This paper addresses the issue of how verbal communication arises from the complex and uncertain representations that seem necessary to robustly carry out perception in real-world domains. We propose that the generation of natural language in such domains should be addressed as the optimization problem of finding, under various constraints, the verbalization that has the greatest probability of achieving a specific change that the speaker wants to induce in the mental state or behavior of the listener. This most likely effective or MLE strategy has the advantage of making the problem concrete, and allowing (possibly empathic) models of the perceptual and behavioral processes to be used in a principled way. We illustrate these issues in the context of the specific problem of describing real objects in native domains using basic color language (e.g. "mostly brown", "partly red"). The term "native domains" refers to real-world environments that have not been tailored to suit the application.
Generating Verbal Descriptions of Colored Objects: Towards Grounding Language in Perception
2005-01-01
296532 byte
Conference paper
Electronic Resource
English
Grounding Mundane Inference in Perception
British Library Online Contents | 1998
|Tree Grammars in the Problems of Searching for Images by Their Verbal Descriptions
British Library Online Contents | 2000
|Odor source identification by grounding linguistic descriptions in an artificial nose [4385-38]
British Library Conference Proceedings | 2001
|The influence of verbal and non-verbal language manipulations on data quality
British Library Conference Proceedings | 2005
|