Toward Improving Coherence and Diversity of Slogan Generation

TL;DR

This paper introduces a transformer-based model for slogan generation from company descriptions, enhancing coherence, diversity, and factual accuracy through delexicalisation, entity masking, and POS-based conditional training.

Contribution

It presents a novel seq2seq transformer approach with techniques to improve slogan relevance, factuality, and stylistic diversity, outperforming existing baselines.

Findings

Achieved ROUGE scores of 35.58/18.47/33.32

Generated slogans are more factual and diverse

Outperformed LSTM and standard transformer baselines

Abstract

Previous work in slogan generation focused on utilising slogan skeletons mined from existing slogans. While some generated slogans can be catchy, they are often not coherent with the company's focus or style across their marketing communications because the skeletons are mined from other companies' slogans. We propose a sequence-to-sequence (seq2seq) transformer model to generate slogans from a brief company description. A naive seq2seq model fine-tuned for slogan generation is prone to introducing false information. We use company name delexicalisation and entity masking to alleviate this problem and improve the generated slogans' quality and truthfulness. Furthermore, we apply conditional training based on the first words' POS tag to generate syntactically diverse slogans. Our best model achieved a ROUGE-1/-2/-L F1 score of 35.58/18.47/33.32. Besides, automatic and human evaluations indicate that our method generates significantly more factual, diverse and catchy slogans than strong LSTM and transformer seq2seq baselines.