Deep Active Learning for Named Entity Recognition

TL;DR

This paper combines deep learning with active learning to significantly reduce labeled data requirements for named entity recognition, introducing a lightweight CNN-CNN-LSTM model that achieves near state-of-the-art performance efficiently.

Contribution

It presents a novel lightweight CNN-CNN-LSTM architecture for NER and demonstrates its effectiveness with active learning to reduce data needs.

Findings

Achieves near state-of-the-art performance with only 25% of training data.

Introduces a computationally efficient NER model.

Shows active learning reduces data requirements significantly.

Abstract

Deep learning has yielded state-of-the-art performance on many natural language processing tasks including named entity recognition (NER). However, this typically requires large amounts of labeled data. In this work, we demonstrate that the amount of labeled training data can be drastically reduced when deep learning is combined with active learning. While active learning is sample-efficient, it can be computationally expensive since it requires iterative retraining. To speed this up, we introduce a lightweight architecture for NER, viz., the CNN-CNN-LSTM model consisting of convolutional character and word encoders and a long short term memory (LSTM) tag decoder. The model achieves nearly state-of-the-art performance on standard datasets for the task while being computationally much more efficient than best performing models. We carry out incremental active learning, during the training process, and are able to nearly match state-of-the-art performance with just 25\% of the original training data.