Natural Language Generation for Advertising: A Survey

TL;DR

This survey reviews the evolution of natural language generation techniques for advertising over the past decade, highlighting key challenges and future research directions in the field.

Contribution

It provides a comprehensive overview of research trends, challenges, and datasets in neural network-based advertising text generation.

Findings

Shift from template-based to neural approaches

Identification of key challenges like faithfulness and diversity

Discussion of emerging benchmark datasets

Abstract

Natural language generation methods have emerged as effective tools to help advertisers increase the number of online advertisements they produce. This survey entails a review of the research trends on this topic over the past decade, from template-based to extractive and abstractive approaches using neural networks. Additionally, key challenges and directions revealed through the survey, including metric optimization, faithfulness, diversity, multimodality, and the development of benchmark datasets, are discussed.