arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.00140cs.IRcs.CL
收藏

摘要提取实验:线性规划、词/句评分和标题驱动模型

Experiments in Extractive Summarization: Integer Linear Programming, Term/Sentence Scoring, and Title-driven Models

University of Houston(休斯顿大学)

Daniel Lee, Rakesh Verma, Avisha Das, Arjun Mukherjee

摘要:

在本文中,我们重新审视了具有挑战性的问题,无监督的单文档摘要和研究以下几个方面:基于线性规划(ILP)的算法,参数化规范化的术语和句子的分数,和标题驱动的方法摘要。我们描述了一个新的框架,NewsSumm,其中包括许多现有的和新的方法,包括ILP和标题驱动的方法总结。NewsSumm的灵活性允许无缝结合不同的算法和句子评分方案。我们的结果结合句子评分与ILP和规范化是在对比以前的工作在这个主题上,显示了更广泛的搜索最佳参数的重要性。我们还表明,新的标题驱动的减少的想法导致性能的改善,无论是无监督和监督的方法考虑。

英文摘要:

In this paper, we revisit the challenging problem of unsupervised single-document summarization and study the following aspects: Integer linear programming (ILP) based algorithms, Parameterized normalization of term and sentence scores, and Title-driven approaches for summarization. We describe a new framework, NewsSumm, that includes many existing and new approaches for summarization including ILP and title-driven approaches. NewsSumm's flexibility allows to combine different algorithms and sentence scoring schemes seamlessly. Our results combining sentence scoring with ILP and normalization are in contrast to previous work on this topic, showing the importance of a broader search for optimal parameters. We also show that the new title-driven reduction idea leads to improvement in performance for both unsupervised and supervised approaches considered.

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。

↑