Cargando…
Enhancing Subword Embeddings with Open N-grams
Using subword n-grams for training word embeddings makes it possible to subsequently compute vectors for rare and misspelled words. However, we argue that the subword vector qualities can be degraded for words which have a high orthographic neighbourhood; a property of words that has been extensivel...
| Autores principales: | , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
2020
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7298185/ http://dx.doi.org/10.1007/978-3-030-51310-8_1 |