Deep Active Learning for Named Entity Recognition

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.

References in corpus (5)

• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• Convolutional Neural Networks for Sentence Classification
• Deep Bayesian Active Learning with Image Data
• Neural Models for Sequence Chunking
• Revisiting Perceptron: Efficient and Label-Optimal Learning of Halfspaces

Cited by in corpus (19)

• Assessing The Factual Accuracy of Generated Text
• Improving Hospital Mortality Prediction with Medical Named Entities and Multimodal Learning
• A Survey of Active Learning for Text Classification using Deep Neural Networks
• A non-cooperative meta-modeling game for automated third-party calibrating, validating, and falsifying constitutive laws with parallelized adversarial attacks
• Uncertainty-Aware Reliable Text Classification
• Deep Ensemble Bayesian Active Learning : Addressing the Mode Collapse issue in Monte Carlo dropout via Ensembles
• Graph Policy Network for Transferable Active Learning on Graphs
• Deep Learning on a Data Diet: Finding Important Examples Early in Training
• Gunrock 2.0: A User Adaptive Social Conversational System
• Robust Lexical Features for Improved Neural Network Named-Entity Recognition
• Single-Modal Entropy based Active Learning for Visual Question Answering
• Active Learning under Label Shift
• LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentation
• Empirical Study of Named Entity Recognition Performance Using Distribution-aware Word Embedding
• LEAN-LIFE: A Label-Efficient Annotation Framework Towards Learning from Explanation
• Robust Assignment of Labels for Active Learning with Sparse and Noisy Annotations
• Char-RNN and Active Learning for Hashtag Segmentation
• Incremental Learning from Scratch for Task-Oriented Dialogue Systems
• Efficient Semi-Supervised Learning for Natural Language Understanding by Optimizing Diversity