http://yangy.org/works/gake/gake-coling16.pdf Jun Feng, Minlie Huang, Yang Yang, and Xiaoyan Zhu. 2016. GAKE: Graph Aware Knowledge Embedding. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 641–651, Osaka, Japan. The COLING 2016 Organizing Committee. GitHub -> https://github.com/JuneFeng/GAKE Abstract In this paper, we propose a graph aware knowledge embedding method (GAKE), which formulates knowledge base as a directed graph, and learns representations for any vertices or edges by leveraging the graph’s structural information. We introduce three types of graph context for embedding: neighbor context, path context, and edge context, each reflects properties of knowledge from different perspectives. [Aqui o contexto é dado pela estrutura do grafo, as interligações. É sintático ou semântico? ] 1 Introduction In this way, we see that most of existing methods only consider “one hop” information ab
