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).

• Type: Conference
• Year: 2008
• Where: EMNLP
• Authors: Pascal Denis, Jason Baldridge
• Keywords: EMNLP 2008, Natural Language Processing, Ranking Loss Function, Significant Performance Improvements, Training Separate Models