Can I read A Graph-to-Text Approach to Knowledge-Grounded Response Generation in Human-Robot Interaction on EtoBox?

A Graph-to-Text Approach to Knowledge-Grounded Response Generation in Human-Robot Interaction by Walker, Nicholas Thomas; Ultes, Stefan; Lison, Pierre is a scholarly article available to read on EtoBox.

What is A Graph-to-Text Approach to Knowledge-Grounded Response Generation in Human-Robot Interaction about?

Knowledge graphs are often used to represent structured information in a flexible and efficient manner, but their use in situated dialogue remains under-explored. This paper presents a novel conversational model for human--robot interaction that rests upon a graph-based representation of the dialogue state. The knowledge graph representing the dialogue state is continuously updated with new observations from the robot sensors, including linguistic, situated and multimodal inputs, and is further enriched by other modules, in particular for spatial understanding. The neural conversational model employed to respond to user utterances relies on a simple but effective graph-to-text mechanism that traverses the dialogue state graph and converts the traversals into a natural language form. This conversion of the state graph into text is performed using a set of parameterized functions, and the values for those parameters are optimized based on a small set of Wizard-of-Oz interactions. After this conversion, the text representation of the dialogue state graph is included as part of the prompt of a large language model used to decode the agent response. The proposed approach is empirically

Author

Walker, Nicholas Thomas; Ultes, Stefan; Lison, Pierre

Published

2023

Language

EN