News Release

Robot learns language through 'conversation' with people

Robot moves from babbling to wordforms after a few minutes of interaction

Peer-Reviewed Publication

PLOS

A robot analogous to a child between 6 and 14 months old can develop rudimentary linguistic skills through interaction with a human participant, as reported June 13 in the open access journal PLoS ONE.

By engaging in a few minutes of "conversation" with humans, in which the participants were instructed to speak to the robot as if it were a small child, the robot moved from random syllabic babble to producing some salient wordforms, the names of simple shapes and colors. The participants were not researchers involved in the project, and were asked to use their own words, rather than any prescribed lines. The researchers, led by Caroline Lyon of the University of Hertfordshire, suggest that this work may be useful for understanding language acquisition in humans. "It is known that infants are sensitive to the frequency of sounds in speech, and these experiments show how this sensitivity can be modelled and contribute to the learning of word forms by a robot."

###

Citation: Lyon C, Nehaniv CL, Saunders J (2012) Interactive Language Learning by Robots: The Transition from Babbling to Word Forms. PLoS ONE 7(6): e38236. doi:10.1371/journal.pone.0038236

Financial Disclosure: This work is supported by the European Commission under project grant FP7-214668 for ITALK: Integration and Transfer of Action and Language Knowledge in Robots. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

Competing Interest Statement: The authors have declared that no competing interests exist.

PLEASE LINK TO THE SCIENTIFIC ARTICLE IN ONLINE VERSIONS OF YOUR REPORT (URL goes live after the embargo ends):

http://dx.plos.org/10.1371/journal.pone.0038236

Disclaimer: This press release refers to upcoming articles in PLoS ONE. The releases have been provided by the article authors and/or journal staff. Any opinions expressed in these are the personal views of the contributors, and do not necessarily represent the views or policies of PLoS. PLoS expressly disclaims any and all warranties and liability in connection with the information found in the release and article and your use of such information.

About PLoS ONE

PLoS ONE is the first journal of primary research from all areas of science to employ a combination of peer review and post-publication rating and commenting, to maximize the impact of every report it publishes. PLoS ONE is published by the Public Library of Science (PLoS), the open-access publisher whose goal is to make the world's scientific and medical literature a public resource.

All works published in PLoS ONE are Open Access. Everything is immediately available—to read, download, redistribute, include in databases and otherwise use—without cost to anyone, anywhere, subject only to the condition that the original authors and source are properly attributed. For more information about PLoS ONE relevant to journalists, bloggers and press officers, including details of our press release process and our embargo policy, see the everyONE blog at http://everyone.plos.org/media.


Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.