Chinese Spelling Errors Research Articles

CMRight: Chinese Morph Resolution based on end-to-end model combined with enhancement algorithms

As the primary means of daily communication, SMS and instant messaging have the advantage of being inexpensive, but as a result, they have received the attention of practitioners in the underground industry. By using morph to bypass the regulation of platforms that mainly rely on rules, they disseminate information that draws traffic for industries such as pornography and gambling. To alleviate the above problems, existing researchers try to use the Chinese spelling error correction model, but the effect could be better. To this end, we manually analyze 11,358 deformed texts in real scenarios and identify four prevalent morph types in the field. Further, we propose a machine translation model-based algorithm for morph resolution, which achieves more than 96.2% BLEU and F1 values in the validation set. We also utilize the alignment and enhancement algorithms to improve the model performance by nearly 2.3% to 98.6%. The above results show that our proposed method can effectively identify the connection between the lexeme and the target word, thus resolving morphs and providing more efficient data support for traceability and information mining in the underground industry.

MLSL-Spell: Chinese Spelling Check Based on Multi-Label Annotation

Chinese spelling errors are commonplace in our daily lives, which might be caused by input methods, optical character recognition, or speech recognition. Due to Chinese characters’ phonetic and visual similarities, the Chinese spelling check (CSC) is a very challenging task. However, the existing CSC solutions cannot achieve good spelling check performance since they often fail to fully extract the contextual information and Pinyin information. In this paper, we propose a novel CSC framework based on multi-label annotation (MLSL-Spell), consisting of two basic phases: spelling detection and correction. In the spelling detection phase, MLSL-Spell uses the fusion vectors of both character-based pre-trained context vectors and Pinyin vectors and adopts the sequence labeling method to explicitly label the type of misspelled characters. In the spelling correction phase, MLSL-Spell uses Masked Language Mode (MLM) model to generate candidate characters, then performs corresponding screenings according to the error types, and finally screens out the correct characters through the XGBoost classifier. Experiments show that the MLSL-Spell model outperforms the benchmark model. On SIGHAN 2013 dataset, the spelling detection F1 score of MLSL-Spell is 18.3% higher than that of the pointer network (PN) model, and the spelling correction F1 score is 10.9% higher. On SIGHAN 2015 dataset, the spelling detection F1 score of MLSL-Spell is 11% higher than that of Bert and 15.7% higher than that of the PN model. And the spelling correction F1 of MLSL-Spell score is 6.8% higher than that of PN model.

Visual and Phonological Feature Enhanced Siamese BERT for Chinese Spelling Error Correction

Chinese Spelling Check (CSC) aims to detect and correct spelling errors in Chinese. Most CSC models rely on human-defined confusion sets to narrow the search space, failing to resolve errors outside the confusion set. However, most spelling errors in current benchmark datasets are character pairs in similar pronunciations. Errors in similar shapes and errors which are visually and phonologically irrelevant are not considered. Furthermore, widely-used automatically generated training data in CSC tasks leads to label leakage and unfair comparison between different methods. In this work, we propose a feature (visual and phonological) enhanced siamese BERT to (1) correct spelling errors without using confusion sets; (2) integrate phonological and visual features for CSC by a glyph graph; (3) improve performance for unseen spelling errors. To evaluate CSC methods fairly and comprehensively, we build a large-scale CSC dataset in which the number of samples in different error types is the same. The experimental results show that the proposed approach achieves better performance compared with previous state-of-the-art methods on three benchmark datasets and the new error-type balanced dataset.

Think Twice: A Post-Processing Approach for the Chinese Spelling Error Correction

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-based solution to the current deep learning method. At present, SpellGCN, proposed by Alibaba’s team, achieves the best results of which character level precision over SIGHAN2013 is 98.4%. However, when we apply this algorithm to practical error correction tasks, it produces many false error correction results. We believe that this is because the corpus used for model training contains significantly more errors than the text used for model correcting. In response to this problem, we propose performing a post-processing operation on the error correction tasks. We employ the initial model’s output as a candidate character, obtain various features of the character itself and its context, and then use a classification model to filter the initial model’s false error correction results. The post-processing idea introduced in this paper can apply to most Chinese Spelling Error Correction models to improve their performance over practical error correction tasks.

Chinese Spelling Error Detection Using a Fusion Lattice LSTM

Spelling error detection serves as a crucial preprocessing in many natural language processing applications. Unlike English, where every single word is directly typed by keyboard, we have to use an input method to input Chinese characters. The pinyin input method is the most widely used. By intuition, pinyin should be helpful in detecting spelling errors. However, when detect spelling errors, most of the current methods ignore the pinyin information and adopt a pipeline framework that leads to error propagation. In this article, we propose a fusion lattice-LSTM model under the end-to-end framework to integrate character, word, and pinyin features for error detection. Experiments on the SIGHAN Bake-off-2015 dataset show that pinyin is a discriminating feature, and our end-to-end model outperforms the baseline models obviously.

Spelling checking using conditional random fields with feature induction for secondary language learners

This paper presents a framework for Chinese spelling error detection and correction using conditional random fields (CRFs) with feature induction for secondary language learners. The trend of learning Chinese as second language is increasing recently. CRFs are adopted here as the model that models the global and local information to judge if the word is correct or not. Local features are usually considered to make the decision for intelligent systems. Herein, CRFs are one of the most used statistical approaches those which can adjust the corresponding weights for features to achieve near optimal results. This paper invested an automatic rule induction method to capture the hidden features for spellcheck in Chinese. Considering position information, the features are inducted by counting in the training corpus automatically. Therefore, the CRFs integrate the features and achieve approximated optimum by adjusting the weights corresponding to related features. From the experimental results, we can find the proposed method outperforms the traditional approaches and obtains improvement for finding the misspelled words and correcting them. It should be concluded, from what has been illustrated above that the proposed method is near to practice and useful for the learners who take Chinese as a secondary language.

A Hybrid Ranking Approach to Chinese Spelling Check

We propose a novel framework for Chinese Spelling Check (CSC), which is an automatic algorithm to detect and correct Chinese spelling errors. Our framework contains two key components: candidate generation and candidate ranking . Our framework differs from previous research, such as Statistical Machine Translation (SMT) based model or Language Model (LM) based model, in that we use both SMT and LM models as components of our framework for generating the correction candidates, in order to obtain maximum recall; to improve the precision, we further employ a Support Vector Machines (SVM) classifier to rank the candidates generated by the SMT and the LM. Experiments show that our framework outperforms other systems, which adopted the same or similar resources as ours in the SIGHAN 7 shared task; even comparing with the state-of-the-art systems, which used more resources, such as a considerable large dictionary, an idiom dictionary and other semantic information, our framework still obtains competitive results. Furthermore, to address the resource scarceness problem for training the SMT model, we generate around 2 million artificial training sentences using the Chinese character confusion sets, which include a set of Chinese characters with similar shapes and similar pronunciations, provided by the SIGHAN 7 shared task.

Chinese Spelling Checker Based on an Inverted Index List with a Rescoring Mechanism

An approach is proposed for Chinese spelling error detection and correction, in which an inverted index list with a rescoring mechanism is used. The inverted index list is a structure for mapping from word to desired sentence, and for representing nodes in lattices constructed through character expansion (according to predefined phonologically and visually similar character sets). Pruning based on a contextual dependency confidence measure was used to markedly reduce the search space and computational complexity. Relevant mapping relations between the original input and desired input were obtained using a scoring mechanism composed of class-based language and maximum entropy correction models containing character, word, and contextual features. The proposed method was evaluated using data sets provided by SigHan 7 bakeoff. The experimental results show that the proposed method achieved acceptable performance in terms of recall rate or precision rate in error sentence detection and error location detection, and it outperformed other approaches in error location detection and correction.

Correcting Chinese Spelling Errors with Word Lattice Decoding

Chinese spell checkers are more difficult to develop because of two language features: 1) there are no word boundaries, and a character may function as a word or a word morpheme; and 2) the Chinese character set contains more than ten thousand characters. The former makes it difficult for a spell checker to detect spelling errors, and the latter makes it difficult for a spell checker to construct error models. We develop a word lattice decoding model for a Chinese spell checker that addresses these difficulties. The model performs word segmentation and error correction simultaneously, thereby solving the word boundary problem. The model corrects nonword errors as well as real-word errors. In order to better estimate the error distribution of large character sets for error models, we also propose a methodology to extract spelling error samples automatically from the Google web 1T corpus. Due to the large quantity of data in the Google web 1T corpus, many spelling error samples can be extracted, better reflecting spelling error distributions in the real world. Finally, in order to improve the spell checker for real applications, we produce n-best suggestions for spelling error corrections. We test our proposed approach with the Bakeoff 2013 CSC Datasets; the results show that the proposed methods with the error model significantly outperform the performance of Chinese spell checkers that do not use error models.

Combining trigram and automatic weight distribution in Chinese spelling error correction

The researches on spelling correction aimmg at detecting errors in texts tend context-sensitive spellng error correction, which is more difficult than traditional isloated-word error correction. A novel and efficient algorithm for the system of Chinese spelling error correction, CInsunSpell, is presented. In this system, the work of correction lncludes two parts: checking phase and correcting phase. At the first phase, a Trigram algorithm within one fixed-size window is designed to locate potenuat errors in local area. This second phase employs a new method ot automatically and dynamically distributing weights among the characters in the confusion set as well as in the Bayesian language model. The tactics used abov exhibits good performances.