CREATER: CTR-driven Advertising Text Generation with Controlled Pre-Training and Contrastive Fine-Tuning
This work addresses the challenge of generating effective ad text for advertising platforms, though it appears incremental as it builds on existing text generation methods with CTR optimization.
The paper tackles the problem of automatically generating advertising text to increase click-through rates by proposing CREATER, which uses CTR-driven pre-training and contrastive fine-tuning on user reviews and A/B test data. Experiments on industrial datasets show it significantly outperforms existing approaches and has been deployed online, bringing uplift in core metrics.
This paper focuses on automatically generating the text of an ad, and the goal is that the generated text can capture user interest for achieving higher click-through rate (CTR). We propose CREATER, a CTR-driven advertising text generation approach, to generate ad texts based on high-quality user reviews. To incorporate CTR objective, our model learns from online A/B test data with contrastive learning, which encourages the model to generate ad texts that obtain higher CTR. To alleviate the low-resource issue, we design a customized self-supervised objective reducing the gap between pre-training and fine-tuning. Experiments on industrial datasets show that CREATER significantly outperforms current approaches. It has been deployed online in a leading advertising platform and brings uplift on core online metrics.