Generating Paraphrases from DBPedia using Deep Learning
Amin Sleimi, Claire Gardent · 2016
Recent deep learning approaches to Natural Language Generation mostly rely on sequence-to-sequence models.In these approaches, the input is treated as a sequence whereas in most cases, input to generation usually is either a tree or a graph.In this paper, we describe an experiment showing how enriching a sequential input with structural information improves results and help support the generation of paraphrases.