A Joint Model for Entity Analysis: Coreference, Typing, and Linking
Published
2014-11-01
Greg Durrett
,
Dan Klein
Greg Durrett
UC Berkeley
Dan Klein
UC Berkeley
Abstract
We present a joint model of three core tasks in the entity analysis stack: coreference resolution (within-document clustering), named entity recognition (coarse semantic typing), and entity linking (matching to Wikipedia entities). Our model is formally a structured conditional random field. Unary factors encode local features from strong baselines for each task. We then add binary and ternary factors to capture cross-task interactions, such as the constraint that coreferent mentions have the same semantic type. On the ACE 2005 and OntoNotes datasets, we achieve state-of-the-art results for all three tasks. Moreover, joint modeling improves performance on each task over strong independent baselines.
PDF (presented at NAACL 2015)