Reasoning about scene descriptions

Reasoning about scene descriptions
复制标题

对场景描述进行推理

DOI:
10.1109/proc.1986.13579
复制
发表时间:
1986
影响因子:
20.6
通讯作者:
Fausto Giunchiglia
Fausto Giunchiglia
中科院分区:
计算机科学1区
文献类型:
--
作者:
M. Dimanzo;G. Adorni;Fausto Giunchiglia

文献摘要

参考文献

被引文献

相似文献

当用自然语言句子描述场景时,通常会省略许多细节,因为它们不是对话的焦点。此外,自然语言并不是精确定义位置和空间关系的最佳工具。解释模棱两可的陈述和推断缺失细节的过程涉及多种类型的知识,从语言学到物理学。本文主要关注静态场景理解描述过程的建模问题。这项工作涵盖的具体主题是空间介词含义的分析、参考系统和维度问题、对未提及对象的期望激活、关于对象位置的默认知识的作用及其与上下文信息源的集成,以及空间表示问题。最后一节简要讨论了理解动态场景描述的问题。
When a scene is described by means of natural language sentences, many details are usually omitted, because they are not in the focus of the conversation. Moreover, natural language is not the best tool to define precisely positions and spatial relationships. The process of interpreting ambiguous statements and inferring missing details involves many types of knowledge, from linguistics to physics. This paper is mainly concerned with the problem of modeling the process of understanding descriptions of static scenes. The specific topics covered by this work are the analysis of the meaning of spatial prepositions, the problem of the reference system and dimensionality, the activation of expectations about unmentioned objects, the role of default knowledge about object positions and its integration with contextual information sources, and the problem of space representation. The issue of understanding dynamic scenes descriptions is briefly approached in the last section.
DOI: 10.1016/0004-3702(84)90008-0
发表时间: 1984-01-01
影响因子: 14.4
作者:
ALLEN, JF
通讯作者: ALLEN, JF