CREATER: CTR-driven Advertising Text Generation with Controlled Pre-Training and Contrastive Fine-Tuning

TL;DR

CREATER is a novel CTR-driven advertising text generation model that leverages contrastive learning and self-supervised objectives to produce more engaging ad texts, significantly improving online advertising metrics.

Contribution

The paper introduces CREATER, a new approach combining contrastive fine-tuning and customized self-supervised learning for improved ad text generation based on user reviews.

Findings

CREATER outperforms existing methods on industrial datasets.

Deployment of CREATER increased click-through rates in a real advertising platform.

The approach effectively leverages online A/B test data for CTR optimization.

Abstract

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.