Modeling Joint Entity and Relation Extraction with Table Representation

This paper proposes a history-based struc-tured learning approach that jointly ex-tracts entities and relations in a sentence. We introduce a novel simple and flexible table representation of entities and rela-tions. We investigate several feature set-tings, search orders, and learning meth-ods with inexact search on the table. The experimental results demonstrate that a joint learning approach significantly out-performs a pipeline approach by incorpo-rating global features and by selecting ap-propriate learning methods and search or-ders.