Named Entity Recognition with Bidirectional LSTM-CNNs

TL;DR

This paper introduces a neural network architecture combining bidirectional LSTM and CNN for named entity recognition, reducing the need for feature engineering and achieving state-of-the-art results on standard datasets.

Contribution

The paper presents a novel hybrid neural network model and a new method for encoding lexicon matches, improving NER performance without extensive feature engineering.

Findings

Achieves 91.62 F1 on CoNLL-2003 dataset

Surpasses previous state-of-the-art on OntoNotes 5.0 by 2.13 F1 points

Uses publicly available resources to outperform systems with proprietary features

Abstract

Named entity recognition is a challenging task that has traditionally required large amounts of knowledge in the form of feature engineering and lexicons to achieve high performance. In this paper, we present a novel neural network architecture that automatically detects word- and character-level features using a hybrid bidirectional LSTM and CNN architecture, eliminating the need for most feature engineering. We also propose a novel method of encoding partial lexicon matches in neural networks and compare it to existing approaches. Extensive evaluation shows that, given only tokenized text and publicly available word embeddings, our system is competitive on the CoNLL-2003 dataset and surpasses the previously reported state of the art performance on the OntoNotes 5.0 dataset by 2.13 F1 points. By using two lexicons constructed from publicly-available sources, we establish new state of the art performance with an F1 score of 91.62 on CoNLL-2003 and 86.28 on OntoNotes, surpassing systems that employ heavy feature engineering, proprietary lexicons, and rich entity linking information.