Search papers, labs, and topics across Lattice.
This paper introduces COBART, a novel method for generating ad headlines that combines prefix control tokens with fine-tuning of the BART architecture. By allowing users to customize the length of headlines and optimize for click-through rates (CTR), COBART adapts to evolving ad formats and creative needs. Experimental results show a significant improvement, with a 25.82% increase in Rouge-L scores and a 5.82% boost in estimated CTR compared to existing baselines.
A flexible headline generation model that boosts click-through rates by over 5% while allowing precise control over headline length.
Online ads are essential to all businesses and ad headlines are one of their core creative component. Existing methods can generate headlines automatically and also optimize their click-through-rate (CTR) and quality. However, evolving ad formats and changing creative requirements make it difficult to generate optimized & customized headlines. We propose a novel method that uses prefix control tokens along with BART [16] fine-tuning. It yields the highest CTR and also allows users to control the length of generated headlines for use across different ad formats. The method is also flexible and can easily be adapted to other architectures, creative requirements and optimization criteria. Our experiments demonstrate a 25.82% increment in Rouge-L and a 5.82% increment in estimated CTR over previously published strong ad headline generation baseline.
Amazon Science