ASTRAL : Adversarial Trained LSTM-CNN for Named Entity Recognition

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

57 Scopus Citations
View graph of relations


Related Research Unit(s)


Original languageEnglish
Article number105842
Journal / PublicationKnowledge-Based Systems
Online published4 Apr 2020
Publication statusPublished - 7 Jun 2020


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.

Research Area(s)

  • Adversarial training, Deep neural network, Gated-CNN, Named entity recognition

Bibliographic Note

Research Unit(s) information for this publication is provided by the author(s) concerned.

Citation Format(s)

ASTRAL: Adversarial Trained LSTM-CNN for Named Entity Recognition. / Wang, Jiuniu; Xu, Wenjia; Fu, Xingyu et al.
In: Knowledge-Based Systems, Vol. 197, 105842, 07.06.2020.

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review