MovieSum：一个面向电影剧本的生成式摘要数据集
MovieSum: An Abstractive Summarization Dataset for Movie Screenplays
AI总结：
针对电影剧本摘要研究不足的问题，本文提出包含2200部格式化剧本及对应维基百科摘要的MovieSum数据集，其规模为现有同类数据集两倍，还附IMDb元数据，并给出了大语言模型的基准测试结果。
摘要：
电影剧本摘要任务颇具挑战性，因为它需要理解长输入上下文以及电影特有的各类元素。大语言模型在文档摘要领域已取得显著进展，但往往难以处理长输入上下文。此外，尽管近年的研究对电视台词文本有所关注，电影剧本摘要的探索仍显不足。为推动该领域的研究，我们提出了一个用于电影剧本生成式摘要的新数据集MovieSum。该数据集包含2200部电影剧本及其对应的维基百科剧情摘要。我们对电影剧本进行了人工格式化，以呈现其结构元素。与现有数据集相比，MovieSum具备若干独特特征：（1）它收录的电影剧本长度超过单集电视剧剧本；（2）它的规模是此前电影剧本数据集的两倍；（3）它提供带有IMDb ID的元数据，便于获取额外的外部知识。我们还展示了近期发布的大语言模型在该数据集上的摘要任务结果，以提供详细的基准线。
英文摘要：
Movie screenplay summarization is challenging, as it requires an understanding of long input contexts and various elements unique to movies. Large language models have shown significant advancements in document summarization, but they often struggle with processing long input contexts. Furthermore, while television transcripts have received attention in recent studies, movie screenplay summarization remains underexplored. To stimulate research in this area, we present a new dataset, MovieSum, for abstractive summarization of movie screenplays. This dataset comprises 2200 movie screenplays accompanied by their Wikipedia plot summaries. We manually formatted the movie screenplays to represent their structural elements. Compared to existing datasets, MovieSum possesses several distinctive features: (1) It includes movie screenplays, which are longer than scripts of TV episodes. (2) It is twice the size of previous movie screenplay datasets. (3) It provides metadata with IMDb IDs to facilitate access to additional external knowledge. We also show the results of recently released large language models applied to summarization on our dataset to provide a detailed baseline.
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。
