@InProceedings{feng-EtAl:2016:COLING1,
  author    = {Feng, Jun  and  Huang, Minlie  and  Yang, Yang  and  zhu, xiaoyan},
  title     = {GAKE: Graph Aware Knowledge Embedding},
  booktitle = {Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {641--651},
  abstract  = {Knowledge embedding, which projects triples in a given knowledge base to
	d-dimensional vectors,
	has attracted considerable research efforts recently. Most existing approaches
	treat the given
	knowledge base as a set of triplets, each of whose representation is then
	learned separately. However, as a fact, triples are connected and depend on
	each other. 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. We also design an
	attention mechanism to learn representative power of different vertices or
	edges. To validate our method, we conduct several experiments on two tasks.
	Experimental results
	suggest that our method outperforms several state-of-art knowledge embedding
	models.
	Author{4}{Affiliation}},
  url       = {http://aclweb.org/anthology/C16-1062}
}