Refining the Distributional Inclusion Hypothesis for Unsupervised Hypernym Identification
Several unsupervised methods for hypernym detection have been investigated in distributional semantics. Here we present a new approach based on a smoothed version of the distributional inclusion hypothesis. The new method is able to improve hypernym detection after testing on the BLESS dataset.
Kaydedildi:
| Yayımlandı: | URI:https://journals.openedition.org/ijcol, |
|---|---|
| Asıl Yazarlar: | , , |
| Materyal Türü: | Article ou chapitre numérique |
| Dil: | Anglais |
| Baskı/Yayın Bilgisi: |
IJCoL
2020
|
| Online Erişim: | Accès Université d'Orléans et IFPM Accès Université d'Orléans et IFPM |