Towards Improving Neural Named Entity Recognition with Gazetteers

ACL 2019  ·  Tianyu Liu, Jin-Ge Yao, Chin-Yew Lin ·

Most of the recently proposed neural models for named entity recognition have been purely data-driven, with a strong emphasis on getting rid of the efforts for collecting external resources or designing hand-crafted features. This could increase the chance of overfitting since the models cannot access any supervision signal beyond the small amount of annotated data, limiting their power to generalize beyond the annotated entities. In this work, we show that properly utilizing external gazetteers could benefit segmental neural NER models. We add a simple module on the recently proposed hybrid semi-Markov CRF architecture and observe some promising results.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Benchmark
Named Entity Recognition (NER) CoNLL 2003 (English) HSCRF + softdict F1 92.75 # 34
Named Entity Recognition (NER) Ontonotes v5 (English) HSCRF + softdict F1 89.94 # 14

Methods