Sciweavers

EMNLP
2008

Specialized Models and Ranking for Coreference Resolution

13 years 11 months ago
Specialized Models and Ranking for Coreference Resolution
This paper investigates 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).
Pascal Denis, Jason Baldridge
Added 29 Oct 2010
Updated 29 Oct 2010
Type Conference
Year 2008
Where EMNLP
Authors Pascal Denis, Jason Baldridge
Comments (0)