Entity summarization aims at creating brief but informative descriptions of entities from knowledge graphs. While previous work mostly focused on traditional techniques such as clustering algorithms and graph models, we ask how to apply deep learning methods into this task. In this paper we propose ESA, a neural network with supervised attention mechanisms for entity summarization. Specifically, we calculate attention weights for facts in each entity, and rank facts to generate reliable summaries. We explore techniques to solve difficult learning problems presented by the ESA, and demonstrate the effectiveness of our model in comparison with the state-of-the-art methods. Experimental results show that our model improves the quality of the entity summaries in both F-measure and MAP.
@article{arxiv.1905.10625,
title = {ESA: Entity Summarization with Attention},
author = {Dongjun Wei and Yaxin Liu and Fuqing Zhu and Liangjun Zang and Wei Zhou and Jizhong Han and Songlin Hu},
journal= {arXiv preprint arXiv:1905.10625},
year = {2020}
}