We study the notion of hierarchy in the context of visualizing textual data and navigating text collections. A formal framework for ``hierarchy'' is given by an ultrametric topology. This provides us with a theoretical foundation for concept hierarchy creation. A major objective is {\em scalable} annotation or labeling of concept maps. Serendipitously we pursue other objectives such as deriving common word pair (and triplet) phrases, i.e., word 2- and 3-grams. We evaluate our approach using (i) a collection of texts, (ii) a single text subdivided into successive parts (for which we provide an interactive demonstrator), and (iii) a text subdivided at the sentence or line level. While detailing a generic framework, a distinguishing feature of our work is that we focus on {\em locality} of hierarchic structure in order to extract semantic information.
Visual Affect Around the World: A Large-scale Multilingual Visual Sentiment Ontology
Columbia University(哥伦比亚大学);Idiap Research Institute(伊迪亚普研究所);EPFL(洛桑联邦理工学院);Yahoo Labs(雅虎实验室);JW Player(JW Player公司)
每一种文化和语言都是独一无二的。我们的工作明确地集中在文化和语言的独特性与人类的影响,特别是情绪和情感语义,以及它们如何体现在社会多媒体。我们通过调整最初由Borth et al.(2013)引入的称为形容词-名词对的语义结构来开发情感和情感极化的视觉概念集。我们提出了一种新的依赖于语言的方法来自动发现这些形容词-名词结构。我们展示了如何将此管道应用于社交多媒体平台,以创建大规模的多语言视觉情感概念本体(MVSO)。与Borth et al.(2013)中的平面结构不同,我们的统一本体论是由视觉上可检测的名词的多语言集群和这些名词的情感偏见版本的子集群分层组织的。此外,我们提出了一个基于图像的预测任务,以显示如何推广的语言特定的模型是在多语言的背景下。一个新的,公开可用的数据集,包含12种语言的>15.6K情感偏见视觉概念,具有语言特定的检测器库,>7.36M图像及其元数据。