, we release vectors pre-trained on the “Opera Maiora” by Thomas Aquinas, thus providing a resource to analyze Latin in a diachronic perspective.
Sprugnoli, R., Passarotti, M. C., Moretti, G., Vir is to Moderatus as Mulier is to Intemperans. Lemma Embeddings for Latin, in Proceedings of the Sixth Italian Conference on Computational Linguistics, (BARI -- ITA, 13-15 November 2019), Accademia University Press, TORINO -- ITA 2019:<<COLLANA DELL'ASSOCIAZIONE ITALIANA DI LINGUISTICA COMPUTAZIONALE>>, 1-7. [10.5281/zenodo.3565572] [http://hdl.handle.net/10807/144302]
Vir is to Moderatus as Mulier is to Intemperans. Lemma Embeddings for Latin
Sprugnoli, Rachele;Passarotti, Marco Carlo;
2019
Abstract
This paper presents a new set of lemma embeddings for the Latin language. Embeddings are trained on a manually annotated corpus of texts belonging to the Classical era: different models, architectures and dimensions are tested and evaluated using a novel benchmark for the synonym selection task. A qualitative evaluation is also performed on the embeddings of rare lemmas. In addition, we release vectors pre-trained on the “Opera Maiora” by Thomas Aquinas, thus providing a resource to analyze Latin in a diachronic perspective.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
