Cross-lingual, Character-Level Neural Morphological Tagging
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2017
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912343525425152 |
|---|---|
| author | Cotterell, Ryan Heigold, Georg |
| author_facet | Cotterell, Ryan Heigold, Georg |
| contents | Even for common NLP tasks, sufficient supervision is not available in many languages -- morphological tagging is no exception. In the work presented here, we explore a transfer learning scheme, whereby we train character-level recurrent neural taggers to predict morphological taggings for high-resource languages and low-resource languages together. Learning joint character representations among multiple related languages successfully enables knowledge transfer from the high-resource languages to the low-resource ones, improving accuracy by up to 30% over a monolingual model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_1708_09157 |
| institution | arXiv |
| publishDate | 2017 |
| record_format | arxiv |
| spellingShingle | Cross-lingual, Character-Level Neural Morphological Tagging Cotterell, Ryan Heigold, Georg Computation and Language Even for common NLP tasks, sufficient supervision is not available in many languages -- morphological tagging is no exception. In the work presented here, we explore a transfer learning scheme, whereby we train character-level recurrent neural taggers to predict morphological taggings for high-resource languages and low-resource languages together. Learning joint character representations among multiple related languages successfully enables knowledge transfer from the high-resource languages to the low-resource ones, improving accuracy by up to 30% over a monolingual model. |
| title | Cross-lingual, Character-Level Neural Morphological Tagging |
| topic | Computation and Language |
| url | https://arxiv.org/abs/1708.09157 |