Scholarlink

<p>To improve the robustness of text classifiers under spelling errors and semantic ambiguity, we propose NoiseDiffuser (ND), a task-oriented text augmentation framework inspired by diffusion-based perturbation and recovery principles. ND incorporates two key mechanisms. First, a length-aware dynamic noise schedule adjusts perturbation intensity according to text length, allowing stronger perturbations for redundant long documents and weaker perturbations for semantically sparse short texts. Second, a lightweight multilingual semantic recovery strategy uses HIT-CIR Tongyici Cilin for Chinese and WordNet for English to support synonym-based perturbation and lexical filtering. Evaluated on six corpora (e.g., THUCNews, 20Newsgroups), ND reduces the absolute magnitude of the generalization gap by 41.7%, increases feature cosine similarity by up to 33.33%, and reduces FGSM-induced accuracy degradation by approximately 40%. Furthermore, under TextFooler word-level adversarial attacks, ND-enhanced models achieve higher accuracy in most settings than baseline models. ND improves short-text F1 scores of baseline classifiers and BERT by approximately 38.63%. Overall, ND offers an efficient and compatible augmentation strategy for text classification in noisy environments while largely preserving the original semantics.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A diffusion-inspired noise augmentation framework for robust multilingual text classification

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月29日

查看全文
  • Ming Gao,
  • Yuanfa Cen,
  • Haifeng Liu,
  • Xiaoming Zuo,
  • Ling Yuan,
  • Guocan Fu,
  • Zhisheng Tan

摘要

To improve the robustness of text classifiers under spelling errors and semantic ambiguity, we propose NoiseDiffuser (ND), a task-oriented text augmentation framework inspired by diffusion-based perturbation and recovery principles. ND incorporates two key mechanisms. First, a length-aware dynamic noise schedule adjusts perturbation intensity according to text length, allowing stronger perturbations for redundant long documents and weaker perturbations for semantically sparse short texts. Second, a lightweight multilingual semantic recovery strategy uses HIT-CIR Tongyici Cilin for Chinese and WordNet for English to support synonym-based perturbation and lexical filtering. Evaluated on six corpora (e.g., THUCNews, 20Newsgroups), ND reduces the absolute magnitude of the generalization gap by 41.7%, increases feature cosine similarity by up to 33.33%, and reduces FGSM-induced accuracy degradation by approximately 40%. Furthermore, under TextFooler word-level adversarial attacks, ND-enhanced models achieve higher accuracy in most settings than baseline models. ND improves short-text F1 scores of baseline classifiers and BERT by approximately 38.63%. Overall, ND offers an efficient and compatible augmentation strategy for text classification in noisy environments while largely preserving the original semantics.