Pattern Mining for Named Entity Recognition

Damien Nouvel (1) , Jean-Yves Antoine (1) , Nathalie Friburger (1)

1 BDTLN - Bases de données et traitement des langues naturelles

Many evaluation campaigns have shown that knowledge-based and data-driven approaches remain equally competitive for Named Entity Recognition. Our re-search team has developed CasEN, a symbolic system based on finite state tran-ducers, which achieved promising results during the Ester2 French-speaking eval-uation campaign. Despite these encouraging results, manually extending the cov-erage of such a hand-crafted system is a difficult task. In this paper, we present a novel approach based on pattern mining for NER and to supplement our sys-tem's knowledge base. The system, mXS, exhaustively searches for hierarchical sequential patterns, that aim at detecting Named Entity boundaries. We assess their efficiency by using such patterns in a standalone mode and in combination with our existing system.

Domaines: Informatique et langage [cs.CL]

Damien Nouvel, Jean-Yves Antoine, Nathalie Friburger. Pattern Mining for Named Entity Recognition. Lecture Notes in Computer Science, 2014, 8387, pp.226 - 237. ⟨10.1007/978-3-319-08958-4_19⟩. ⟨hal-01076157⟩