A Survey of Natural Language Generation

TL;DR

This survey comprehensively reviews two decades of NLG research, focusing on deep learning methods, tasks, datasets, evaluation challenges, and future directions, highlighting the integration with other AI fields.

Contribution

It provides an extensive synthesis of deep learning architectures, tasks, datasets, evaluation methods, and future research issues in Natural Language Generation.

Findings

Deep learning has significantly advanced NLG core tasks.

Evaluation of NLG remains challenging with diverse methods.

Future research will increasingly integrate NLG with other AI domains.

Abstract

This paper offers a comprehensive review of the research on Natural Language Generation (NLG) over the past two decades, especially in relation to data-to-text generation and text-to-text generation deep learning methods, as well as new applications of NLG technology. This survey aims to (a) give the latest synthesis of deep learning research on the NLG core tasks, as well as the architectures adopted in the field; (b) detail meticulously and comprehensively various NLG tasks and datasets, and draw attention to the challenges in NLG evaluation, focusing on different evaluation methods and their relationships; (c) highlight some future emphasis and relatively recent research issues that arise due to the increasing synergy between NLG and other artificial intelligence areas, such as computer vision, text and computational creativity.