arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.08593cs.LGcs.CLcs.IR
收藏

用于抽取数据摘要的深度子模块网络

Deep Submodular Networks for Extractive Data Summarization

University of Texas, Dallas(得克萨斯大学达拉斯分校);University of Washington, Seattle(华盛顿大学西雅图分校)

Suraj Kothawade, Jiten Girdhar, Chandrashekhar Lavania, Rishabh Iyer

摘要:

深度模型在摘要问题(例如文档、视频和图像)中越来越普遍,因为它们能够学习复杂的特征交互和表示。然而,它们没有对多样性、表示和覆盖等特征进行建模,这些特征对于摘要任务也非常重要。另一方面,子模函数由于其收益递减属性而自然地模拟这些特征。大多数建模和学习次模函数的方法都依赖于非常简单的模型,例如次模函数的加权混合。不幸的是,这些模型只能学习不同子模块函数的相对重要性(例如多样性,表示或重要性),但不能学习更复杂的特征表示,这通常是最先进的性能所需的。我们提出了深度子模块化网络(DSN),这是一个端到端的学习框架,有助于学习更复杂的功能和更丰富的功能,为更好地建模总结的各个方面而精心制作。DSN框架可用于从头开始学习适合于摘要的功能。我们展示了通用和查询集中的图像收集摘要的DSN的效用,并显示出显着的改进,在国家的最先进的。特别是,我们表明,DSN优于简单的混合模型使用现成的功能。其次,我们还证明了在DSN中使用四个子模块函数进行端到端学习,可以使用手工制作的594个组件来实现最先进的混合模型,并且优于其他图像集合摘要方法。

英文摘要:

Deep Models are increasingly becoming prevalent in summarization problems (e.g. document, video and images) due to their ability to learn complex feature interactions and representations. However, they do not model characteristics such as diversity, representation, and coverage, which are also very important for summarization tasks. On the other hand, submodular functions naturally model these characteristics because of their diminishing returns property. Most approaches for modelling and learning submodular functions rely on very simple models, such as weighted mixtures of submodular functions. Unfortunately, these models only learn the relative importance of the different submodular functions (such as diversity, representation or importance), but cannot learn more complex feature representations, which are often required for state-of-the-art performance. We propose Deep Submodular Networks (DSN), an end-to-end learning framework that facilitates the learning of more complex features and richer functions, crafted for better modelling of all aspects of summarization. The DSN framework can be used to learn features appropriate for summarization from scratch. We demonstrate the utility of DSNs on both generic and query focused image-collection summarization, and show significant improvement over the state-of-the-art. In particular, we show that DSNs outperform simple mixture models using off the shelf features. Secondly, we also show that just using four submodular functions in a DSN with end-to-end learning performs comparably to the state-of-the-art mixture model with a hand-crafted set of 594 components and outperforms other methods for image collection summarization.

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。

↑