Traditionally, Referring Expression Generation (REG) models first decide on the form and then on the content of references to discourse entities in text, typically relying on features such as salience and grammatical function. In this paper, we present a new approach (NeuralREG), relying on deep neural networks, which makes decisions about form and content in one go without explicit feature extraction. Using a delexicalized version of the WebNLG corpus, we show that the neural model substantially improves over two strong baselines. Data and models are publicly available.
@article{arxiv.1805.08093,
title = {NeuralREG: An end-to-end approach to referring expression generation},
author = {Thiago Castro Ferreira and Diego Moussallem and Ákos Kádár and Sander Wubben and Emiel Krahmer},
journal= {arXiv preprint arXiv:1805.08093},
year = {2018}
}