Effective Slogan Generation with Noise Perturbation
This work addresses the challenge of automating slogan generation for branding, though it appears incremental as it builds on existing transformer models with specific modifications.
The paper tackled the problem of generating distinctive and coherent slogans for firms by introducing a novel approach using a T5 model with noise perturbation on a new dataset, achieving better performance than baseline and other transformer-based models as evaluated by ROUGE scores, cosine similarity, and human assessments.
Slogans play a crucial role in building the brand's identity of the firm. A slogan is expected to reflect firm's vision and brand's value propositions in memorable and likeable ways. Automating the generation of slogans with such characteristics is challenging. Previous studies developted and tested slogan generation with syntactic control and summarization models which are not capable of generating distinctive slogans. We introduce a a novel apporach that leverages pre-trained transformer T5 model with noise perturbation on newly proposed 1:N matching pair dataset. This approach serves as a contributing fator in generting distinctive and coherent slogans. Turthermore, the proposed approach incorporates descriptions about the firm and brand into the generation of slogans. We evaluate generated slogans based on ROUGE1, ROUGEL and Cosine Similarity metrics and also assess them with human subjects in terms of slogan's distinctiveness, coherence, and fluency. The results demonstrate that our approach yields better performance than baseline models and other transformer-based models.