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.
LaMSUM: Amplifying Voices Against Harassment through LLM Guided Extractive Summarization of User Incident Reports
Indian Institute of Technology Delhi, India(印度理工学院德里分校);Delhi Technological University, India(德里技术大学);Indian Institute of Technology Kharagpur, India(印度理工学院哈里科特分校);Collaborative Dynamics, Texas, USA(协同动力公司);Indian Institute of Science Education and Research Kolkata, India(印度科学教育与研究学院科希拉分校)
Query-Focused Extractive Summarization for Sentiment Explanation
Croesus Lab Laval, Québec, Canada(魁北克省拉瓦尔市的Croesus实验室);Software Engineering and IT Dept. École de Technologie Supérieure Montreal, Canada(蒙特利尔大学理工学院软件工程与IT部门)
Knapsack Constrained Contextual Submodular List Prediction with Application to Multi-document Summarization
Carnegie Mellon University(卡内基梅隆大学)
研究了背包约束下的一组或一列期权的预测问题。这些列表的质量由一个衡量质量和多样性的子模块奖励函数来评估。类似于Dagger(Ross等人,2010),通过简化为在线学习,我们展示了如何调整两个序列预测模型来模拟背包约束问题下的贪婪最大化:CONSEQOPT(Dey et al.,2012)和SCP(Ross等人,2013年)。抽取式多文档摘要的实验表明,我们的方法优于现有的国家的最先进的方法。
A Unified Framework for Generic, Query-Focused, Privacy Preserving and Update Summarization using Submodular Information Measures
Department of Computer Science, Indian Institute of Technology Bombay(印度理工学院孟买分校计算机科学系);Department of Computer Science, University of Texas at Dallas(得克萨斯大学达拉斯分校计算机科学系);Department of Electrical and Computer Engineering, University of Washington, Seattle(华盛顿大学西雅图分校电气与计算机工程系);School of Technology and Computer Science, Tata Institute of Fundamental Research, Mumbai(塔塔基础研究所孟买技术与计算机科学学院)
RankSum An unsupervised extractive text summarization based on rank fusion
Universidad de León(莱昂大学);INCIBE (Spanish National Cybersecurity Institute)(西班牙国家网络安全研究所(INCIBE));Centre for Development of Advanced Computing(先进计算发展中心)