arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2010.08014cs.CL
收藏

GSum:一个通用的引导式神经抽象摘要框架

GSum: A General Framework for Guided Neural Abstractive Summarization

Carnegie Mellon University(卡内基梅隆大学)

Zi-Yi Dou, Pengfei Liu, Hiroaki Hayashi, Zhengbao Jiang, Graham Neubig

摘要:

神经抽象摘要模型是灵活的,可以产生连贯的摘要,但它们有时是不忠实的,很难控制。虽然以前的研究试图提供不同类型的指导,以控制输出和增加忠诚,这是不清楚这些策略如何比较和对比。在本文中,我们提出了一个通用的和可扩展的指导摘要框架(GSum),可以有效地采取不同种类的外部指导作为输入,我们在几个不同的品种进行实验。实验表明,该模型是有效的,达到了最先进的性能根据ROUGE 4流行的摘要数据集时,使用突出显示的句子作为指导。此外,我们还证明了我们的指导模型可以生成更忠实的摘要,并演示了不同类型的指导如何生成质量不同的摘要,从而为学习模型提供一定程度的可控性。

英文摘要:

Neural abstractive summarization models are flexible and can produce coherent summaries, but they are sometimes unfaithful and can be difficult to control. While previous studies attempt to provide different types of guidance to control the output and increase faithfulness, it is not clear how these strategies compare and contrast to each other. In this paper, we propose a general and extensible guided summarization framework (GSum) that can effectively take different kinds of external guidance as input, and we perform experiments across several different varieties. Experiments demonstrate that this model is effective, achieving state-of-the-art performance according to ROUGE on 4 popular summarization datasets when using highlighted sentences as guidance. In addition, we show that our guided model can generate more faithful summaries and demonstrate how different types of guidance generate qualitatively different summaries, lending a degree of controllability to the learned models.

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。

↑