让摘要句子按语义顺序排列，提升可读性。
OrderSum: Semantic Sentence Ordering for Extractive Summarization
- 用新嵌入方法融合句子顺序信息到摘要表示中
- 在CNN/DailyMail上ROUGE-L达30.52，领先前模型2.54分
- 适合需要高质量有序摘要的应用场景
当前抽取式摘要主要关注选择哪些句子放入摘要，而忽视了句子顺序对摘要质量的关键影响。本文提出OrderSum，一种新型抽取式摘要模型，能够对摘要中的句子进行语义排序。该模型设计了新的表示方法，将句子顺序信息融入摘要嵌入表示，并引入目标函数训练模型在语义空间中判断哪个摘要的句子顺序更优。大量实验表明，OrderSum在句子选择和句子排序两方面均达到当前最优性能。尤其在CNN/DailyMail数据集上，ROUGE-L得分为30.52，较之前最佳模型提升2.54分。
原文摘要 · Abstract (English)
There are two main approaches to recent extractive summarization: the sentence-level framework, which selects sentences to include in a summary individually, and the summary-level framework, which generates multiple candidate summaries and ranks them. Previous work in both frameworks has primarily focused on improving which sentences in a document should be included in the summary. However, the sentence order of extractive summaries, which is critical for the quality of a summary, remains underexplored. In this paper, we introduce OrderSum, a novel extractive summarization model that semantically orders sentences within an extractive summary. OrderSum proposes a new representation method to incorporate the sentence order into the embedding of the extractive summary, and an objective function to train the model to identify which extractive summary has a better sentence order in the semantic space. Extensive experimental results demonstrate that OrderSum obtains state-of-the-art performance in both sentence inclusion and sentence order for extractive summarization. In particular, OrderSum achieves a ROUGE-L score of 30.52 on CNN/DailyMail, outperforming the previous state-of-the-art model by a large margin of 2.54.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。