54,575 Hits in 5.6 sec

Embodied Agents in Language Learning for Children with Language Challenges [chapter]

Dominic W. Massaro
2006 Lecture Notes in Computer Science  
We have implemented these agents as computer-assisted speech and language tutors for hard of hearing and autistic children, and other children with language challenges.  ...  We report a new experiment showing its effectiveness for school children learning English as a new language.  ...  Learning a new language, however, is a significant challenge for all individuals, whether young or old.  ... 
doi:10.1007/11788713_118 fatcat:ldtybl4wwreerlhn7mmjgkxegy

Integration of Action and Language Knowledge: A Roadmap for Developmental Robotics

Angelo Cangelosi, Giorgio Metta, Gerhard Sagerer, Stefano Nolfi, Chrystopher Nehaniv, Kerstin Fischer, Jun Tani, Tony Belpaeme, Giulio Sandini, Francesco Nori, Luciano Fadiga, Britta Wrede (+5 others)
2010 IEEE Transactions on Autonomous Mental Development  
Four key areas of research challenges are discussed, specifically for the issues related to the understanding of: (i) how agents learn and represent compositional actions; (ii) how agents learn and represent  ...  This in turn will benefit the design of cognitive robots capable of learning to handle and manipulate objects and tools autonomously, to cooperate and communicate with other robots and humans, and to adapt  ...  In particular, we wish to thank the following people for comments and contributions to some of the sections in the paper: Davide Marocco, Francesco Nori, Vadim Tikhanoff, Alessandra Sciutti, Arjan Gijsberts  ... 
doi:10.1109/tamd.2010.2053034 fatcat:bqi276njyvcw5dkrd2bqv6hlwe

Vygotskian Autotelic Artificial Intelligence: Language and Culture Internalization for Human-Like AI [article]

Cédric Colas, Tristan Karch, Clément Moulin-Frier, Pierre-Yves Oudeyer
2022 arXiv   pre-print
learning and natural language processing.  ...  Looking forward, it highlights future opportunities and challenges for Vygotskian Autotelic AI research.  ...  For an embodied and situated rl agent, learning a skill (e.g. playing chess) is about learning to act so as to maximize future rewards measuring progression in that skill (e.g. +1 for winning a game, -  ... 
arXiv:2206.01134v1 fatcat:nr7m5nsbijhmphfe6uuxxrosca

Virtual Embodiment: A Scalable Long-Term Strategy for Artificial Intelligence Research [article]

Douwe Kiela and Luana Bulat and Anita L. Vero and Stephen Clark
2016 arXiv   pre-print
Here, we propose virtual embodiment as an alternative, long-term strategy for AI research that is multi-modal in nature and that allows for the kind of scalability required to develop the field coherently  ...  The field of Artifical Intelligence (AI) is very much a part of that list: the development of sophisticated natural language semantics is a sine qua non for achieving a level of intelligence comparable  ...  Second, these approaches lack any interaction, which plays an important role in language acquisition: children learn basic language understanding by interacting with the environment, and build more intricate  ... 
arXiv:1610.07432v1 fatcat:wrdcs3gfi5bktlmaxhlcjaksiy

Language (Re)modelling: Towards Embodied Language Understanding [article]

Ronen Tamari, Chen Shani, Tom Hope, Miriam R. L. Petruck, Omri Abend, Dafna Shahaf
2020 arXiv   pre-print
While natural language understanding (NLU) is advancing rapidly, today's technology differs from human-like language understanding in fundamental ways, notably in its inferior efficiency, interpretability  ...  This work proposes an approach to representation and learning based on the tenets of embodied cognitive linguistics (ECL).  ...  Acknowledgments We thank the reviewers for their insightful comments.  ... 
arXiv:2005.00311v2 fatcat:giwy3vxpazd73m5nmvj7lwo32e

Guidelines for Designing Social Robots as Second Language Tutors

Tony Belpaeme, Paul Vogt, Rianne van den Berghe, Kirsten Bergmann, Tilbe Göksun, Mirjam de Haas, Junko Kanero, James Kennedy, Aylin C. Küntay, Ora Oudgenoeg-Paz, Fotios Papadopoulos, Thorsten Schodde (+12 others)
2018 International Journal of Social Robotics  
In recent years, it has been suggested that social robots have potential as tutors and educators for both children and adults.  ...  As language learning relies on situated, grounded and social learning, in which interaction and repeated practice are central, social robots hold promise as educational tools for supporting second language  ...  Acknowledgements We are grateful to all research assistants, participating schools, parents, and their children for their assistance in this project.  ... 
doi:10.1007/s12369-018-0467-6 pmid:30996752 pmcid:PMC6438435 fatcat:xah6iul7pvatnpetwtecl5g26i

Building Human-like Communicative Intelligence: A Grounded Perspective

Marina Dubova
2021 Cognitive Systems Research  
These components include embodying machines in a perception-action cycle, equipping agents with active exploration mechanisms so they can build their own curriculum, allowing agents to gradually develop  ...  I review results on 4E research lines in Cognitive Science to distinguish the main aspects of naturalistic learning conditions that play causal roles for human language development.  ...  ACKNOWLEDGEMENTS I would like to thank Justin Wood and Robert Goldstone for their extremely helpful feedback at every stage of the preparation of this manuscript.  ... 
doi:10.1016/j.cogsys.2021.12.002 fatcat:c2dwpl43dba2dduhmbm4fg2ayy

A formal model of visual attention in embodied language acquisition

C. Yu, D. H Ballard
2010 Journal of Vision  
The challenge ahead is to develop formal models of language acquisition that can shed light on the leverage provided by embodiment and attention.  ...  This paper describes a computational model of embodied language acquisition that can simulate some of the formative steps in infant language acquisition.  ...  Among them, one of the most challenging tasks is to learn words (symbols) in their native language by discovering the sound patterns of words and associating them with their meanings embodied in the physical  ... 
doi:10.1167/3.9.309 fatcat:mf4tyji6ojb2dlpfsfxrykjafy

Building a Conversational Agent based on the principles of Cognitive Pragmatics using Cognitive Architecture

Asst. Prof. G. Gnaneswari, Dr. Vijayakumar
2017 International Journal of Engineering Research and  
Speech recognition, natural language processing and cognitive architecture all play a vital role in building a conversational agent.  ...  Conversational agents which use computational linguistics techniques faces some technical challenges such accuracy and efficiency. (1) two basic challenges in building a conversational agent are understanding  ...  : This research group develops robots that empower humans by interactively learning from  Robotic Language Learning Companions: These systems help children in interactive language learning and focuses  ... 
doi:10.17577/ijertv6is020093 fatcat:3nwoyo44vrf2bmwbapnr55qaqa

State-of-the-art in TEL to support social communication skill development in children with autism: a multi-disciplinary review

Katerina Avramides, Sara Bernardini, Mary Ellen Foster, Christopher Frauenberger, Lila Kossyvaki, Marilena Mademtzi
2012 International Journal of Technology Enhanced Learning  
Lila has a strong interest in school-based interventions to promote social communication in children with autism and learning difficulties.  ...  include embodied communication, natural language generation, multimodal dialogue systems, and human-robot interaction.  ...  Acknowledgements We would like to thank the children, teachers, and parents who worked with us on the ECHOES project, funded by the Economic and Social Research Council and Engineering and Physical Sciences  ... 
doi:10.1504/ijtel.2012.051819 fatcat:wpsohkbnl5fpfcffjlfmqjvbny

Social Neuro AI: Social Interaction as the "dark matter" of AI [article]

Samuele Bolotta, Guillaume Dumas
2022 arXiv   pre-print
To conclude, we discuss the example of active inference, which offers powerful insights for developing agents that possess biological realism, can self-organize in time, and are socially embodied.  ...  Then, we discuss three lines of research that fall under the umbrella of Social NeuroAI and can contribute to developing socially intelligent embodied agents in complex environments.  ...  Here, we highlight that, among others, low sample efficiency is one of the greatest challenges for MARL, as millions of interactions with the environment are usually needed for agents to learn.  ... 
arXiv:2112.15459v3 fatcat:ofcmawor2vdxhl5k3sqpaxxhbm

Anchoring Social Symbol Grounding in Children's Interactions

Paul Vogt, J. Douglas Mastin
2013 Künstliche Intelligenz  
In order to use multi-agent modelling as a reliable tool to study human language acquisition, we argue that the simulations need to be anchored in observations of social interactions that children encounter  ...  In addition, we discuss some challenges that need to be solved in order to construct the computational model.  ...  Acknowledgements The research presented in this article is funded by a Vidi grant awarded to the first author by the Netherlands Organisation for Scientific Research (NWO, grant no. 276-70-018).  ... 
doi:10.1007/s13218-013-0243-6 fatcat:akwmz6jc7rg3bnlyebsoicb5k4

Crossmodal Language Grounding, Learning, and Teaching

Stefan Heinrich, Cornelius Weber, Stefan Wermter, Ruobing Xie, Yankai Lin, Zhiyuan Liu
2016 Neural Information Processing Systems  
In this position paper we present visionand action-embodied language learning research as part of a project investigating multi-modal learning.  ...  and scale-up the language acquisition to a level of language development in children of age up to two years.  ...  Acknowledgments The authors gratefully acknowledge support from the German Research Foundation (DFG) and the National Science Foundation of China (NSFC) under project Crossmodal Learning, TRR-169.  ... 
dblp:conf/nips/HeinrichWWXLL16 fatcat:yfu2gsgejjf7bo3qtq7ca7ceiu

Imitation of a Pedagogical Agent's Gestures Enhances Memory for Words in Second Language

Manuela Macedonia
2014 Science Journal of Education  
Pedagogical agents (PAs) are virtual characters in computer-based learning environments. PAs can train humans in various domains.  ...  Over four days, we found that, compared to the baseline and to mere observation, imitation of enactment significantly enhanced memory for words in the foreign language.  ...  The authors are grateful to Bob Bach for helpful discussion.  ... 
doi:10.11648/j.sjedu.20140205.15 fatcat:lrbvesf5xzbthkwc25mjw3ep6e

Child-Robot Interactions for Second Language Tutoring to Preschool Children

Paul Vogt, Mirjam de Haas, Chiara de Jong, Peta Baxter, Emiel Krahmer
2017 Frontiers in Human Neuroscience  
Finally, a big thank you to all the children and their parents for participating in our research.  ...  We also thank Kinderopvanggroep Tilburg and all participating daycare centers and preschools for their assistance in this research.  ...  challenges for developing these.  ... 
doi:10.3389/fnhum.2017.00073 pmid:28303094 pmcid:PMC5332435 fatcat:nvg2e5c63nb3djrjd7gwk6q3uq
« Previous Showing results 1 — 15 out of 54,575 results