Learning when to point: A data-driven approach
Learning when to point: A data-driven approach
复制标题
学习何时指向：数据驱动的方法
DOI：
10.1109/ssrr.2018.8468622
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
Patrizia Paggio
中科院分区：
文献类型：
--
作者：
Albert Gatt;Patrizia Paggio
人们描述事物的方式和他们选择指向的时间之间的关系是复杂的，可能会受到与感知语境和话语语境相关的因素的影响。在本文中，我们使用机器学习在对话语料库上探索这些交互，以确定可用于自动多通道生成的多通道参考策略。我们表明，使用指向手势的决定取决于伴随描述的特征(特别是它是否包含空间信息)，以及视觉属性，特别是参照物与其先前参照物的距离或分离。
The relationship between how people describe objects and when they choose to point is complex and likely to be influenced by factors related to both perceptual and discourse context. In this paper, we explore these interactions using machine-learning on a dialogue corpus, to identify multimodal referential strategies that can be used in automatic multimodal generation. We show that the decision to use a pointing gesture depends on features of the accompanying description (especially whether it contains spatial information), and on visual properties, especially distance or separation of a referent from its previous referent.