Abstract
Chinese spelling correction (CSC) and BERT pre-training task can both be regarded as text denoising. In this work, to further narrow the gap between the pre-training and CSC tasks, we present a Single Channel BERT (SCBERT) which incorporates semantics, pinyin and glyph of typos to provide effective spelling correction. In model pre-training, we introduce fuzzy pinyin and glyph of Chinese characters and adjust mask strategies to restore the pinyin or glyph information of the “[MASK]” token under certain probabilities. Therefore, we can mask out the char channel of the typo and only provide its pinyin or glyph information in order to reduce the input noise when using our models, as the char information of typos in CSC is a kind of noise. Moreover, we apply synonym replacement and sentence reordering for paraphrasing to improve the accuracy of the correction step. We conduct experiments using widely accepted benchmarks. Our method outperforms state-of-the-art approaches under zero-shot learning condition and achieves competitive results when fine-tuning.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
References
Islam, N., Islam, Z., Noor, N.: A survey on optical character recognition system. arXiv preprint arXiv:1710.05703 (2017)
Benzeghiba, M., et al.: Automatic speech recognition and speech variability: a review. Speech Commun. 49, 763–786 (2007)
Guo, J., Sainath, T.N., Weiss, R.J.: A spelling correction model for end-to-end speech recognition. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5651–5655. IEEE (2019)
Liu, C.-L., Lai, M.-H., Chuang, Y.-H., Lee, C.-Y.: Visually and phonologically similar characters in incorrect simplified chinese words. In: Coling 2010: Posters, pp. 739–747 (2010)
Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training (2018)
Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R.R., Le, Q.V.: Xlnet: generalized autoregressive pretraining for language understanding. Adv. Neural Inf. Process. Syst. 32 (2019)
Lewis, M., et al.: Bart: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461 (2019)
Ji, T., Yan, H., Qiu, X.: SpellBERT: a lightweight pretrained model for chinese spelling check. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 3544–3551 (2021)
Zhang, A., Li, B., Wang, W., Wan, S: A Novel Text Classification Model Combining Deep Active Learning with BERT. CMC-COMPUTERS MATERIALS & CONTINUA
Li, X., Feng, J., Meng, Y., Han, Q., Wu, F., Li, J.: A unified MRC framework for named entity recognition. arXiv preprint arXiv:1910.11476 (2019)
Sun, Z., et al.: Chinesebert: Chinese pretraining enhanced by glyph and pinyin information. arXiv preprint arXiv:2106.16038 (2021)
Liu, S., Yang, T., Yue, T., Zhang, F., Wang, D.: PLOME: pre-training with misspelled knowledge for Chinese spelling correction. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, vol. 1, Long Papers, pp. 2991–3000 (2019)
Wang, D., Song, Y., Li, J., Han, J., Zhang, H.: A hybrid approach to automatic corpus generation for Chinese spelling check. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 2517–2527 (2018)
Hong, Y., Yu, X., He, N., Liu, N., Liu, J.: FASPell: A fast, adaptable, simple, powerful Chinese spell checker based on DAE-decoder paradigm. In: Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019), pp. 160–169 (2019)
Wang, D., Tay, Y., Zhong, L.: Confusionset-guided pointer networks for chinese spelling check. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 5780–5785 (2018)
Dai, Y., et al.: Is Whole Word Masking Always Better for Chinese BERT?: probing on Chinese Grammatical Error Correction. arXiv preprint arXiv:2203.00286 (2022)
Liu, Y., et al.: Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)
Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: Albert: a lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942 (2019)
Xu, L., Zhang, X., Dong, Q.: CLUECorpus2020: a large-scale Chinese corpus for pre-training language model. arXiv preprint arXiv:2003.01355 (2020)
You, Y., et al.: Large batch optimization for deep learning: Training bert in 76 min. arXiv preprint arXiv:1904.00962 (2019)
Smith, L.N., Topin, N.: Super-convergence: Very fast training of neural networks using large learning rates. In: Artificial intelligence and machine learning for multi-domain operations applications, p. 1100612. International Society for Optics and Photonics (2020)
Micikevicius, P., et al.: Mixed precision training. arXiv preprint arXiv:1710.03740 (2017)
Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., Neubig, G.: Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing. arXiv preprint arXiv:2107.13586 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Gao, H., Tu, X., Guan, D. (2023). SCBERT: Single Channel BERT for Chinese Spelling Correction. In: Li, B., Yue, L., Tao, C., Han, X., Calvanese, D., Amagasa, T. (eds) Web and Big Data. APWeb-WAIM 2022. Lecture Notes in Computer Science, vol 13422. Springer, Cham. https://doi.org/10.1007/978-3-031-25198-6_30
Download citation
DOI: https://doi.org/10.1007/978-3-031-25198-6_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25197-9
Online ISBN: 978-3-031-25198-6
eBook Packages: Computer ScienceComputer Science (R0)