有效口号生成与噪声扰动
Effective Slogan Generation with Noise Perturbation
AI总结：
本文提出一种利用预训练T5模型与噪声扰动在1:N匹配对数据集上生成独特且连贯口号的方法，并引入企业描述，实验证明其优于基线及其他Transformer模型。
摘要：
口号在建立企业品牌身份中起着至关重要的作用。一句口号应当以令人难忘且讨喜的方式反映企业的愿景和品牌的价值主张。自动化生成具有这些特征的口号具有挑战性。以往的研究开发并测试了具有句法控制和摘要模型的口号生成方法，这些方法无法生成独特的口号。我们提出了一种新颖的方法，利用预训练的Transformer T5模型，并在新提出的1:N匹配对数据集上进行噪声扰动。该方法在生成独特且连贯的口号方面起到了贡献作用。此外，所提出的方法将企业和品牌的描述纳入口号生成中。我们基于ROUGE1、ROUGEL和余弦相似度指标评估生成的口号，并让人类受试者从口号的独特性、连贯性和流畅性方面进行评估。结果表明，我们的方法在性能上优于基线模型和其他基于Transformer的模型。
英文摘要：
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.
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。
