English

Self-Attention Gazetteer Embeddings for Named-Entity Recognition

Computation and Language 2020-04-21 v2

Abstract

Recent attempts to ingest external knowledge into neural models for named-entity recognition (NER) have exhibited mixed results. In this work, we present GazSelfAttn, a novel gazetteer embedding approach that uses self-attention and match span encoding to build enhanced gazetteer embeddings. In addition, we demonstrate how to build gazetteer resources from the open source Wikidata knowledge base. Evaluations on CoNLL-03 and Ontonotes 5 datasets, show F1 improvements over baseline model from 92.34 to 92.86 and 89.11 to 89.32 respectively, achieving performance comparable to large state-of-the-art models.

Keywords

Cite

@article{arxiv.2004.04060,
  title  = {Self-Attention Gazetteer Embeddings for Named-Entity Recognition},
  author = {Stanislav Peshterliev and Christophe Dupuy and Imre Kiss},
  journal= {arXiv preprint arXiv:2004.04060},
  year   = {2020}
}

Comments

Preprint

R2 v1 2026-06-23T14:44:25.473Z