Natural Language Generation for Advertising: A Survey
It provides a comprehensive overview for researchers and advertisers, but is incremental as a survey paper.
This survey reviews natural language generation methods for advertising over the past decade, covering template-based to neural network approaches, and discusses key challenges such as metric optimization and faithfulness.
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.