id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-024501-nl0gsr0c	Tan, Chunyang	MSGE: A Multi-step Gated Model for Knowledge Graph Completion	2020-04-17		.txt	text/plain	3236	206	55	In this paper, we first integrate iterative mechanism into knowledge graph embedding and propose a multi-step gated model which utilizes relations as queries to extract useful information from coarse to fine in multiple steps. First gate mechanism is adopted to control information flow by the interaction between entity and relation with multiple steps. In this paper, we propose a Multi-Step Gated Embedding (MSGE) model for link prediction in KGs. During every step, gate mechanism is applied several times, which is used to decide what features are retained and what are excluded at the dimension level, corresponding to the multi-step reasoning procedure. All results demonstrate our motivation that controlling information flow in a multi-step way is beneficial for link prediction task in knowledge graphs. In this paper, we propose a multi-step gated model MSGE for link prediction task in knowledge graph completion.	./cache/cord-024501-nl0gsr0c.txt	./txt/cord-024501-nl0gsr0c.txt