Natural Reference to Objects in a Visual Domain
Natural Reference to Objects in a Visual Domain
复制标题
DOI：
--
复制
发表时间：
2010-07
期刊：
影响因子：
--
通讯作者：
Margaret Mitchell;Kees van Deemter;Ehud Reiter
中科院分区：
文献类型：
--
作者：
Margaret Mitchell;Kees van Deemter;Ehud Reiter
本文讨论了在视觉场景中生成对象参考所必需的基本结构。我们构建了一项研究，旨在引出相对复杂的对象的自然指称表达，并找到在指称表达生成（REG）工作中尚未考虑到的指称方面。这包括对对象部件的参考，没有清晰测量的尺寸比较，以及类比的使用。通过对认知科学、神经生理学和心理语言学的研究，我们开始开发一种算法所需的输入结构和背景知识，这种算法能够生成我们所观察到的各种参考。
This paper discusses the basic structures necessary for the generation of reference to objects in a visual scene. We construct a study designed to elicit naturalistic referring expressions to relatively complex objects, and find aspects of reference that have not been accounted for in work on Referring Expression Generation (REG). This includes reference to object parts, size comparisons without crisp measurements, and the use of analogies. By drawing on research in cognitive science, neurophysiology, and psycholinguistics, we begin developing the input structure and background knowledge necessary for an algorithm capable of generating the kinds of reference we observe.