A Chinese Spelling Check Framework Based on Reverse Contrastive Learning

• URL: http://arxiv.org/abs/2210.13823v2
• Date: Thu, 6 Jul 2023 07:34:14 GMT
• Title: A Chinese Spelling Check Framework Based on Reverse Contrastive Learning
• Authors: Nankai Lin, Hongyan Wu, Sihui Fu, Shengyi Jiang, Aimin Yang
• Abstract summary: We present a novel framework for Chinese spelling checking, which consists of three modules: language representation, spelling check and reverse contrastive learning. Specifically, we propose a reverse contrastive learning strategy, which explicitly forces the model to minimize the agreement between the similar examples. Experimental results show that our framework is model-agnostic and could be combined with existing Chinese spelling check models to yield state-of-the-art performance.
• Score: 4.60495447017298
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Chinese spelling check is a task to detect and correct spelling mistakes in Chinese text. Existing research aims to enhance the text representation and use multi-source information to improve the detection and correction capabilities of models, but does not pay too much attention to improving their ability to distinguish between confusable words. Contrastive learning, whose aim is to minimize the distance in representation space between similar sample pairs, has recently become a dominant technique in natural language processing. Inspired by contrastive learning, we present a novel framework for Chinese spelling checking, which consists of three modules: language representation, spelling check and reverse contrastive learning. Specifically, we propose a reverse contrastive learning strategy, which explicitly forces the model to minimize the agreement between the similar examples, namely, the phonetically and visually confusable characters. Experimental results show that our framework is model-agnostic and could be combined with existing Chinese spelling check models to yield state-of-the-art performance.

Related papers

• FINEMATCH: Aspect-based Fine-grained Image and Text Mismatch Detection and Correction [66.98008357232428]
  We propose FineMatch, a new aspect-based fine-grained text and image matching benchmark. FineMatch focuses on text and image mismatch detection and correction. We show that models trained on FineMatch demonstrate enhanced proficiency in detecting fine-grained text and image mismatches.
  arXiv  Detail & Related papers  (2024-04-23T03:42:14Z)
• Pixel Sentence Representation Learning [67.4775296225521]
  In this work, we conceptualize the learning of sentence-level textual semantics as a visual representation learning process. We employ visually-grounded text perturbation methods like typos and word order shuffling, resonating with human cognitive patterns, and enabling perturbation to be perceived as continuous. Our approach is further bolstered by large-scale unsupervised topical alignment training and natural language inference supervision.
  arXiv  Detail & Related papers  (2024-02-13T02:46:45Z)
• An Adversarial Multi-Task Learning Method for Chinese Text Correction with Semantic Detection [0.0]
  adversarial multi-task learning method is proposed to enhance the modeling and detection ability of character polysemy in Chinese sentence context. Monte Carlo tree search strategy and a policy network are introduced to accomplish the efficient Chinese text correction task with semantic detection.
  arXiv  Detail & Related papers  (2023-06-28T15:46:00Z)
• ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting [121.11880210592497]
  We argue that the limited capacity of language models comes from 1) implicit language modeling; 2) unidirectional feature representation; and 3) language model with noise input. We propose an autonomous, bidirectional and iterative ABINet++ for scene text spotting.
  arXiv  Detail & Related papers  (2022-11-19T03:50:33Z)
• Improving Chinese Story Generation via Awareness of Syntactic Dependencies and Semantics [17.04903530992664]
  We present a new generation framework that enhances the feature mechanism by informing the generation model of dependencies between words. We conduct a range of experiments, and the results demonstrate that our framework outperforms the state-of-the-art Chinese generation models on all evaluation metrics.
  arXiv  Detail & Related papers  (2022-10-19T15:01:52Z)
• Improving Pre-trained Language Models with Syntactic Dependency Prediction Task for Chinese Semantic Error Recognition [52.55136323341319]
  Existing Chinese text error detection mainly focuses on spelling and simple grammatical errors. Chinese semantic errors are understudied and more complex that humans cannot easily recognize.
  arXiv  Detail & Related papers  (2022-04-15T13:55:32Z)
• Read, Listen, and See: Leveraging Multimodal Information Helps Chinese Spell Checking [20.74049189959078]
  We propose a Chinese spell checker called ReaLiSe, by directly leveraging the multimodal information of the Chinese characters. The ReaLiSe tackles model the CSC task by (1) capturing the semantic, phonetic and graphic information of the input characters, and (2) mixing the information in these modalities to predict the correct output. Experiments on the SIGHAN benchmarks show that the proposed model outperforms strong baselines by a large margin.
  arXiv  Detail & Related papers  (2021-05-26T02:38:11Z)
• An Alignment-Agnostic Model for Chinese Text Error Correction [17.429266115653007]
  This paper investigates how to correct Chinese text errors with types of mistaken, missing and redundant characters. Most existing models can correct mistaken characters errors, but they cannot deal with missing or redundant characters. We propose a novel detect-correct framework which is alignment-agnostic, meaning that it can handle both text aligned and non-aligned occasions.
  arXiv  Detail & Related papers  (2021-04-15T01:17:34Z)
• LET: Linguistic Knowledge Enhanced Graph Transformer for Chinese Short Text Matching [29.318730227080675]
  We introduce HowNet as an external knowledge base and propose a Linguistic knowledge Enhanced graph Transformer (LET) to deal with word ambiguity. Experimental results on two Chinese datasets show that our models outperform various typical text matching approaches.
  arXiv  Detail & Related papers  (2021-02-25T04:01:51Z)
• SLUA: A Super Lightweight Unsupervised Word Alignment Model via Cross-Lingual Contrastive Learning [79.91678610678885]
  We propose a super lightweight unsupervised word alignment model (SLUA) Experimental results on several public benchmarks demonstrate that our model achieves competitive, if not better, performance. Notably, we recognize our model as a pioneer attempt to unify bilingual word embedding and word alignments.
  arXiv  Detail & Related papers  (2021-02-08T05:54:11Z)
• Probing Contextual Language Models for Common Ground with Visual Representations [76.05769268286038]
  We design a probing model that evaluates how effective are text-only representations in distinguishing between matching and non-matching visual representations. Our findings show that language representations alone provide a strong signal for retrieving image patches from the correct object categories. Visually grounded language models slightly outperform text-only language models in instance retrieval, but greatly under-perform humans.
  arXiv  Detail & Related papers  (2020-05-01T21:28:28Z)

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.