A Joint Model for Entity Analysis: Coreference, Typing, and Linking
Open Access
- 1 December 2014
- journal article
- Published by MIT Press in Transactions of the Association for Computational Linguistics
- Vol. 2, 477-490
- https://doi.org/10.1162/tacl_a_00197
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.Keywords
This publication has 3 references indexed in Scilit:
- Evaluating Entity Linking with WikipediaArtificial Intelligence, 2012
- Learning multilingual named entity recognition from WikipediaArtificial Intelligence, 2012
- A Machine Learning Approach to Coreference Resolution of Noun PhrasesComputational Linguistics, 2001