arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.05690cs.AI
收藏

利用GPT实现大规模文档集合的生成式摘要

Abstractive Summarization of Large Document Collections Using GPT

North Carolina State University(北卡罗来纳州立大学)

Sengjie Liu, Christopher G. Healey

AI总结:

本研究提出一种结合语义聚类、GPT生成等技术的文档集合生成式摘要方法,实验显示其在两个基准数据集上性能与部分前沿系统统计等效,为大规模文档摘要任务提供了可行方案。

摘要:

本文提出了一种生成式摘要方法,旨在适配文档集合而非单篇文档的摘要任务。我们的方法结合了语义聚类、主题簇内文档篇幅压缩、簇内文档语义分块、基于GPT的摘要生成与拼接,以及各主题的情感与文本联合可视化以支持探索性数据分析。通过ROGUE摘要得分将我们的结果与现有前沿系统BART、BRIO、PEGASUS和MoCa进行统计对比,结果显示在CNN/Daily Mail测试数据集上,本方法性能与BART、PEGASUS统计等效;在Gigaword测试数据集上与BART统计等效。这一结果颇具前景,因为我们认为文档集合摘要比单篇文档摘要更具挑战性。文末我们讨论了规模相关问题的解决方向。

英文摘要:

This paper proposes a method of abstractive summarization designed to scale to document collections instead of individual documents. Our approach applies a combination of semantic clustering, document size reduction within topic clusters, semantic chunking of a cluster's documents, GPT-based summarization and concatenation, and a combined sentiment and text visualization of each topic to support exploratory data analysis. Statistical comparison of our results to existing state-of-the-art systems BART, BRIO, PEGASUS, and MoCa using ROGUE summary scores showed statistically equivalent performance with BART and PEGASUS on the CNN/Daily Mail test dataset, and with BART on the Gigaword test dataset. This finding is promising since we view document collection summarization as more challenging than individual document summarization. We conclude with a discussion of how issues of scale are

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。

↑