arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.09772cs.CL
收藏

重新思考基于图意义表示的关系分类

Rethinking Relation Classification with Graph Meaning Representations

University of Electronic Science and Technology of China(电子科技大学);University of Copenhagen(哥本哈根大学)

Li Zhou, Wenyu Chen, Dingyi Zeng, Malu Zhang, Daniel Hershcovich

AI总结:

本文提出DAGNN-plus架构,解耦上下文学习与结构传播,在四个数据集上系统评估图意义表示对关系分类的影响,发现其在多数数据集上有效,且英文优于中文、通用领域优于文学领域。

摘要:

在自然语言理解领域,神经模型与图意义表示(GMRs)的交汇仍是一个引人关注的研究方向。尽管兴趣日益增长,但关于GMRs确切影响的理解仍存在关键空白,尤其是在关系抽取任务方面。针对这一问题,我们引入了DAGNN-plus,一种简单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解耦。该架构与多种序列编码器和GMRs相结合,为在两个英文和两个中文数据集上的系统性实验提供了基础。我们的实证分析利用了四种不同的图形式体系和九种解析器。结果对GMRs产生了细致入微的理解,显示在四个数据集中的三个上有所改进,尤其由于高精度的解析器,英文表现优于中文。有趣的是,与通用领域数据集相比,GMRs在文学领域数据集上的效果似乎较差。这些发现为更好地设计GMRs和解析器以改进关系分类奠定了基础,预计将对自然语言理解研究的未来轨迹产生实质性影响。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑