DeNERT: Named Entity Recognition Model using DQN and BERT (DeNERT: DQN과 BERT를 이용한 개체명 인식 모델)

Sung-Min Yang (양성민); Ok-Ran Jeong (정옥란)

doi:10.9708/jksci.2020.25.04.029

DeNERT: Named Entity Recognition Model using DQN and BERT

Journal of The Korea Society of Computer and Information
Abbr : JKSCI
2020, 25(4), pp.29-35
DOI : 10.9708/jksci.2020.25.04.029
Publisher : The Korean Society Of Computer And Information
Research Area : Engineering > Computer Science
Received : February 13, 2020
Accepted : April 9, 2020
Published : April 30, 2020

Sung-Min Yang ¹, Ok-Ran Jeong ¹

¹가천대학교

Accredited

ABSTRACT

In this paper, we propose a new structured entity recognition DeNERT model. Recently, the field of natural language processing has been actively researched using pre-trained language representation models with a large amount of corpus. In particular, the named entity recognition, which is one of the fields of natural language processing, uses a supervised learning method, which requires a large amount of training dataset and computation. Reinforcement learning is a method that learns through trial and error experience without initial data and is closer to the process of human learning than other machine learning methodologies and is not much applied to the field of natural language processing yet. It is often used in simulation environments such as Atari games and AlphaGo. BERT is a general-purpose language model developed by Google that is pre-trained on large corpus and computational quantities. Recently, it is a language model that shows high performance in the field of natural language processing research and shows high accuracy in many downstream tasks of natural language processing. In this paper, we propose a new named entity recognition DeNERT model using two deep learning models, DQN and BERT. The proposed model is trained by creating a learning environment of reinforcement learning model based on language expression which is the advantage of the general language model. The DeNERT model trained in this way is a faster inference time and higher performance model with a small amount of training dataset. Also, we validate the performance of our model's named entity recognition performance through experiments.

KEYWORDS

Natural language processing, Named entity recognition, Reinforcement learning, BERT, DQN, Language model

Citation status

* References for papers published after 2023 are currently being built.

[confproc] T. Mikolov / 2013 / Distributed representations of words and phrases and their compositionality / Advances in neural information processing systems : 3111~3119

[confproc] G. Lample / 2016 / Neural architectures for named entity recognition / Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies : 260~270

[confproc] ME. Peters / 2018 / Deep contextualized word representations / Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies 1 : 2227~2237

[web] A. Radford / Improving language understanding by generative pre-training / https://cdn.openai.com/research-covers/language-unsupervised/language_understanding_paper.pdf

[confproc] J. Devlin / 2019 / Bert: Pre-training of deep bidirectional transformers for language understanding / Proceedings of the 2019Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies 1 : 4171~4186

[confproc] A. Vaswani / 2017 / Attention is all you need / Advances in neural information processing systems

[journal] Christopher J. C. H. Watkins / 1992 / Q-learning / Machine Learning / Springer Science and Business Media LLC 8(3-4) : 279~292

[web] V. Mnih / 2013 / Playing atari with deep reinforcement learning / https://arxiv.org/abs/1312.5602

[journal] Volodymyr Mnih / 2015 / Human-level control through deep reinforcement learning / Nature / Springer Science and Business Media LLC 518(7540) : 529~533

[confproc] M. Fang / 2017 / Learning how to active learn: A deep reinforcement learning approach / Proceedings of the 2017Conference on Empirical Methods in Natural Language Processing : 595~605

[confproc] Y. Yang / 2018 / Distantly supervised ner with partial annotation learning and reinforcement learning / Proceedings of the 27th International Conference on Computational Linguistics : 2159~2169

[confproc] Z. Huang / 2015 / Bidirectional LSTM-CRF models for sequence tagging / Pro-ceedings of the 21st International Conference on AsianLanguage Processing

[web] Y. Wu / 2016 / Google's neural machine translation system: Bridging the gap between human and machine translation / https://arxiv.org/abs/1609.08144

[confproc] CD. Manning / 2014 / The Stanford CoreNLP natural language processing toolkit / Proceedings of 52nd annual meeting of the association for computational linguistics: system demonstrations : 55~60

[confproc] EF. Sang / 2003 / Introduction to the CoNLL-2003shared task: Language-independent named entity recognition / Proceedings of the Seventh Conference on Natural Language Learning at HLT-NAACL : 142~147

[web] M. Abadi / 2016 / Tensorflow: Large-scale machine learning on heterogeneous distributed systems / https://arxiv.org/abs/1603.04467

[confproc] A. Akbik / 2019 / Pooled contextualized embeddings for named entity recognition / Proceedings of the 2019Conference of the North American Chapter of the Association for Computational Linguistics 1 : 724~728

[confproc] V. Mnih / 2016 / Asynchronous methods for deep reinforcement learning / International conference on machine learning

[confproc] RS. Sutton / 2000 / Policy gradient methods for reinforcement learning with function approximation / Advances in neural information processing systems : 1057~1063

KJCKorea
Journal Central

Journal of The Korea Society of Computer and Information 2023 KCI Impact Factor : 0.65

DeNERT: Named Entity Recognition Model using DQN and BERT

ABSTRACT

KEYWORDS

Citation status

* References for papers published after 2023 are currently being built.

Journal of The Korea Society of Computer and Information 2023 KCI Impact Factor : 0.65

DeNERT: Named Entity Recognition Model using DQN and BERT

ABSTRACT

KEYWORDS

Statistics

Tools

Issue List

Citation status

KCI Citation Counts (1)

REFERENCES (19) * References for papers published after 2023 are currently being built.

Search PDF

Citation

* References for papers published after 2023 are currently being built.