arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.05924cs.CL
收藏

提高标语生成的一致性和多样性

Toward Improving Coherence and Diversity of Slogan Generation

Chulalongkorn University(朱拉隆功大学);Knorex

Yiping Jin, Akshay Bhatia, Dittaya Wanvarie, Phu T. V. Le

摘要:

以前的口号生成工作集中在利用从现有的口号挖掘的口号骨架。虽然一些生成的口号可能很吸引人,但它们通常与公司在营销传播中的重点或风格不一致,因为骨架是从其他公司的口号中挖掘出来的。我们提出了一个序列到序列(seq 2seq)的Transformer模型,从一个简短的公司描述生成的口号。一个简单的seq 2seq模型被微调用于口号生成,很容易引入错误信息。我们使用公司名称去词汇化和实体掩蔽来缓解这个问题,并提高生成的标语的质量和真实性。此外,我们应用基于第一个词的POS标签的条件训练来生成句法多样的口号。我们的最佳模型获得了ROUGE-1/-2/-L F1评分35.58/18.47/33.32。此外,自动和人工评估表明,我们的方法比强大的LSTM和Transformer seq 2seq基线生成了更多的事实,多样性和吸引人的口号。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑