Extractive models usually formulate text summarization as extracting fixed top-$k$ salient sentences from the document as a summary. Few works exploited extracting finer-grained Elementary Discourse Unit (EDU) with little analysis and justification for the extractive unit selection. Further, the selection strategy of the fixed top-$k$ salient sentences fits the summarization need poorly, as the number of salient sentences in different documents varies and therefore a common or best $k$ does not exist in reality. To fill these gaps, this paper first conducts the comparison analysis of oracle summaries based on EDUs and sentences, which provides evidence from both theoretical and experimental perspectives to justify and quantify that EDUs make summaries with higher automatic evaluation scores than sentences. Then, considering this merit of EDUs, this paper further proposes an EDU-level extractive model with Varying summary Lengths and develops the corresponding learning algorithm. EDU-VL learns to encode and predict probabilities of EDUs in the document, generate multiple candidate summaries with varying lengths based on various $k$ values, and encode and score candidate summaries, in an end-to-end training manner. Finally, EDU-VL is experimented on single and multi-document benchmark datasets and shows improved performances on ROUGE scores in comparison with state-of-the-art extractive models, and further human evaluation suggests that EDU-constituent summaries maintain good grammaticality and readability.

翻译：抽取式模型通常将文本摘要任务形式化为从文档中抽取固定的前$k$个显著句子作为摘要。已有研究很少探索以更细粒度的基本篇章单元（EDU）进行抽取，且对抽取单元选择缺乏分析与论证。此外，固定前$k$个显著句子的选择策略难以适配摘要需求，因为不同文档中显著句子的数量存在差异，因此现实中不存在通用或最优的$k$值。为填补这些空白，本文首先开展基于EDU和句子的最佳摘要对比分析，从理论与实验双重视角提供证据，论证并量化了EDU相较于句子能生成自动评估分数更高的摘要。基于EDU的这一优势，本文进一步提出一种可变长度的EDU级抽取式模型（EDU-VL），并开发相应的学习算法。EDU-VL以端到端训练方式实现以下功能：编码并预测文档中EDU的概率；基于不同$k$值生成多个长度可变的候选摘要；对候选摘要进行编码与评分。最终，EDU-VL在单文档和多文档基准数据集上实验表明，其ROUGE评分优于现有最优抽取式模型，人工评估进一步证实EDU组成的摘要具有良好的语法正确性与可读性。