Striking Gold in Advertising: Standardization and Exploration of Ad Text Generation
This work addresses the problem of inconsistent comparisons in ad text generation for researchers and industry, though it is incremental as it focuses on benchmarking rather than new methods.
The paper tackles the lack of benchmarks in automatic ad text generation by standardizing the task and introducing CAMERA, a first benchmark dataset that enables multi-modal and industry-wise evaluations, with experiments on nine baselines showing current state and challenges.
In response to the limitations of manual ad creation, significant research has been conducted in the field of automatic ad text generation (ATG). However, the lack of comprehensive benchmarks and well-defined problem sets has made comparing different methods challenging. To tackle these challenges, we standardize the task of ATG and propose a first benchmark dataset, CAMERA, carefully designed and enabling the utilization of multi-modal information and facilitating industry-wise evaluations. Our extensive experiments with a variety of nine baselines, from classical methods to state-of-the-art models including large language models (LLMs), show the current state and the remaining challenges. We also explore how existing metrics in ATG and an LLM-based evaluator align with human evaluations.