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.- Anthology ID:
- Q14-1037
- Volume:
- Transactions of the Association for Computational Linguistics, Volume 2
- Month:
- Year:
- 2014
- Address:
- Cambridge, MA
- Editors:
- Dekang Lin, Michael Collins, Lillian Lee
- Venue:
- TACL
- SIG:
- Publisher:
- MIT Press
- Note:
- Pages:
- 477–490
- Language:
- URL:
- https://aclanthology.org/Q14-1037
- DOI:
- 10.1162/tacl_a_00197
- Cite (ACL):
- Greg Durrett and Dan Klein. 2014. A Joint Model for Entity Analysis: Coreference, Typing, and Linking. Transactions of the Association for Computational Linguistics, 2:477–490.
- Cite (Informal):
- A Joint Model for Entity Analysis: Coreference, Typing, and Linking (Durrett & Klein, TACL 2014)
- PDF:
- https://preview.aclanthology.org/ml4al-ingestion/Q14-1037.pdf
- Data
- OntoNotes 5.0