Browse > Article
http://dx.doi.org/10.9717/kmms.2021.24.10.1391

Context-Sensitive Spelling Error Correction Techniques in Korean Documents using Generative Adversarial Network  

Lee, Jung-Hun (Grand Information Technology Research Center)
Kwon, Hyuk-Chul (Dept. of Information Computer Science., College of Eng., Pusan National University)
Publication Information
Journal of Korea Multimedia Society / v.24, no.10, 2021 , pp. 1391-1402 More about this Journal
Abstract
This paper focuses use context-sensitive spelling error correction using generative adversarial network. Generative adversarial network[1] are attracting attention as they solve data generation problems that have been a challenge in the field of deep learning. In this paper, sentences are generated using word embedding information and reflected in word distribution representation. We experiment with DCGAN[2] used for the stability of learning in the existing image processing and D2GAN[3] with double discriminator. In this paper, we experimented with how the composition of generative adversarial networks and the change of learning corpus influence the context-sensitive spelling error correction In the experiment, we correction the generated word embedding information and compare the performance with the actual word embedding information.
Keywords
context-sensitive correction; generative adversarial network; dual discriminator GAN; embedding based context-sensitive spelling error correction; DCGAN; D2GAN;
Citations & Related Records
연도 인용수 순위
  • Reference
1 J.-H. Lee, M. Kim, and H.-C. Kwon. "The Utilization of Local Document Information to Improve Statistical Context-Sensitive Spelling Error Correction," KIISE Transaction on Computing, Vol. 23, No. 7, pp. 446-451, 2017.   DOI
2 I. Goodfellow, et al., "Generative Adversarial Nets," Advances in Neural Information Processing Systems, Vol. 2, pp. 2672-2680, 2014.
3 R. Radford, L. Metz, and S. Chintala. "Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks," arXiv preprint, arXiv:1511.06434, 2015.
4 T. Nguyen, et al., "Dual Discriminator Generative Adversarial Nets," Advances in Neural Information Processing Systems. 2017.
5 G. Antipov, M. Baccouche, and J.-L. Dugelay. "Face Aging with Conditional Generative Adversarial Networks," 2017 IEEE International Conference on Image Processing (ICIP). pp. 2089-2093, 2017.
6 D.-J. Kim, "A Method for Detection and Correction of Pseudo-Semantic Errors Due to Typographical Errors," Journal of the Korea Society of Computer and Information, Vol. 18, No. 10, pp. 173-182, 2013.   DOI
7 J. Wu, et al., "Learning a Probabilistic Latent Space of Object Shapes via 3D Genera-Tive-Adversarial Modeling," Advances in Neural Information Processing Systems, pp. 82-90, 2016.
8 C. Ledig, et al., "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4681-4690, 2017.
9 S. Robert, Generative Adversarial Networks and Word Embeddings for Natural Language Generation, Master's Thesis of City University of New York, 2019.
10 A. Budhkar, et al. "Generative Adversarial Networks for Text using Word2vec Intermediaries," arXiv preprint, arXiv:1904. 02293, 2019.
11 J.-H. Lee, M. Kim, and H.-C. Kwon. "Context-Sensitive Spelling Error Correction Techniques using Generative Adversarial Network," Proceedings of the KIISE Korea Software Congress, pp. 395-397, 2019.
12 H. Zhang, et al. "Stackgan: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks." Proceed- ings of the IEEE International Conference on Computer Vision, pp. 5907-5915, 2017.
13 P. Bojanowski, et al. "Enriching Word Vectors with Subword Information," Transactions of the Association for Computational Linguistics, Vol. 5, pp. 135-146, 2017.   DOI
14 J.-H. Lee, M. Kim, and H.-C. Kwon. "Improved Statistical Language Model for Context-Sensitive Spelling Error Candidates," Journal of Korea Multimedia Society, Vol. 20, No. 2, pp. 371-381, 2017.   DOI