ASTRAL: Adversarial Trained LSTM-CNN for Named Entity Recognition

TL;DR

This paper introduces ASTRAL, a novel NER system combining adversarial training with LSTM-CNN architecture, leveraging Gated-CNN for spatial info and perturbations for robustness, achieving state-of-the-art results.

Contribution

The paper proposes a new NER model that integrates adversarial training with LSTM-CNN and Gated-CNN to enhance accuracy and robustness over existing methods.

Findings

Achieved state-of-the-art results on three benchmark datasets.

Faster convergence and reduced overfitting in training.

Improved generalization and robustness of the NER model.

Abstract

Named Entity Recognition (NER) is a challenging task that extracts named entities from unstructured text data, including news, articles, social comments, etc. The NER system has been studied for decades. Recently, the development of Deep Neural Networks and the progress of pre-trained word embedding have become a driving force for NER. Under such circumstances, how to make full use of the information extracted by word embedding requires more in-depth research. In this paper, we propose an Adversarial Trained LSTM-CNN (ASTRAL) system to improve the current NER method from both the model structure and the training process. In order to make use of the spatial information between adjacent words, Gated-CNN is introduced to fuse the information of adjacent words. Besides, a specific Adversarial training method is proposed to deal with the overfitting problem in NER. We add perturbation to variables in the network during the training process, making the variables more diverse, improving the generalization and robustness of the model. Our model is evaluated on three benchmarks, CoNLL-03, OntoNotes 5.0, and WNUT-17, achieving state-of-the-art results. Ablation study and case study also show that our system can converge faster and is less prone to overfitting.