Towards improving coherence and diversity of slogan generation

• Published in: Natural language engineering Vol. 29; no. 2; pp. 254 - 286
• Main Authors: Jin, Yiping, Bhatia, Akshay, Wanvarie, Dittaya, Le, Phu T. V.
• Format: Journal Article
• Language: English
• Published: Cambridge Cambridge University Press 01.03.2023
• Subjects: Advertising; Coherence; Credibility; Datasets; Genetic algorithms; Keywords; Masking; Natural language generation; Short term memory; Slogans; Syntax; Transformers
• DOI: 10.1017/S1351324921000474
• ISSN: 1351-3249

Previouswork 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 naïve 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’ part-of-speech tag to generate syntactically diverse slogans. Our best model achieved a ROUGE-1/-2/-L $\mathrm{F}_1$ 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 long short-term memory and Transformer seq2seq baselines.