papers AI Learner
The Github is limit! Click to go to the new site.

Link Prediction with Mutual Attention for Text-Attributed Networks

2019-02-28
Robin Brochier, Adrien Guille, Julien Velcin

Abstract

In this extended abstract, we present an algorithm that learns a similarity measure between documents from the network topology of a structured corpus. We leverage the Scaled Dot-Product Attention, a recently proposed attention mechanism, to design a mutual attention mechanism between pairs of documents. To train its parameters, we use the network links as supervision. We provide preliminary experiment results with a citation dataset on two prediction tasks, demonstrating the capacity of our model to learn a meaningful textual similarity.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1902.11054

PDF

http://arxiv.org/pdf/1902.11054


Similar Posts

Comments