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.
|COLLANA DELL'ASSOCIAZIONE ITALIANA DI LINGUISTICA COMPUTAZIONALE
|Sixth Italian Conference on Computational Linguistics
|BARI -- ITA
|13/11/19 → 15/11/19