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.
@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}
}