Exploring the Relationship Between Diversity and Quality in Ad Text Generation

TL;DR

This paper investigates how different diversity-enhancing methods affect the quality of generated ad texts, highlighting the unique challenges and considerations in advertising language generation.

Contribution

It provides an analysis of the impact of diversity methods on ad text quality, specifically tailored to advertising language generation, which differs from traditional NLP tasks.

Findings

Diversity methods influence ad quality variably depending on hyperparameters.

Ad text generation requires specialized evaluation metrics for advertising context.

The study highlights the importance of balancing diversity and coherence in ad texts.

Abstract

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.