推进中文文本中的主题分割与大纲生成：段落级主题表示、语料库与基准
Advancing Topic Segmentation and Outline Generation in Chinese Texts: The Paragraph-level Topic Representation, Corpus, and Benchmark
AI总结：
本文构建了中文段落级主题表示、语料库与基准，提出三层层次化结构表示，采用两阶段人机协同标注构建最大规模CPTS语料库，并基于ChatGPT等基线验证了其在主题分割、大纲生成及话语解析任务上的有效性。
摘要：
主题分割与大纲生成旨在将文档划分为连贯的主题章节并生成相应的副标题，从而揭示文档的话语主题结构。与句子级主题结构相比，段落级主题结构能够从更高层次快速把握和理解文档的整体语境，有利于摘要、话语解析和信息检索等许多下游任务。然而，缺乏大规模、高质量的中文段落级主题结构语料库限制了相关研究和应用。为了填补这一空白，本文构建了中文段落级主题表示、语料库和基准。首先，我们提出了一种包含三层的层次化段落级主题结构表示，以指导语料库的构建。然后，我们采用两阶段人机协同标注方法，构建了目前最大的中文段落级主题结构语料库（CPTS），实现了高质量。我们还构建了包括ChatGPT在内的几个强基线模型，以验证CPTS在两个基础任务（主题分割和大纲生成）上的可计算性，并初步验证了其对下游任务（话语解析）的有用性。
英文摘要：
Topic segmentation and outline generation strive to divide a document into coherent topic sections and generate corresponding subheadings, unveiling the discourse topic structure of a document. Compared with sentence-level topic structure, the paragraph-level topic structure can quickly grasp and understand the overall context of the document from a higher level, benefitting many downstream tasks such as summarization, discourse parsing, and information retrieval. However, the lack of large-scale, high-quality Chinese paragraph-level topic structure corpora restrained relative research and applications. To fill this gap, we build the Chinese paragraph-level topic representation, corpus, and benchmark in this paper. Firstly, we propose a hierarchical paragraph-level topic structure representation with three layers to guide the corpus construction. Then, we employ a two-stage man-machine collaborative annotation method to construct the largest Chinese Paragraph-level Topic Structure corpus (CPTS), achieving high quality. We also build several strong baselines, including ChatGPT, to validate the computability of CPTS on two fundamental tasks (topic segmentation and outline generation) and preliminarily verified its usefulness for the downstream task (discourse parsing).
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。
