Fast and Accurate Entity Recognition with Iterated Dilated Convolutions

EMNLP 2017 Emma StrubellPatrick VergaDavid BelangerAndrew McCallum

Today when many practitioners run basic NLP on the entire web and large-volume traffic, faster methods are paramount to saving time and energy costs. Recent advances in GPU hardware have led to the emergence of bi-directional LSTMs as a standard method for obtaining per-token vector representations serving as input to labeling tasks such as NER (often followed by prediction in a linear-chain CRF)... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
Named Entity Recognition Ontonotes v5 (English) BiLSTM-CRF F1 86.99 # 8
Named Entity Recognition Ontonotes v5 (English) Iterated Dilated CNN F1 86.84 # 9