Automatic Word Spacing of Korean Using Syllable and Morpheme
Abstract
:1. Introduction
2. Data
3. Word Spacing Correction Model
3.1. Integer Encoding
3.2. Embedding
3.3. Multiple Filter 1-dimensional Convolutional Neural Networks
3.4. Bidirectional Long Short-Term Memory
4. Experiment
4.1. Labeling
4.2. Data Feed
4.3. Parameters
4.4. Train
4.5. Metric
4.6. Evaluation and Result
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Shim, K. Automatic Word Spacing Using Raw Corpus and a Morphological Analyzer. J. KIISE. 2015, 42, 68–75. [Google Scholar] [CrossRef]
- Kang, S. Improvement of Automatic Word Segmentation of Korean by Simplifying Syllable Bigram. In Proceedings of the Annual Conference on Human and Language Technology, Seoul, Korea, 10–11 October 2003; pp. 227–231. [Google Scholar]
- Lee, C. Joint models for Korean word spacing and POS tagging using structural SVM. J. KIISE: Softw. Appl. 2013, 40, 604–606. [Google Scholar]
- Shim, K. Automatic Word Spacing based on Conditional Random Fields. Korean J. Cogn. Sci. 2011, 22, 217–233. [Google Scholar] [CrossRef]
- Jang, J.; Wang, K.; Kang, S. Automatic Korean Word Spacing Using Bi-directional LSTM. In Proceedings of the KISS Conference, Jeju, Korea, 20–22 June 2018; pp. 2052–2053. [Google Scholar]
- Kim, S.-W.; Choi, S.-P. Research on Joint Models for Korean Word Spacing and POS (Part-Of-Speech) Tagging based on Bidirectional LSTM-CRF. J. KIISE 2018, 45, 792–800. [Google Scholar] [CrossRef]
- Hwang, T.; Jung, S. Automatic Korean word spacing using BERT. In Proceedings of the KISS Conference, Pyeongchang, Korea, 18–20 December 2019; pp. 374–376. [Google Scholar]
- Lee, H.Y.; Kang, S.S. Automatic word spacing of the Korean sentences by using end-to-end deep neural network. KIPS Trans Softw. Data Eng. 2019, 8, 441–448. [Google Scholar]
- Lee, T.S.; Kang, S.S. LSTM based sequence-to-sequence model for Korean automatic word-spacing. Korean Inst. Smart Media 2018, 7, 17–23. [Google Scholar]
- She, X.; Zhang, D. Text Classification Based on Hybrid CNN-LSTM Hybrid Model. In Proceedings of the International Symposium on Computational Intelligence and Design, ISCID, Hangzhou, China, 8–9 December 2018; pp. 185–189. [Google Scholar]
- Jang, B.; Kim, M.; Harerimana, G.; Kang, S.-u.; Kim, J.W. Bi-LSTM Model to Increase Accuracy in Text Classification: Combining Word2vec CNN and Attention Mechanism. Appl. Sci. 2020, 10, 5841. [Google Scholar] [CrossRef]
- Wu, C.; Wu, F.; Chen, Y.; Wu, S.; Yuan, Z.; Huang, Y. Neural metaphor detecting with CNN-LSTM model. In Proceedings of the Workshop on Figurative Language Processing, New Orleans, Louisiana, 6 June 2018; pp. 110–114. [Google Scholar]
- Hwang, H.; Lee, C. Automatic Korean Word Spacing using Deep Learning. In Proceedings of the Korea Computer Congress, Jeju, Korea, 29 June–1 July 2016; pp. 738–740. [Google Scholar]
- National Institute of Korean Language. Available online: https://ithub.korean.go.kr/ (accessed on 27 December 2020).
- Bengio, Y.; Ducharme, R.; Vincent, P.; Jauvin, C. A neural probabilistic language model. J. Mach. Learn. Res. 2003, 3, 1137–1155. [Google Scholar]
- Kombrink, S.; Mikolov, T.; Karafiát, M.; Budget, L. Recurrent Neural Network Based Language Modeling in Meeting Recognition. In Proceedings of the Twelfth Annual Conference of the International Speech Communication Association, Florence, Italy, 28–31 August 2011; pp. 2877–2880. [Google Scholar]
- Mikolov, T.; Chen, K.; Corrado, G.; Dean, J. Efficient estimation of word representations in vector space. arXiv 2013, arXiv:1301.3781. [Google Scholar]
- Mikolov, T.; Sutskever, I.; Chen, K.; Corrado, G.; Dean, J. Distributed Representations of Words and Phrases and their Compositionality. In Proceedings of the Advances in Neural Information Processing Systems, Lake Tahoe, NV, USA, 5–8 December 2013; pp. 3111–3119. [Google Scholar]
- Levy, O.; Goldbeg, Y. Dependency-based word embeddings. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, Baltimore, MD, USA, 22–27 June 2014; pp. 302–308. [Google Scholar]
- Pennington, J.; Socher, R.; Manning, C.D. GloVe: Global vectors for word representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Qatar, 25–29 October 2014; pp. 1532–1543. [Google Scholar]
- Zhang, Y.; Wallace, B. A sensitivity analysis of (and Practitioners’ guide to) convolutional neural networks for sentence classification. arXiv 2015, arXiv:1510.03820. [Google Scholar]
- Kim, Y. Convolutional neural networks for sentence classification. arXiv 2014, arXiv:1408.5882. [Google Scholar]
- Kalchbrenner, N.; Grefenstette, E.; Blunsom, P. A convolutional neural network for modelling sentences. arXiv 2014, arXiv:1404.2188. [Google Scholar]
- Zhang, X.; Zhao, J.; LeCun, Y. Character-level convolutional networks for text classification. In Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada, 7–12 December 2015; pp. 649–657. [Google Scholar]
- Schuster, M.; Paliwal, K.K. Bidirectional Recurrent Neural Networks. IEEE Trans. Signal Process. 1997, 45, 2673–2681. [Google Scholar] [CrossRef] [Green Version]
Level | Example |
---|---|
Sentence | 아버지가 방에 들어가신다. (Father-nominative bang-locative enter-honorific-ending.) |
Pronunciation | abeoji-ga bang-e deuleoga-sin-da. |
English | Father enters the room |
Word | abeoji-ga/bang-e/deuleoga-sin-da. |
Morpheme | abeoji/-ga/bang/-e/deuleoga/sin-da/. |
Syllable | a/beo/ji/-ga/bang/-e/deul/eo/ga/sin/-da/. |
Level | Average | Max |
---|---|---|
syllable | 39.183 | 350 |
word | 9.333 | 79 |
Morpheme | Start | Middle | End |
---|---|---|---|
Common Noun | 1 | 1 | 2 |
Nominative postposition | 3 | 3 | 4 |
Adverbial postposition | 5 | 5 | 6 |
Verb | 7 | 7 | 8 |
Prefinal ending | 9 | 9 | 10 |
Period | 11 | 11 | 12 |
Sentence | a | beo | ji | -ga | bang | -e | deol | eo | ga | -sin | -da | . |
---|---|---|---|---|---|---|---|---|---|---|---|---|
Syllable | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 4 | 9 | 10 | 11 |
Morpheme | 1 | 1 | 2 | 4 | 2 | 6 | 7 | 7 | 8 | 9 | 10 | 12 |
Input | Tag | Word | ||
---|---|---|---|---|
Accuracy (%) | Precision (%) | Recall (%) | F1 Score (%) | |
Morpheme | 98.29 | 93.00 | 92.96 | 92.98 |
Syllable | 98.70 | 95.11 | 93.75 | 94.43 |
Syllable and morpheme | 99.13 | 96.54 | 95.59 | 96.06 |
Model | Tag | Word | ||
---|---|---|---|---|
Accuracy (%) | Precision (%) | Recall (%) | F1 Score (%) | |
2015 [1] | 98.06 | 92.27 | 94.15 | 93.20 |
2016 [13] | 98.32 | 92.68 | 91.96 | 92.32 |
2018 [9] | - | 93.72 | 94.27 | 93.99 |
2019 [8] | 98.53 | 95.06 | 93.46 | 94.26 |
Proposed model | 99.13 | 96.54 | 95.59 | 96.06 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Choi, J.-M.; Kim, J.-D.; Park, C.-Y.; Kim, Y.-S. Automatic Word Spacing of Korean Using Syllable and Morpheme. Appl. Sci. 2021, 11, 626. https://doi.org/10.3390/app11020626
Choi J-M, Kim J-D, Park C-Y, Kim Y-S. Automatic Word Spacing of Korean Using Syllable and Morpheme. Applied Sciences. 2021; 11(2):626. https://doi.org/10.3390/app11020626
Chicago/Turabian StyleChoi, Jeong-Myeong, Jong-Dae Kim, Chan-Young Park, and Yu-Seop Kim. 2021. "Automatic Word Spacing of Korean Using Syllable and Morpheme" Applied Sciences 11, no. 2: 626. https://doi.org/10.3390/app11020626