JaccDiv：量化音乐行业生成营销文本多样性的指标与基准
JaccDiv: A Metric and Benchmark for Quantifying Diversity of Generated Marketing Text in the Music Industry
AI总结：
本文针对音乐行业营销文本生成中的重复问题，提出基于LLM的data-to-text方法并设定基准，同时引入JaccDiv指标量化文本多样性，适用于多种内容生成领域。
摘要：
在线平台越来越倾向于使用Data-to-Text技术来生成内容并帮助其用户。遗憾的是，传统的生成方法常常陷入重复模式，仅需几次迭代便会导致单调的文本集合。在本文中，我们研究了基于LLM的data-to-text方法，以自动生成质量足够高且多样性足以广泛采用的营销文本。我们利用T5、GPT-3.5、GPT-4和LLaMa2等语言模型，结合fine-tuning、few-shot和zero-shot方法，为多样化的营销文本设定基准。我们还引入了JaccDiv指标来评估一组文本的多样性。本研究将其相关性扩展至音乐行业之外，证明在重复性自动内容生成普遍存在的各个领域中均具有益处。
英文摘要：
Online platforms are increasingly interested in using Data-to-Text technologies to generate content and help their users. Unfortunately, traditional generative methods often fall into repetitive patterns, resulting in monotonous galleries of texts after only a few iterations. In this paper, we investigate LLM-based data-to-text approaches to automatically generate marketing texts that are of sufficient quality and diverse enough for broad adoption. We leverage Language Models such as T5, GPT-3.5, GPT-4, and LLaMa2 in conjunction with fine-tuning, few-shot, and zero-shot approaches to set a baseline for diverse marketing texts. We also introduce a metric JaccDiv to evaluate the diversity of a set of texts. This research extends its relevance beyond the music industry, proving beneficial in various fields where repetitive automated content generation is prevalent.
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。
