尝试阅读和理解 PairRE: Knowledge Graph Embeddings via Paired Relation Vectors

文章提出面临的问题

Since most knowledge graphs suffer from incompleteness, predicting missing links between entities has been a fundamental problem. This problem is named as link prediction or knowledge graph completion.

针对这个问题的解决办法

Knowledge graph embedding methods, which embed all entities and relations into alow dimensional space, have been proposed for this problem.

文章中对于这个PairRE的大概描述

The proposed model uses two vectors for relation representation. These vectors project the corresponding head and tail entities to Euclidean space, where the distance between the projected vectors is minimized.

对于这个文章即 PairRE 的贡献

Further analysis also proves that PairRE can better handle complex relations and encode symmetry/antisymmetry, inverse, composition and subrelation relations.

单词	翻译
plausibility	合理性
Hadamard product	哈达玛积，一种矩阵运算
scaling freedoms	扩展自由度
state-of-the-art	最先进的
aforementioned	前述

---

一般来说 知识图谱模型面临的两个问题为

• complex relatons 即指 1 to N | N to 1 | N to N 这几个对应关系的问题
• different relation patterns 即指 symmetry/antisymmetry, inverse and composition 这四个关系

Hadamard product 哈达玛积 是一种矩阵运算

Score Functions

Main Results

Based on performances of baselines, the performance of PairRE may be improved further if embedding dimension is increased to 500.

作者在此说明如果将维度提升至500，那么训练的效果将会更好

阅读后产生的问题

5.3中 add subrelation rules to semantic matching models对于这个不是很理解