Toward Unifying Text Segmentation and Long Document Summarization
Toward Unifying Text Segmentation and Long Document Summarization
复制标题
DOI：
10.48550/arxiv.2210.16422
复制
发表时间：
2022-10
期刊：
影响因子：
--
通讯作者：
Sangwoo Cho;Kaiqiang Song;Xiaoyang Wang;Fei Liu;Dong Yu
中科院分区：
文献类型：
--
作者：
Sangwoo Cho;Kaiqiang Song;Xiaoyang Wang;Fei Liu;Dong Yu
文本分割对于表示文档的结构很重要。如果不将一个长文档分割成主题连贯的部分，读者就很难理解文本，更不用说找到重要信息了。由于录音/录像记录的文字记录没有分段，这一问题更加严重。在本文中，我们探讨的作用，部分分割书面和口头文件的提取摘要。我们的方法通过同时执行摘要和分割来学习鲁棒的句子表示，并通过基于优化的正则化器进一步增强，以促进对不同摘要句子的选择。我们在从科学文章到口语成绩单的多个数据集上进行实验，以评估模型的性能。我们的研究结果表明，该模型不仅可以实现国家的最先进的性能公开可用的基准，但表现出更好的跨体裁的可移植性时，配备了文本分割。我们进行了一系列的分析，以量化的影响，总结书面和口头文件的长度和复杂性的部分分割。
Text segmentation is important for signaling a document’s structure. Without segmenting a long document into topically coherent sections, it is difficult for readers to comprehend the text, let alone find important information. The problem is only exacerbated by a lack of segmentation in transcripts of audio/video recordings. In this paper, we explore the role that section segmentation plays in extractive summarization of written and spoken documents. Our approach learns robust sentence representations by performing summarization and segmentation simultaneously, which is further enhanced by an optimization-based regularizer to promote selection of diverse summary sentences. We conduct experiments on multiple datasets ranging from scientific articles to spoken transcripts to evaluate the model’s performance. Our findings suggest that the model can not only achieve state-of-the-art performance on publicly available benchmarks, but demonstrate better cross-genre transferability when equipped with text segmentation. We perform a series of analyses to quantify the impact of section segmentation on summarizing written and spoken documents of substantial length and complexity.