learning multi faceted knowledge graph embeddings for natural language processing
Abstract
Knowledge graphs have challenged the existing embedding-based approaches for representing their multifacetedness. To address some of the issues, we have investigated some novel approaches that (i) capture the multilingual transitions on different language-specific versions of knowledge, and (ii) encode the commonly existing monolingual knowledge with important relational properties and hierarchies. In addition, we propose the use of our approaches in a wide spectrum of NLP tasks that have not been well explored by related works.