Phrase-level attention network for few-shot inverse relation classification in knowledge graph-猫眼课题宝

DOI：

10.1007/s11280-023-01142-6

发表时间：

2023-05

期刊：

World Wide Web

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Shaojuan Wu;Chunliu Dou;Dazhuang Wang;Jitong Li;Xiaowang Zhang;Zhiyong Feng;Kewen Wang;Sofonias Yitagesu

关系分类旨在识别给定文本中提到的两个给定实体之间的语义关系。现有模型在大规模数据集的逆关系分类上表现良好，但对于小样本学习，其性能显着下降。在本文中，我们提出了一种短语级注意力网络，即功能词自适应增强注意框架（FAEA+），通过为知识图谱中的少样本逆关系分类设计的混合注意力来关注与类相关的功能词。然后，提出了一个实例感知原型网络来自适应地捕获与查询实例相关的关系信息，并消除由于引入的功能词而导致的类内冗余。我们从理论上证明，功能词的引入会增加类内差异，并且设计的实例感知原型网络能够减少冗余。实验结果表明，在两个少镜头关系分类数据集上，FAEA+ 比强基线有了显着改进。此外，我们的模型在解决逆关系方面具有明显的优势，在 FewRel1.0 的 1-shot 设置下，其性能比最先进的结果高 16.82%。

Relation classification aims to recognize semantic relation between two given entities mentioned in the given text. Existing models have performed well on the inverse relation classification with large-scale datasets, but their performance drops significantly for few-shot learning. In this paper, we propose a Phrase-level Attention Network, function words adaptively enhanced attention framework (FAEA+), to attend class-related function words by the designed hybrid attention for few-shot inverse relation classification in Knowledge Graph. Then, an instance-aware prototype network is present to adaptively capture relation information associated with query instances and eliminate intra-class redundancy due to function words introduced. We theoretically prove that the introduction of function words will increase intra-class differences, and the designed instance-aware prototype network is competent for reducing redundancy. Experimental results show that FAEA+ significantly improved over strong baselines on two few-shot relation classification datasets. Moreover, our model has a distinct advantage in solving inverse relations, which outperforms state-of-the-art results by 16.82% under a 1-shot setting in FewRel1.0.

Phrase-level attention network for few-shot inverse relation classification in knowledge graph

文献摘要

相似文献