Quantifying Similarity between Relations with Fact Distribution

By Weize Chen, Hao Zhu, Xu Han, Zhiyuan Liu, Maosong Sun. 2019

9 citations recorded by the source corpus.

We introduce a conceptually simple and effective method to quantify the similarity between relations in knowledge bases. Specifically, our approach is based on the divergence between the conditional probability distributions over entity pairs. In this paper, these distributions are parameterized by a very simple neural network. Although computing the exact similarity is in-tractable, we provide a sampling-based method to get a good approximation. We empirically show the outputs of our approach significantly correlate with human judgments. By applying our method to various tasks, we also find that (1) our approach could effectively detect redundant relations extracted by open information extraction (Open IE) models, that (2) even the most competitive models for relational classification still make mistakes among very similar relations, and that (3) our approach could be incorporated into negative sampling and softmax classification to alleviate these mistakes.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Reza Haffari
2. Tongtong Wu
3. Guilin Qi
4. Yujin Zhu
5. Xuekai Li
6. Yuan-Fang Li
7. Guoqiang Xu

Citations in the corpus

• Curriculum-Meta Learning for Order-Robust Continual Relation Extraction (2021, methodology): “In order to calculate the semantic embedding of each relation, inspired by (Chen et al. 2019), we introduce a knowledge- and distributionbased representation learning method.”