Chinese Grammatical Error Correction Using Statistical and Neural Models

Zhou, Junpei; Li, Chen; Liu, Hengyou; Bao, Zuyi; Xu, Guangwei; Li, Linlin

doi:10.1007/978-3-319-99501-4_10

Cited by 21 publications

(14 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…YouDao [50] incorporated the vanilla transformer as the main neural translation model. AliGM [55] took the statistical language and machine translation models and the seq2seq with attention architecture as the neural machine translation to solve the grammatical problems. As for BLCU [56], the convolutional sequence-tosequence model was introduced as the main model.…”

Section: Comparison In Cgec Taskmentioning

confidence: 99%

Pre-Training-Based Grammatical Error Correction Model for the Written Language of Chinese Hearing Impaired Students

Chen

Zhang

2022

IEEE Access

View full text Add to dashboard Cite

Grammatical error correction has been considered as an application closely related to daily life and an important shared task in many prestigious competitions and workshops. The neural machine translation with an encoder-decoder architecture containing language models has been the fundamental solution for the grammatical error correction. Whereas Grammatical error correction task on texts of deaf people or its solution has not been seen yet, and common Grammatical error correction tasks are suffering several challenges, such as insufficient training data, insufficient accuracy due to the unsatisfactory capacity of extracting semantic and grammatical patterns. Under these circumstances, we proposed a novel encoderdecoder architecture based on multi-head self-attention along with multiple strategies, which excels at extracting deep representations from the corrupted sentences of deaf students and further reconstructing the sentences into grammatical ones. Via the re-ranking strategy, our model can correct various kinds of errors including spelling and complex syntax errors. The ablation experiments prove that the semantic extracting of self-attention mechanism excluding the position encoding with the word order shuffle operation can significantly learn the deaf students' sentence patterns whose word order is quite different from the ones of hearing people and improve the correction scores. The pre-training can enhance the restoring efficiency of sentence structure in the decoding process. The comparison experiments with baseline models show that our model obtains superior performance either in the deaf students' grammatical error correction or in a common grammatical error correction shared task.

show abstract

Section: Comparison In Cgec Taskmentioning

confidence: 99%

Pre-Training-Based Grammatical Error Correction Model for the Written Language of Chinese Hearing Impaired Students

Chen

Zhang

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Precision Recall F 0.5 YouDao (Fu, Huang, and Duan 2018) 35.24 18.64 29.91 AliGM (Zhou et al 2018) 41.00 13.75 29.36 BLCU (Ren, Yang, and…”

Section: Modelmentioning

confidence: 99%

“…We denote them as GECToR-BERT, GECToR-XLNet and GECToR (Ensemble) respectively. For the Chinese GEC task, we compare S2A to several best performing systems evaluated on the NLPCC-2018 dataset, including three top systems in the NLPCC-2018 challenge (YouDao (Fu, Huang, and Duan 2018), AliGM (Zhou et al 2018), BLCU (Ren, Yang, and Xun 2018)), the seq2seq baseline Char Transformer, and the current state-of-the-art method MaskGEC (Zhao and Wang 2020). Note that the proposed S2A model is orthogonal to MaskGEC, and we also report our results enhanced with the data augmentation method of MaskGEC.…”

Section: Baselinesmentioning

confidence: 99%

Sequence-to-Action: Grammatical Error Correction with Action Guided Sequence Generation

Guo

Zhang

et al. 2022

AAAI

View full text Add to dashboard Cite

The task of Grammatical Error Correction (GEC) has received remarkable attention with wide applications in Natural Language Processing (NLP) in recent years. While one of the key principles of GEC is to keep the correct parts unchanged and avoid over-correction, previous sequence-to-sequence (seq2seq) models generate results from scratch, which are not guaranteed to follow the original sentence structure and may suffer from the over-correction problem. In the meantime, the recently proposed sequence tagging models can overcome the over-correction problem by only generating edit operations, but are conditioned on human designed language-specific tagging labels. In this paper, we combine the pros and alleviate the cons of both models by proposing a novel Sequence-to-Action (S2A) module. The S2A module jointly takes the source and target sentences as input, and is able to automatically generate a token-level action sequence before predicting each token, where each action is generated from three choices named SKIP, COPY and GENerate. Then the actions are fused with the basic seq2seq framework to provide final predictions. We conduct experiments on the benchmark datasets of both English and Chinese GEC tasks. Our model consistently outperforms the seq2seq baselines, while being able to significantly alleviate the over-correction problem as well as holding better generality and diversity in the generation results compared to the sequence tagging models.

show abstract

“…• AliGM (Zhou et al 2018): The Chinese GEC system developed by Alibaba, which combines NMT-based approaches, SMT-based approaches and a rule-based approach together with various modules.…”

Section: Baselinesmentioning

confidence: 99%

MaskGEC: Improving Neural Grammatical Error Correction via Dynamic Masking

Zhao

Wang

2020

AAAI

View full text Add to dashboard Cite

Grammatical error correction (GEC) is a promising natural language processing (NLP) application, whose goal is to change the sentences with grammatical errors into the correct ones. Neural machine translation (NMT) approaches have been widely applied to this translation-like task. However, such methods need a fairly large parallel corpus of error-annotated sentence pairs, which is not easy to get especially in the field of Chinese grammatical error correction. In this paper, we propose a simple yet effective method to improve the NMT-based GEC models by dynamic masking. By adding random masks to the original source sentences dynamically in the training procedure, more diverse instances of error-corrected sentence pairs are generated to enhance the generalization ability of the grammatical error correction model without additional data. The experiments on NLPCC 2018 Task 2 show that our MaskGEC model improves the performance of the neural GEC models. Besides, our single model for Chinese GEC outperforms the current state-of-the-art ensemble system in NLPCC 2018 Task 2 without any extra knowledge.

show abstract

Chinese Grammatical Error Correction Using Statistical and Neural Models

Cited by 21 publications

References 15 publications

Pre-Training-Based Grammatical Error Correction Model for the Written Language of Chinese Hearing Impaired Students

Pre-Training-Based Grammatical Error Correction Model for the Written Language of Chinese Hearing Impaired Students

Sequence-to-Action: Grammatical Error Correction with Action Guided Sequence Generation

MaskGEC: Improving Neural Grammatical Error Correction via Dynamic Masking

Contact Info

Product

Resources

About