Recent years have seen the dependency tree as effective information for relation extraction. Two problems still exist in previous methods: (1) dependency tree relies on external tools and needs to be carefully integrated with a trade-off between pruning noisy words and keeping semantic integrity; (2) dependency-based methods still have to encode sequential context as a supplement, which needs extra time. To tackle the two problems, we propose a faster dependency-free model in this paper: regarding the sentence as a fully-connected graph, we customize the vanilla transformer architecture to remove the irrelevant information via filtering mechanism and further aggregate the sentence information through the enhanced query. Our model yields comparable results on the SemEval2010 Task8 dataset and better results on the TACRED dataset, without requiring external information from the dependency tree but with improved time efficiency.

近年来，依赖树已成为关系提取的有效信息。以前的方法中仍然存在两个问题：（1）依赖树依赖于外部工具，需要在修剪嘈杂单词和保持语义完整性之间进行权衡的情况下进行仔细集成；（2）基于依存关系的方法仍然必须编码顺序上下文作为补充，这需要额外的时间。为了解决这两个问题，我们在本文中提出了一个更快的无依赖模型：将句子作为一个完全连接的图，我们定制了香草转换器架构，以通过过滤机制去除无关信息，并进一步通过过滤机制聚合句子信息。增强查询。我们的模型在SemEval2010 Task8数据集上可获得可比的结果，而在TACRED数据集上可获得更好的结果，