|
Modèles de classement specialisés pour la résolution automatique de la coréference| old_uid | 5487 |
|---|
| title | Modèles de classement specialisés pour la résolution automatique de la coréference |
|---|
| start_date | 2008/10/27 |
|---|
| schedule | 14h-16h |
|---|
| online | no |
|---|
| summary | We investigate two strategies for improving coreference resolution: (1) training separate models that specialize in particular types of mentions (e.g., pronouns versus proper nouns) and (2) using a ranking loss function rather than a classification function. In addition to being conceptually simple, these modifications of the standard single-model, classification-based approach also deliver significant performance improvements. Specifically, we show that on the ACE corpus both strategies produce f-score gains of more than 3% across the three coreference evaluation metrics (MUC, B3, and CEAF). |
|---|
| responsibles | Information non disponible, Crabbé |
|---|
| |
|