id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_3nicn4x7u5bbvf6ajajnu73nbi	Diego Marcheggiani	Discrete-State Variational Autoencoders for Joint Discovery and Factorization of Relations	2016	15	.pdf	application/pdf	8830	823	59	https://www.research.ed.ac.uk/portal/en/publications/discretestate-variational-autoencoders-for-joint-discovery-and-factorization-of-relations(7b6ff228-0589-4b78-bf5c-289ee79084d8).html relation between two entities, and a factorization model, which reconstructs arguments extractor which predicts a semantic relation between two entities in a specific sentence given The use of a reconstruction-error objective, previously considered primarily in the context of training neural autoencoders (Hinton, 1989; Vincent et also qualitatively evaluate our model by both considering several examples of induced relations (both the semantic relation r = REVIEWED.1 The standard approach to this task is to either rely on human annotated data (i.e., supervised learning) or use 1In some of our examples we will use relation names, although our method, as virtually any other latent variable model, In this work we explore three different factorizations ψ for the decoding component: a tensor factorization model inspired by previous work on relation factorization, a simple selectional-preference that we train the relation classifier (i.e., the encoding model), unlike some of the previous approaches,	./cache/work_3nicn4x7u5bbvf6ajajnu73nbi.pdf	./txt/work_3nicn4x7u5bbvf6ajajnu73nbi.txt