[alife] Research Asst/Fellow in Computational Linguistics for Human-Robot Interaction

[Chrystopher Nehaniv]

Research Assistant/Research Fellow in Computational Linguistics for  
Human-Robot Interaction
School of Computer Science
Faculty of Engineering and Information Sciences

c 20,200 - 29,700 UK pounds sterling per annum, depending on  
qualifications, skills and experience

Applications from postgraduate/postdoctoral candidates are invited for  
a full-time research assistantship or research fellowship in  
computational linguistics for human-robot interaction. The post offers  
the opportunity to work within the Adaptive Systems Research Group, a  
proactive and dynamic research team with an excellent international  
research profile. You will work in the European project ITALK  
(Integration and Transfer of Action and Language Knowledge in Robot).  
The ITALK project aims to develop artificial embodied agents able to  
acquire complex behavioural, cognitive, and linguistic skills through  
individual and social learning. This will be achieved through the  
development of cognitive robots that learn to handle and manipulate  
objects and tools autonomously, to cooperate and communicate with  
other robots and humans, and to adapt their abilities to changing  
internal, environmental, and social conditions.

The main hypothesis behind the project is that the parallel  
development of action, conceptualization and social interaction  
permits the enhancement of language capabilities, which on their part  
enrich cognitive development. This is possible through the integration  
and transfer of knowledge and cognitive processes involved in  
sensorimotor learning and the construction of action categories,  
imitation and other forms of social learning, the acquisition of  
grounded conceptual representations and the development of the  
grammatical structure of language. Such a developmental approach  
towards the integration of action, conceptualization, social  
interaction and language has fundamental technological implications  
for designing communication in robots and overcoming current  
limitations of natural language interfaces and human-robot  
communication systems. Different partners in the highly  
interdisciplinary project consortium cooperate closely in the study of  
different aspects of this challenging work.

The research team at University of Hertfordshire is involved in the  
development of software and algorithms that will contribute to the  
development of complex, compositional and hierarchical behaviour and  
communication via scaffolded social learning, involving the use of  
deixis, gesture, reference, negation, imitation, and constructional  
grounding in embodied human-robot interaction. Processes centering on  
social learning play an important part in child development in the  
emergence of linguistic, communicative, and cognitive competencies,  
and computational algorithms will be developed to study these issues  
using leading-edge child-sized humanoid robot platforms (KASPAR http://kaspar.feis.herts.ac.uk/ 
  and the iCub http://www.robotcub.org/) available in the group. The  
work will use the facilities available in the Robotics and Interactive  
Systems Laboratory, as part of the Adaptive Systems Research Group at  
University of Hertfordshire which has a strong research record in  
adaptive behaviour, artificial life, and robot-human interaction. The  
research involves working as part of the ITALK team on: a) creating  
and/or extending developmental computational linguistics methods for  
use in situated, embodied interactions with robots, b) developing  
computational linguistics software for deployment on humanoid robots,  
c) investigating the acquisition of grammar and its relations to  
cognitive and behavioural scaffolding, and to interaction and the  
sensori-motor loop, d) designing, conducting and analysing human-robot  
interaction studies into the development of behavioural and linguistic  
competences, and e) writing and presenting scientific publications and  
reports documenting the work.

Applicants are expected to have excellent qualifications and  
experience in an appropriate area of Computational Linguistics,  
Artificial Intelligence, Artificial Life, Machine Learning, Autonomous  
Robotics, or related disciplines. Mastery of programming skills, as  
well as experience in natural language processing, cognitive and  
computational linguistics, and/or communicative pragmatics, are also  
essential. A specialist postgraduate degree or PhD, or other strong  
evidence of research experience is required, as well as excellent  
skills in presenting research and writing scientific documents in  
English. You should also be very motivated to working in an  
interdisciplinary and European research team.

The position is based on a fixed-term contract of up to three years.  
The post is available full-time. Start date: December 2008 or later.

Informal enquiries can be made to Prof. Chrystopher L. Nehaniv (C.L.Nehaniv at herts.ac.uk 
).

Closing Date: 30 October 2008 Quote Reference: EN8724AC

Interview Date: 13 November 2008

The University offers a range of benefits including a final salary  
pension scheme, professional development, family friendly policies,  
child care vouchers, waiving of course fees for the children of staff  
at UH, discounted memberships at the Hertfordshire Sports Village and  
generous annual leave.

Apply online at http://recruitment.herts.ac.uk/recruit or request an  
application pack from Human Resources on +44-1707 284802 (24hr  
voicemail), quoting the appropriate reference number.

Shortlisted for the Times Higher Education "University of the Year"  
award 2008