TerraVision, a system for interactively viewing terrain data is described. The terrain data comprises elevation information and specially processed aerial or satellite images. The system uses a multi-resolution representation of the terrain data divided into equal-sized subimages called tiles.
In a sharp departure from conventional approaches to the problem of meaning representation in natural languages, test-score semantics is based on the premise that almost everything that relates to natural language is a matter of degree.
Most conventional computer information-retrieval systems are limited by rigid data structures and inflexible query languages. In this paper we will describe an approach to combining and extending recently developed question-answering techniques to reasonably large data files.
Communication channels physically constrain the flow and shape of human language just as irresistably as a river bed directs the river’s current. Escarpments speed the current, sculpting jetties and whirlpools. Meadows encourage evenness, a certain recumbency.
This document contains an in-depth description of the Core Knowledge System (CKS)–an integrative environment for the many functions that must be performed by sensor-based autonomous and semi-autonomous systems.
The primary purpose of the Image Understanding (IU) Testbed is to provide a means for transferring technology from the DARPA-sponsored IU research program to DMA and other organizations in the defense community.
The primary purpose of the Image Understanding (IU) Testbed is to provide a means for transferring technology from the DARPA-sponsored IU research program to DMA and other organizations in the defense community.
This paper presents a method of formally representing the information that is available to a user of a relational database. The intended application area is deductive question-answering systems that must access an existing relational database
In the past 20 years, AI researchers in knowledge representation (KR) have implemented over 50 frame knowledge representation systems (FRSs). KR researchers have explored a large and surprisingly diverse space of alternative FRS designs.
