MTCSC: Retrieval-Augmented Iterative Refinement for Chinese Spelling Correction

• URL: http://arxiv.org/abs/2504.18938v1
• Date: Sat, 26 Apr 2025 14:48:44 GMT
• Title: MTCSC: Retrieval-Augmented Iterative Refinement for Chinese Spelling Correction
• Abstract summary: Chinese Spelling Correction aims to detect and correct erroneous tokens in sentences.<n>LLMs have shown remarkable success in identifying and rectifying potential errors.<n>Existing CSC task impose rigid constraints requiring input and output lengths to be identical.
• Score: 3.2706233566525613
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Chinese Spelling Correction (CSC) aims to detect and correct erroneous tokens in sentences. While Large Language Models (LLMs) have shown remarkable success in identifying and rectifying potential errors, they often struggle with maintaining consistent output lengths and adapting to domain-specific corrections. Furthermore, existing CSC task impose rigid constraints requiring input and output lengths to be identical, limiting their applicability. In this work, we extend traditional CSC to variable-length correction scenarios, including Chinese Splitting Error Correction (CSEC) and ASR N-best Error Correction. To address domain adaptation and length consistency, we propose MTCSC (Multi-Turn CSC) framework based on RAG enhanced with a length reflection mechanism. Our approach constructs a retrieval database from domain-specific training data and dictionaries, fine-tuning retrievers to optimize performance for error-containing inputs. Additionally, we introduce a multi-source combination strategy with iterative length reflection to ensure output length fidelity. Experiments across diverse domain datasets demonstrate that our method significantly outperforms current approaches in correction quality, particularly in handling domain-specific and variable-length error correction tasks.

Related papers

• FactCorrector: A Graph-Inspired Approach to Long-Form Factuality Correction of Large Language Models [47.782867391739195]
  Large language models (LLMs) are widely used in knowledge-intensive applications but often generate factually incorrect responses.<n>We introduce FactCorrector, a new post-hoc correction method that adapts across domains without retraining.<n> Experiments on VELI5 and several popular long-form factuality datasets show that the FactCorrector approach significantly improves factual precision while preserving relevance.
  arXiv  Detail & Related papers  (2026-01-16T12:23:58Z)
• Adapting LLMs for Minimal-edit Grammatical Error Correction [0.0]
  We explore the error rate adaptation topic and propose a novel training schedule method.<n>Our experiments set a new state-of-the-art result for a single-model system on the BEA-test set.<n>We analyze whether training on detokenized datasets impacts the results and measure the impact of the usage of datasets with corrected erroneous examples.
  arXiv  Detail & Related papers  (2025-06-16T07:00:48Z)
• Chain of Correction for Full-text Speech Recognition with Large Language Models [21.37485126269991]
  Chain of Correction (CoC) for full-text error correction with Large Language Models (LLMs)<n>CoC corrects errors segment by segment using pre-recognized text as guidance within a regular multi-turn chat format.<n>We analyze how to set the correction threshold to balance under-correction and over-rephrasing.
  arXiv  Detail & Related papers  (2025-04-02T09:06:23Z)
• A Training-free LLM-based Approach to General Chinese Character Error Correction [31.511249971873962]
  Chinese spelling correction (CSC) is a crucial task that aims to correct character errors in Chinese text. We introduce the task of General Chinese Character Error Correction (C2EC), which focuses on all three types of character errors. We extend the training-free prompt-free CSC method to C2EC by using Levenshtein distance for handling length changes and leveraging an additional prompt-based large language model (LLM) to improve performance.
  arXiv  Detail & Related papers  (2025-02-21T07:48:54Z)
• Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentation [73.9145653659403]
  We show that Generative Error Correction models struggle to generalize beyond the specific types of errors encountered during training. We propose DARAG, a novel approach designed to improve GEC for ASR in in-domain (ID) and OOD scenarios. Our approach is simple, scalable, and both domain- and language-agnostic.
  arXiv  Detail & Related papers  (2024-10-17T04:00:29Z)
• A Coin Has Two Sides: A Novel Detector-Corrector Framework for Chinese Spelling Correction [79.52464132360618]
  Chinese Spelling Correction (CSC) stands as a foundational Natural Language Processing (NLP) task. We introduce a novel approach based on error detector-corrector framework. Our detector is designed to yield two error detection results, each characterized by high precision and recall.
  arXiv  Detail & Related papers  (2024-09-06T09:26:45Z)
• C-LLM: Learn to Check Chinese Spelling Errors Character by Character [61.53865964535705]
  We propose C-LLM, a Large Language Model-based Chinese Spell Checking method that learns to check errors Character by Character. C-LLM achieves an average improvement of 10% over existing methods.
  arXiv  Detail & Related papers  (2024-06-24T11:16:31Z)
• LM-Combiner: A Contextual Rewriting Model for Chinese Grammatical Error Correction [49.0746090186582]
  Over-correction is a critical problem in Chinese grammatical error correction (CGEC) task. Recent work using model ensemble methods can effectively mitigate over-correction and improve the precision of the GEC system. We propose the LM-Combiner, a rewriting model that can directly modify the over-correction of GEC system outputs without a model ensemble.
  arXiv  Detail & Related papers  (2024-03-26T06:12:21Z)
• Chinese Spelling Correction as Rephrasing Language Model [63.65217759957206]
  We study Chinese Spelling Correction (CSC), which aims to detect and correct the potential spelling errors in a given sentence. Current state-of-the-art methods regard CSC as a sequence tagging task and fine-tune BERT-based models on sentence pairs. We propose Rephrasing Language Model (ReLM), where the model is trained to rephrase the entire sentence by infilling additional slots, instead of character-to-character tagging.
  arXiv  Detail & Related papers  (2023-08-17T06:04:28Z)
• Error-Robust Retrieval for Chinese Spelling Check [43.56073620728942]
  Chinese Spelling Check (CSC) aims to detect and correct error tokens in Chinese contexts. Previous methods may not fully leverage the existing datasets. We introduce our plug-and-play retrieval method with error-robust information for Chinese Spelling Check.
  arXiv  Detail & Related papers  (2022-11-15T01:55:34Z)
• Improving Chinese Spelling Check by Character Pronunciation Prediction: The Effects of Adaptivity and Granularity [76.20568599642799]
  Chinese spelling check (CSC) is a fundamental NLP task that detects and corrects spelling errors in Chinese texts. In this paper, we consider introducing an auxiliary task of Chinese pronunciation prediction ( CPP) to improve CSC. We propose SCOPE which builds on top of a shared encoder two parallel decoders, one for the primary CSC task and the other for a fine-grained auxiliary CPP task.
  arXiv  Detail & Related papers  (2022-10-20T03:42:35Z)
• uChecker: Masked Pretrained Language Models as Unsupervised Chinese Spelling Checkers [23.343006562849126]
  We propose a framework named textbfuChecker to conduct unsupervised spelling error detection and correction. Masked pretrained language models such as BERT are introduced as the backbone model. Benefiting from the various and flexible MASKing operations, we propose a Confusionset-guided masking strategy to fine-train the masked language model.
  arXiv  Detail & Related papers  (2022-09-15T05:57:12Z)
• Tail-to-Tail Non-Autoregressive Sequence Prediction for Chinese Grammatical Error Correction [49.25830718574892]
  We present a new framework named Tail-to-Tail (textbfTtT) non-autoregressive sequence prediction. Considering that most tokens are correct and can be conveyed directly from source to target, and the error positions can be estimated and corrected. Experimental results on standard datasets, especially on the variable-length datasets, demonstrate the effectiveness of TtT in terms of sentence-level Accuracy, Precision, Recall, and F1-Measure.
  arXiv  Detail & Related papers  (2021-06-03T05:56:57Z)
• Improving the Efficiency of Grammatical Error Correction with Erroneous Span Detection and Correction [106.63733511672721]
  We propose a novel language-independent approach to improve the efficiency for Grammatical Error Correction (GEC) by dividing the task into two subtasks: Erroneous Span Detection ( ESD) and Erroneous Span Correction (ESC) ESD identifies grammatically incorrect text spans with an efficient sequence tagging model. ESC leverages a seq2seq model to take the sentence with annotated erroneous spans as input and only outputs the corrected text for these spans. Experiments show our approach performs comparably to conventional seq2seq approaches in both English and Chinese GEC benchmarks with less than 50% time cost for inference.
  arXiv  Detail & Related papers  (2020-10-07T08:29:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.