Cargando…
subs2vec: Word embeddings from subtitles in 55 languages
This paper introduces a novel collection of word embeddings, numerical representations of lexical semantics, in 55 languages, trained on a large corpus of pseudo-conversational speech transcriptions from television shows and movies. The embeddings were trained on the OpenSubtitles corpus using the f...
| Autores principales: | , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
Springer US
2020
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8062394/ https://www.ncbi.nlm.nih.gov/pubmed/32789660 http://dx.doi.org/10.3758/s13428-020-01406-3 |