Linguistically-driven Selection of Difficult-to-Parse Dependency Structures
The paper illustrates a novel methodology meeting a twofold goal, namely quantifying the reliability of automatically generated dependency relations without using gold data on the one hand, and identifying which are the linguistic constructions negatively affecting the parser performance on the othe...
Сохранить в:
| Опубликовано в: : | URI:https://journals.openedition.org/ijcol, |
|---|---|
| Главные авторы: | , , , |
| Формат: | Article ou chapitre numérique |
| Язык: | Anglais |
| Опубликовано: |
IJCoL
2021
|
| Online-ссылка: | Accès Université d'Orléans et IFPM Accès Université d'Orléans et IFPM |