Research Area:  Machine Learning
Generating text from structured data is important for various tasks such as question answering and dialog systems. We show that in at least one domain, without any supervision and only based on unlabeled text, we are able to build a Natural Language Generation (NLG) system with higher performance than supervised approaches. In our approach, we interpret the structured data as a corrupt representation of the desired output and use a denoising auto-encoder to reconstruct the sentence. We show how to introduce noise into training examples that do not contain structured data, and that the resulting denoising auto-encoder generalizes to generate correct sentences when given structured data.
Keywords:  
Unsupervised
Natural Language Generation
Denoising Autoencoders
Machine Learning
Deep Learning
Author(s) Name:  Markus Freitag, Scott Roy
Journal name:  Computation and Language
Conferrence name:  
Publisher name:  arxiv
DOI:  arXiv:1804.07899
Volume Information:  
Paper Link:   https://arxiv.org/abs/1804.07899