TY - GEN
T1 - Collective entity resolution with multi-focal attention
AU - Globerson, Amir
AU - Lazic, Nevena
AU - Chakrabarti, Soumen
AU - Subramanya, Amarnag
AU - Ringgaard, Michael
AU - Pereira, Fernando
N1 - Publisher Copyright:
© 2016 Association for Computational Linguistics.
PY - 2016
Y1 - 2016
N2 - 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 attentionlike 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 documentwide 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.
AB - 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 attentionlike 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 documentwide 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.
UR - http://www.scopus.com/inward/record.url?scp=85011866745&partnerID=8YFLogxK
U2 - 10.18653/v1/p16-1059
DO - 10.18653/v1/p16-1059
M3 - פרסום בספר כנס
AN - SCOPUS:85011866745
T3 - 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers
SP - 621
EP - 631
BT - 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers
PB - Association for Computational Linguistics (ACL)
Y2 - 7 August 2016 through 12 August 2016
ER -