Effective Slogan Generation with Noise Perturbation

TL;DR

This paper presents a novel slogan generation method using a pre-trained T5 transformer with noise perturbation, incorporating brand descriptions to produce distinctive, coherent, and memorable slogans, outperforming baseline models.

Contribution

Introduces a noise-perturbed T5-based approach that integrates brand descriptions for improved slogan generation, addressing limitations of previous syntactic control and summarization models.

Findings

Outperforms baseline models in ROUGE and cosine similarity metrics.

Generates slogans with higher human-rated distinctiveness and coherence.

Demonstrates effectiveness of noise perturbation in enhancing slogan uniqueness.

Abstract

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.