Leveraging Lexical Resources for Learning Entity Embeddings in Multi-Relational Data

• DOI: 10.18653/v1/p16-2019
• Publication Date: 2016-08-13T19:45:39Z
• Authors: Teng Long; Ryan Lowe; Jackie Chi Kit Ch...; Doina Precup
• Keywords: Statistical relational learning

Recent work in learning vector-space embeddings for multi-relational data has focused on combining relational information derived from knowledge bases with distributional large text corpora. We propose a simple approach that leverages the descriptions of entities or phrases available lexical resources, conjunction semantics, order to derive better initialization training models. Applying this TransE model results significant new state-of-the-art performances WordNet dataset, decreasing mean rank previous best 212 51. It also faster convergence entity representations. find there is trade-off between improving and hits@10 approach. This illustrates much remains be understood regarding performance improvements