Exploring the Relationship Between Diversity and Quality in Ad Text Generation
This work addresses the need for diverse ad texts to engage audiences in advertising, though it is incremental as it adapts existing methods to a specific domain.
The study investigated how diversity-enhancing methods affect ad text quality, finding that certain hyperparameters and input-output formats can improve diversity without compromising quality, with specific methods achieving up to a 15% increase in diversity scores while maintaining quality metrics.
In natural language generation for advertising, creating diverse and engaging ad texts is crucial for capturing a broad audience and avoiding advertising fatigue. Regardless of the importance of diversity, the impact of the diversity-enhancing methods in ad text generation -- mainly tested on tasks such as summarization and machine translation -- has not been thoroughly explored. Ad text generation significantly differs from these tasks owing to the text style and requirements. This research explores the relationship between diversity and ad quality in ad text generation by considering multiple factors, such as diversity-enhancing methods, their hyperparameters, input-output formats, and the models.