In the field of natural language understanding, the intersection of neural models and graph meaning representations (GMRs) remains a compelling area of research. Despite the growing interest, a critical gap persists in understanding the exact influence of GMRs, particularly concerning relation extraction tasks. Addressing this, we introduce DAGNN-plus, a simple and parameter-efficient neural architecture designed to decouple contextual representation learning from structural information propagation. Coupled with various sequence encoders and GMRs, this architecture provides a foundation for systematic experimentation on two English and two Chinese datasets. Our empirical analysis utilizes four different graph formalisms and nine parsers. The results yield a nuanced understanding of GMRs, showing improvements in three out of the four datasets, particularly favoring English over Chinese due to highly accurate parsers. Interestingly, GMRs appear less effective in literary-domain datasets compared to general-domain datasets. These findings lay the groundwork for better-informed design of GMRs and parsers to improve relation classification, which is expected to tangibly impact the future trajectory of natural language understanding research.

翻译：在自然语言理解领域，神经模型与图义表示（GMR）的交叉仍是一个引人注目的研究方向。尽管兴趣日益增长，但在理解GMR对关系提取任务具体影响方面仍存在关键空白。针对这一问题，我们提出DAGNN-plus——一种简洁且参数高效的神经架构，旨在将上下文表示学习与结构信息传播相解耦。该架构结合多种序列编码器和图义表示，为在四个数据集（两个英文、两个中文）上开展系统性实验奠定了基础。我们的实证分析采用了四种不同的图形式与九个解析器。结果表明，对GMR的理解更为细致：四个数据集中有三个性能得到提升，其中英文数据集因高精度解析器而表现尤为突出。值得注意的是，在文学领域数据集中，GMR的效果弱于通用领域数据集。这些发现为更合理地设计GMR与解析器以改进关系分类奠定了基础，有望实质性地影响自然语言理解研究的未来发展方向。