A Joint Model for Entity Analysis: Coreference, Typing, and Linking
Transactions of the Association for Computational Linguistics2014Vol. 2, pp. 477–490
Citations Over TimeTop 1% of 2014 papers
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.
Related Papers
- → Two-phase biomedical named entity recognition using CRFs(2009)81 cited
- → Biomedical Named Entity Recognition Based on Skip-Chain CRFS(2012)22 cited
- Chinese Word Segmentation and Named Entity Recognition Based on Conditional Random Fields Models(2006)
- Two Step Chinese Named Entity Recognition Based on Conditional Random Fields Models(2008)
- → Conditional Random Fields for Biomedical Named Entity Recognition Revisited(2020)