TY - JOUR
KW - Human-Robot Interaction
KW - Large Language Models
KW - Social Robots
AU - Javier Sevilla-Salcedo
AU - Enrique Fernádez-Rodicio
AU - Laura Martín-Galván
AU - Álvaro Castro-González
AU - José C. Castillo
AU - Miguel A. Salichs
AB - Social robots are making their way into our lives in different scenarios in which humans and robots need to communicate. In these scenarios, verbal communication is an essential element of human-robot interaction. However, in most cases, social robots’ utterances are based on predefined texts, which can cause users to perceive the robots as repetitive and boring. Achieving natural and friendly communication is important for avoiding this scenario. To this end, we propose to apply state-of- the-art natural language generation models to provide our social robots with more diverse speech. In particular, we have implemented and evaluated two mechanisms: a paraphrasing module that transforms the robot’s utterances while keeping their original meaning, and a module to generate speech about a certain topic that adapts the content of this speech to the robot’s conversation partner. The results show that these models have great potential when applied to our social robots, but several limitations must be considered. These include the computational cost of the solutions presented, the latency that some of these models can introduce in the interaction, the use of proprietary models, or the lack of a subjective evaluation that complements the results of the tests conducted.
IS - Special Issue on Practical Applications of Agents and Multi-Agent Systems
M1 - 3
N2 - Social robots are making their way into our lives in different scenarios in which humans and robots need to communicate. In these scenarios, verbal communication is an essential element of human-robot interaction. However, in most cases, social robots’ utterances are based on predefined texts, which can cause users to perceive the robots as repetitive and boring. Achieving natural and friendly communication is important for avoiding this scenario. To this end, we propose to apply state-of- the-art natural language generation models to provide our social robots with more diverse speech. In particular, we have implemented and evaluated two mechanisms: a paraphrasing module that transforms the robot’s utterances while keeping their original meaning, and a module to generate speech about a certain topic that adapts the content of this speech to the robot’s conversation partner. The results show that these models have great potential when applied to our social robots, but several limitations must be considered. These include the computational cost of the solutions presented, the latency that some of these models can introduce in the interaction, the use of proprietary models, or the lack of a subjective evaluation that complements the results of the tests conducted.
PY - 2023
SE - 6
SP - 6
EP - 20
T2 - International Journal of Interactive Multimedia and Artificial Intelligence
TI - Using Large Language Models to Shape Social Robots’ Speech
UR - https://www.ijimai.org/journal/sites/default/files/2023-08/ijimai8_3_1.pdf
VL - 8
SN - 1989-1660
ER -