Collective Entity Resolution with Multi-Focal Attention
Venue
ACL (2016) (to appear)
Publication Year
2016
Authors
Amir Globerson, Nevena Lazic, Soumen Chakrabarti, Amarnag Subramanya, Michael Ringaard, Fernando Pereira
BibTeX
Abstract
Entity resolution is the task of linking each mention of an entity in text to the
corresponding record in a knowledge base (KB). Coherence models for entity
resolution encourage all referring expressions in a document to resolve to entities
that are related in the KB. We explore attention-like mechanisms for coherence,
where the evidence for each candidate is based on a small set of strong relations,
rather than relations to all other entities in the document. The rationale is that
document-wide support may simply not exist for non-salient entities, or entities
not densely connected in the KB. Our proposed system outperforms state-of-the-art
systems on the CoNLL 2003, TAC KBP 2010, 2011 and 2012 tasks.
