Weighted Aggregator for the Open-World Knowledge Graph Completion

Open-world knowledge graph completion aims to find a set of missing triples through entity description, where entities can be either in or out of the graph. However, when aggregating entity description’s word embedding matrix to a single embedding, most existing models either use CNN and LSTM to make the model complex and ineffective, or use simple semantic averaging which neglects the unequal nature of the different words of an entity description. In this paper, an aggregator is proposed, adopting an attention network to get the weights of words in the entity description. This does not upset information in the word embedding, and make the single embedding of aggregation more efficient. Compared with state-of-the-art systems, experiments show that the model proposed performs well in the open-world KGC task.