Tackling Long-Tailed Relations and Uncommon Entities in Knowledge Graph Completion
Refereed conference paper presented and published in conference proceedings


Full Text

Other information
AbstractFor large-scale knowledge graphs (KGs), recent research has been focusing on the large proportion of infrequent relations which have been ignored by previous studies. For example few-shot learning paradigm for relations
has been investigated. In this work, we further advocate that handling uncommon entities is
inevitable when dealing with infrequent relations. Therefore, we propose a meta-learning framework that aims at handling infrequent relations with few-shot learning and uncommon entities by using textual descriptions. We design
a novel model to better extract key information from textual descriptions. Besides, we also develop a novel generative model in our framework to enhance the performance by generating extra triplets during the training
stage. Experiments are conducted on two datasets from real-world KGs, and the results show that our framework 1 outperforms previous methods when dealing with infrequent relations and their accompanying uncommon entities.
Acceptance Date13/08/2019
All Author(s) ListZihao Wang, Kwun Ping Lai, Piji Li, Lidong Bing, Wai Lam
Name of ConferenceConference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Start Date of Conference03/11/2019
End Date of Conference07/11/2019
Place of ConferenceHong Kong
Country/Region of ConferenceChina
Proceedings TitleProceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing
Year2019
Month11
Day3
Pages250 - 260
LanguagesEnglish-United States

Last updated on 2021-07-01 at 12:28