小模型用语言特征精准识别多词表达，性能超大模型
Binary Token-Level Classification with DeBERTa for All-Type MWE Identification: A Lightweight Approach with Linguistic Enhancement
- 将识别任务转为二元标记分类，提升精度与效率
- 在CoAM数据集上达69.8% F1，比大模型高12个百分点
- 适合资源受限场景，尤其对复杂结构表达识别有效
我们提出一种针对多词表达（MWE）识别的综合方法，结合二元标记级分类、语言学特征融合与数据增强。所用DeBERTa-v3-large模型在CoAM数据集上取得69.8% F1，相比最佳基准（Qwen-72B，57.8% F1）提升12个百分点，参数量仅为后者的1/165。性能提升源于三点：(1) 将检测任务重构为二元标记级START/END/INSIDE分类，而非跨度预测；(2) 融入名词短语分块与依存句法特征，显著提升非连续及名词类MWE识别效果；(3) 采用过采样缓解训练数据严重类别不平衡问题。该方法在STREUSLE数据集上验证泛化能力，达78.9% F1。结果表明，精心设计的小模型可在结构化NLP任务中显著超越大语言模型，对资源受限部署具有重要意义。
原文摘要 · Abstract (English)
We present a comprehensive approach for multiword expression (MWE) identification that combines binary token-level classification, linguistic feature integration, and data augmentation. Our DeBERTa-v3-large model achieves 69.8% F1 on the CoAM dataset, surpassing the best results (Qwen-72B, 57.8% F1) on this dataset by 12 points while using 165x fewer parameters. We achieve this performance by (1) reformulating detection as binary token-level START/END/INSIDE classification rather than span-based prediction, (2) incorporating NP chunking and dependency features that help discontinuous and NOUN-type MWEs identification, and (3) applying oversampling that addresses severe class imbalance in the training data. We confirm the generalization of our method on the STREUSLE dataset, achieving 78.9% F1. These results demonstrate that carefully designed smaller models can substantially outperform LLMs on structured NLP tasks, with important implications for resource-constrained deployments.
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。