Hierarchical character tagger for short text spelling error correction

M Gao, C Xu, P Shi - arXiv preprint arXiv:2109.14259, 2021 - arxiv.org
State-of-the-art approaches to spelling error correction problem include Transformer-based
Seq2Seq models, which require large training sets and suffer from slow inference time; and …

PTCSpell: Pre-trained Corrector Based on Character Shape and Pinyin for Chinese Spelling Correction

X Wei, J Huang, H Yu, Q Liu - Findings of the Association for …, 2023 - aclanthology.org
Chinese spelling correction (CSC) is a challenging task with the goal of correcting each
wrong character in Chinese texts. Incorrect characters in a Chinese text are mainly due to …

Context influence on sequence to sequence Turkish spelling correction

O Büyük, M Erden, LM Arslan - 2019 27th Signal Processing …, 2019 - ieeexplore.ieee.org
In this paper, we implement a Turkish spelling correction system using sequence to
sequence (seq2seq) deep neural networks (DNN). In the baseline system, the letters of the …

PGBERT: Phonology and Glyph Enhanced Pre-training for Chinese Spelling Correction

L Bao, XS Chen, J Ren, Y Liu, C Qi - CCF International Conference on …, 2022 - Springer
Abstract Chinese Spelling Correction (CSC) is a challenging task that requires the ability to
model the language and capture the implicit pattern of spelling error generation. In this …

Bi-DCSpell: A Bi-directional Detector-Corrector Interactive Framework for Chinese Spelling Check

H Wu, H Zhang, R Xuan, D Song - arXiv preprint arXiv:2406.01879, 2024 - arxiv.org
Chinese Spelling Check (CSC) aims to detect and correct potentially misspelled characters
in Chinese sentences. Naturally, it involves the detection and correction subtasks, which …

Think twice: a post-processing approach for the Chinese spelling error correction

W Gou, Z Chen - Applied Sciences, 2021 - mdpi.com
Chinese Spelling Error Correction is a hot subject in the field of natural language
processing. Researchers have already produced many great solutions, from the initial rule …

Araspell: A deep learning approach for arabic spelling correction

M Salhab, F Abu-Khzam - arXiv preprint arXiv:2405.06981, 2024 - arxiv.org
Spelling correction is the task of identifying spelling mistakes, typos, and grammatical
mistakes in a given text and correcting them according to their context and grammatical …

Deep learning-based context-sensitive spelling typing error correction

JH Lee, M Kim, HC Kwon - IEEE Access, 2020 - ieeexplore.ieee.org
This study aims to solve the context-sensitive spelling error problem for English documents.
There are two types of spelling errors in English: non-word spelling errors and context …

[HTML][HTML] EDMSpell: Incorporating the error discriminator mechanism into chinese spelling correction for the overcorrection problem

L Sheng, Z Xu, X Li, Z Jiang - Journal of King Saud University-Computer …, 2023 - Elsevier
Chinese spelling correction (CSC), which is designed to detect and correct typos in the text,
is an important and challenging task that has attracted increasing attention. Current CSC …

SweetCoat-2D: Two-Dimensional Bangla Spelling Correction and Suggestion Using Levenshtein Edit Distance and String Matching Algorithm

MM Hasan, DD Mallick, T Khan… - … Joint Conference on …, 2023 - ieeexplore.ieee.org
Autonomous spelling correction and suggestion generation for any language is a tough task
since the system must grasp context or it will create a negative impression. Our goal is to …