arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.04677cs.CL
收藏

抽象摘要中的源句识别

Source Identification in Abstractive Summarization

NVIDIA(英伟达);Grammarly

Yoshi Suhara, Dimitris Alikaniotis

AI总结:

本文通过定义源句并分析PEGASUS生成的摘要,研究抽象摘要的生成机制,提出自动源句检测方法,实验表明困惑度法适合高抽象场景,相似度法适合抽取场景。

摘要:

神经抽象摘要模型以端到端方式生成摘要,但关于源信息如何实际转化为摘要的过程知之甚少。在本文中,我们将生成摘要中包含关键信息的输入句子定义为“源句”,并通过分析源句来研究抽象摘要的生成机制。为此,我们为从CNN/DailyMail和XSum数据集中采样的文档-摘要对,标注了参考摘要和PEGASUS生成系统摘要的源句。我们还制定了自动源句检测任务,并比较了多种方法以建立该任务的强基线。实验结果表明,基于困惑度的方法在高抽象性场景下表现良好,而基于相似度的方法在相对抽取性场景下表现稳健。我们的代码和数据可在https://github.com/suhara/sourcesum获取。

英文摘要:

Neural abstractive summarization models make summaries in an end-to-end manner, and little is known about how the source information is actually converted into summaries. In this paper, we define input sentences that contain essential information in the generated summary as $\textit{source sentences}$ and study how abstractive summaries are made by analyzing the source sentences. To this end, we annotate source sentences for reference summaries and system summaries generated by PEGASUS on document-summary pairs sampled from the CNN/DailyMail and XSum datasets. We also formulate automatic source sentence detection and compare multiple methods to establish a strong baseline for the task. Experimental results show that the perplexity-based method performs well in highly abstractive settings, while similarity-based methods perform robustly in relatively extractive settings. Our code and data are available at https://github.com/suhara/sourcesum.

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。

↑