用标签置信度加权训练模型，提升句子简化效果。
Label Confidence Weighted Learning for Target-level Sentence Simplification
- 在编码器-解码器框架中引入标签置信度加权损失
- 在英文分级简化数据集上超越现有无监督基线
- 适合需要精准控制语言难度的文本简化任务
多级句子简化生成不同语言水平的简化句。我们提出标签置信度加权学习（LCWL），在编码器-解码器模型的训练损失中引入标签置信度加权机制，区别于以往主要面向分类任务的置信度加权方法。在英文分级简化数据集上的实验表明，LCWL优于当前最优的无监督基线。在领域内数据上微调并结合对称交叉熵（SCE）后，其简化效果持续优于强监督方法。结果表明，标签置信度加权技术在基于编码器-解码器架构的文本简化任务中具有显著有效性。
原文摘要 · Abstract (English)
Multi-level sentence simplification generates simplified sentences with varying language proficiency levels. We propose Label Confidence Weighted Learning (LCWL), a novel approach that incorporates a label confidence weighting scheme in the training loss of the encoder-decoder model, setting it apart from existing confidence-weighting methods primarily designed for classification. Experimentation on English grade-level simplification dataset shows that LCWL outperforms state-of-the-art unsupervised baselines. Fine-tuning the LCWL model on in-domain data and combining with Symmetric Cross Entropy (SCE) consistently delivers better simplifications compared to strong supervised methods. Our results highlight the effectiveness of label confidence weighting techniques for text simplification tasks with encoder-decoder architectures.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。