Limits...
Why Robots Should Be Social: Enhancing Machine Learning through Social Human-Robot Interaction.

de Greeff J, Belpaeme T - PLoS ONE (2015)

Bottom Line: We observe that conveying a learning preference through the use of social cues results in better and faster learning by the robot.In addition, the social learning shows a clear gender effect with female participants being responsive to the robot's bids, while male teachers appear to be less receptive.This work shows how additional social cues in social machine learning can result in people offering better quality learning input to artificial systems, resulting in improved learning performance.

View Article: PubMed Central - PubMed

Affiliation: Centre for Robotics and Neural Systems, Plymouth University, Plymouth, United Kingdom; Interactive Intelligence Group, Delft University of Technology, Delft, the Netherlands.

ABSTRACT
Social learning is a powerful method for cultural propagation of knowledge and skills relying on a complex interplay of learning strategies, social ecology and the human propensity for both learning and tutoring. Social learning has the potential to be an equally potent learning strategy for artificial systems and robots in specific. However, given the complexity and unstructured nature of social learning, implementing social machine learning proves to be a challenging problem. We study one particular aspect of social machine learning: that of offering social cues during the learning interaction. Specifically, we study whether people are sensitive to social cues offered by a learning robot, in a similar way to children's social bids for tutoring. We use a child-like social robot and a task in which the robot has to learn the meaning of words. For this a simple turn-based interaction is used, based on language games. Two conditions are tested: one in which the robot uses social means to invite a human teacher to provide information based on what the robot requires to fill gaps in its knowledge (i.e. expression of a learning preference); the other in which the robot does not provide social cues to communicate a learning preference. We observe that conveying a learning preference through the use of social cues results in better and faster learning by the robot. People also seem to form a "mental model" of the robot, tailoring the tutoring to the robot's performance as opposed to using simply random teaching. In addition, the social learning shows a clear gender effect with female participants being responsive to the robot's bids, while male teachers appear to be less receptive. This work shows how additional social cues in social machine learning can result in people offering better quality learning input to artificial systems, resulting in improved learning performance.

No MeSH data available.


Schematic illustration of the language game flow.Both teacher and learner examine a shared world-view consisting of images. The teacher chooses one image as the topic and communicates an associated linguistic description to the learner. The learner tries to guess which image the teacher has in mind and receives feedback on its guess from the teacher. Based on this feedback the learner modifies its word-meaning associations.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4589374&req=5

pone.0138061.g001: Schematic illustration of the language game flow.Both teacher and learner examine a shared world-view consisting of images. The teacher chooses one image as the topic and communicates an associated linguistic description to the learner. The learner tries to guess which image the teacher has in mind and receives feedback on its guess from the teacher. Based on this feedback the learner modifies its word-meaning associations.

Mentions: The interaction between human participants and the robot is modelled through a language game [41, 42]. A language game is a single turn in a linguistic interaction and is played between two agents (people or robots). Both agents are presented with a shared world-view called the ‘context’, which consists of images. One agent names an image (the ‘topic’) without revealing which image it refers to and the other agent tries to guess the referent based on the provided name. This interaction is the essence of a single linguistic turn between two language users. When agents repeatedly play language games, it has been shown that both agents can reach an agreement on a lexicon and associated meanings [43–47]. While language games are often used to study the dynamics of language change, they can also be used to model the interaction between a teacher and learner. Through iteratively playing language games with a teacher, the learner will assimilate a lexicon and associated meanings. Fig 1 depicts a schematic overview of a single language game interaction, and a formal description of the language game as used in the experiments is provided below.


Why Robots Should Be Social: Enhancing Machine Learning through Social Human-Robot Interaction.

de Greeff J, Belpaeme T - PLoS ONE (2015)

Schematic illustration of the language game flow.Both teacher and learner examine a shared world-view consisting of images. The teacher chooses one image as the topic and communicates an associated linguistic description to the learner. The learner tries to guess which image the teacher has in mind and receives feedback on its guess from the teacher. Based on this feedback the learner modifies its word-meaning associations.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4589374&req=5

pone.0138061.g001: Schematic illustration of the language game flow.Both teacher and learner examine a shared world-view consisting of images. The teacher chooses one image as the topic and communicates an associated linguistic description to the learner. The learner tries to guess which image the teacher has in mind and receives feedback on its guess from the teacher. Based on this feedback the learner modifies its word-meaning associations.
Mentions: The interaction between human participants and the robot is modelled through a language game [41, 42]. A language game is a single turn in a linguistic interaction and is played between two agents (people or robots). Both agents are presented with a shared world-view called the ‘context’, which consists of images. One agent names an image (the ‘topic’) without revealing which image it refers to and the other agent tries to guess the referent based on the provided name. This interaction is the essence of a single linguistic turn between two language users. When agents repeatedly play language games, it has been shown that both agents can reach an agreement on a lexicon and associated meanings [43–47]. While language games are often used to study the dynamics of language change, they can also be used to model the interaction between a teacher and learner. Through iteratively playing language games with a teacher, the learner will assimilate a lexicon and associated meanings. Fig 1 depicts a schematic overview of a single language game interaction, and a formal description of the language game as used in the experiments is provided below.

Bottom Line: We observe that conveying a learning preference through the use of social cues results in better and faster learning by the robot.In addition, the social learning shows a clear gender effect with female participants being responsive to the robot's bids, while male teachers appear to be less receptive.This work shows how additional social cues in social machine learning can result in people offering better quality learning input to artificial systems, resulting in improved learning performance.

View Article: PubMed Central - PubMed

Affiliation: Centre for Robotics and Neural Systems, Plymouth University, Plymouth, United Kingdom; Interactive Intelligence Group, Delft University of Technology, Delft, the Netherlands.

ABSTRACT
Social learning is a powerful method for cultural propagation of knowledge and skills relying on a complex interplay of learning strategies, social ecology and the human propensity for both learning and tutoring. Social learning has the potential to be an equally potent learning strategy for artificial systems and robots in specific. However, given the complexity and unstructured nature of social learning, implementing social machine learning proves to be a challenging problem. We study one particular aspect of social machine learning: that of offering social cues during the learning interaction. Specifically, we study whether people are sensitive to social cues offered by a learning robot, in a similar way to children's social bids for tutoring. We use a child-like social robot and a task in which the robot has to learn the meaning of words. For this a simple turn-based interaction is used, based on language games. Two conditions are tested: one in which the robot uses social means to invite a human teacher to provide information based on what the robot requires to fill gaps in its knowledge (i.e. expression of a learning preference); the other in which the robot does not provide social cues to communicate a learning preference. We observe that conveying a learning preference through the use of social cues results in better and faster learning by the robot. People also seem to form a "mental model" of the robot, tailoring the tutoring to the robot's performance as opposed to using simply random teaching. In addition, the social learning shows a clear gender effect with female participants being responsive to the robot's bids, while male teachers appear to be less receptive. This work shows how additional social cues in social machine learning can result in people offering better quality learning input to artificial systems, resulting in improved learning performance.

No MeSH data available.