A Survey on Recent Advances in Named Entity Recognition from Deep Learning models

TL;DR

This survey reviews recent deep learning-based approaches to Named Entity Recognition, highlighting their advancements over traditional methods and emphasizing the integration of past feature-based insights for improved performance.

Contribution

It provides a comprehensive comparison of neural network architectures for NER and discusses how lessons from previous approaches can enhance current models.

Findings

Deep neural networks significantly improve NER accuracy.

Incorporating feature-based insights further enhances neural network performance.

Neural approaches outperform traditional feature-engineered methods.

Abstract

Named Entity Recognition (NER) is a key component in NLP systems for question answering, information retrieval, relation extraction, etc. NER systems have been studied and developed widely for decades, but accurate systems using deep neural networks (NN) have only been introduced in the last few years. We present a comprehensive survey of deep neural network architectures for NER, and contrast them with previous approaches to NER based on feature engineering and other supervised or semi-supervised learning algorithms. Our results highlight the improvements achieved by neural networks, and show how incorporating some of the lessons learned from past work on feature-based NER systems can yield further improvements.