Toward Improving Coherence and Diversity of Slogan Generation
This work addresses the challenge of generating high-quality marketing slogans for companies, though it is incremental as it builds on existing seq2seq methods with specific enhancements.
The paper tackled the problem of generating slogans that are both coherent with a company's focus and diverse in style, proposing a seq2seq transformer model with delexicalisation and conditional training to improve truthfulness and syntactic diversity. Their best model achieved ROUGE-1/-2/-L F1 scores of 35.58/18.47/33.32 and outperformed baselines in factual accuracy, diversity, and catchiness.
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.