统一弧与标签评分，提升依存句法分析效率与准确率
Scaling Graph-Based Dependency Parsing with Arc Vectorization and Attention-Based Refinement
- 用向量统一建模弧与标签得分
- 在PTB和UD上达到更高精度与更快速度
- 适合需要高效句法分析的NLP应用
我们提出一种新型图结构依存句法分析架构，显式构建向量以同时进行弧与标签的打分。该方法通过将弧评分与标签识别整合进单一网络，克服了传统两阶段流程中的信息瓶颈与参数不共享问题，有效缓解可扩展性挑战。此外，通过引入基于注意力的优化机制，增强了变压器层对高阶依赖关系的模拟能力。在PTB与UD数据集上的实验表明，该模型在准确率与效率方面均超越现有最优解析器。
原文摘要 · Abstract (English)
We propose a novel architecture for graph-based dependency parsing that explicitly constructs vectors, from which both arcs and labels are scored. Our method addresses key limitations of the standard two-pipeline approach by unifying arc scoring and labeling into a single network, reducing scalability issues caused by the information bottleneck and lack of parameter sharing. Additionally, our architecture overcomes limited arc interactions with transformer layers to efficiently simulate higher-order dependencies. Experiments on PTB and UD show that our model outperforms state-of-the-art parsers in both accuracy and efficiency.
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。