Conversational Robots: Building Blocks For Grounding Word Meaning
نویسندگان
چکیده
How can we build robots that engage in fluid spoken conversations with people, moving beyond canned responses to words and towards actually understanding? As a step towards addressing this question, we introduce a robotic architecture that provides a basis for grounding word meanings. The architecture provides perceptual, procedural, and affordance representations for grounding words. A perceptuallycoupled on-line simulator enables sensorymotor representations that can shift points of view. Held together, we show that this architecture provides a rich set of data structures and procedures that provide the foundations for grounding the meaning of certain classes of words.
منابع مشابه
Conversational Robots: Building Blocks for Grounding Word Meanings
How can we build robots that engage in fluid spoken conversations with people, moving beyond canned responses to words and towards actually understanding? As a step towards addressing this question, we introduce a robotic architecture that provides a basis for grounding word meanings. The architecture provides perceptual, procedural, and affordance representations for grounding words. A percept...
متن کاملCoupling Robot Perception and Online Simulation for Grounding Conversational Semantics
How can we build robots that engage in fluid spoken conversations with people, moving beyond canned responses and towards actual understanding? Many difficult questions arise regarding the nature of word meanings, and how those meanings are grounded in the world of the robot. We introduce an architecture that provides the basis for grounding word meanings in terms of robot perception, action, a...
متن کاملNatural Language Communication with Robots
We propose a framework for devising empirically testable algorithms for bridging the communication gap between humans and robots. We instantiate our framework in the context of a problem setting in which humans give instructions to robots using unrestricted natural language commands, with instruction sequences being subservient to building complex goal configurations in a blocks world. We show ...
متن کاملFrom Words to Sentences & Back: Characterizing Context-dependent Meaning Representations in the Brain
Recent Machine Learning systems in vision and language processing have drawn attention to single-word vector spaces, where concepts are represented by a set of basic features or attributes based on textual and perceptual input. However, such representations are still shallow and fall short from symbol grounding. In contrast, Grounded Cognition theories such as CAR (Concept Attribute Representat...
متن کاملComedy, Context and Unsaid Meaning: A Case Study in Conversational Implicature
Pragmatics moves away from the word level and sentence level study of language towards the study of language in real-world context and at discourse level whereby two or more participants take part in conversation. There are moments when the speaker explicitly says something but the listener may have other interpretations and inferences from their statements. The aim of this study was to demonst...
متن کامل