arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.07210cs.CL
收藏

RefSum:重构神经摘要

RefSum: Refactoring Neural Summarization

Carnegie Mellon University(卡内基梅隆大学)

Yixin Liu, Zi-Yi Dou, Pengfei Liu

摘要:

虽然最近的一些作品表现出潜在的互补性之间的不同国家的最先进的系统,很少有作品试图研究这个问题,在文本摘要。其他领域的研究人员通常会参考重新排序或堆叠的技术来解决这个问题。在这项工作中,我们强调了以前的方法,这促使我们提出了一个新的框架重构,提供了一个统一的视图的文本摘要和摘要组合的几个限制。在实验中,我们进行了全面的评估,涉及22个基础系统,四个数据集,和三个不同的应用场景。除了在CNN/DailyMail数据集(46.18 ROUGE-1)上获得的最新结果外,我们还详细说明了我们提出的方法如何解决传统方法的局限性,以及重构模型的有效性为性能改进提供了见解。我们的系统可以直接使用其他研究人员作为一个现成的工具,以实现进一步的性能改进。我们开源了所有的代码,并提供了一个方便的界面来使用它:https://github.com/yixinL7/Refactoring-Summarization。我们还在http://explainaboard.nlpedia.ai/leaderboard/task-summ/index.php上提供了这项工作的演示。

英文摘要:

Although some recent works show potential complementarity among different state-of-the-art systems, few works try to investigate this problem in text summarization. Researchers in other areas commonly refer to the techniques of reranking or stacking to approach this problem. In this work, we highlight several limitations of previous methods, which motivates us to present a new framework Refactor that provides a unified view of text summarization and summaries combination. Experimentally, we perform a comprehensive evaluation that involves twenty-two base systems, four datasets, and three different application scenarios. Besides new state-of-the-art results on CNN/DailyMail dataset (46.18 ROUGE-1), we also elaborate on how our proposed method addresses the limitations of the traditional methods and the effectiveness of the Refactor model sheds light on insight for performance improvement. Our system can be directly used by other researchers as an off-the-shelf tool to achieve further performance improvements. We open-source all the code and provide a convenient interface to use it: https://github.com/yixinL7/Refactoring-Summarization. We have also made the demo of this work available at: http://explainaboard.nlpedia.ai/leaderboard/task-summ/index.php.

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。

↑