AAAI "Language-Action Integration" workshop

International Workshop on

"Language - Action Tools for Cognitive Artificial Agents:
Integrating Vision, Action and Language"

A  Satellite event of the

25^th Conference on Artificial Intelligence (AAAI-2011),

7-11 August, 2011, San Francisco, USA

(New:  Presentations and Workshop AAAI technical Report)

Workshop Schedule

Invited Speakers and Panelists, Abstracts of talks and papers

Scope

Endowing artificial agents with language and action abilities has been a quest in many Artificial Intelligence (AI) subfields. A number of AI applications require coupling of language and motoric or visual action (and objects), ranging from language-based human-robot interaction to event recognition. Recent years have witnessed great advances in different disciplines that provide the theoretical and technological framework for an interdisciplinary approach to language-action integration. Neuroscience research provides more and more evidence on a common neural basis for language and action, both in perception and in production. A growing body of experimental cognitive science findings sheds light on the close interaction and reciprocal influence of language and action in a number of tasks, such as categorisation and learning.  On their part, technological advances in multisensory human behaviour measurement have enabled the development of recognitive and generative algorithms for the analysis of sensorimotor representations, ones that are analogical to language analysis and generation models. How could language-action integration benefit from all such developments? If it does, will this lead beyond the current state of the art in real-life AI applications that require generalisation and optimality in language-action integration?

The goal of this workshop is to bring together an interdisciplinary group of computational linguists, computer vision researchers, roboticists and neuroscientists that will address the issue of developing biologically-inspired language and action technology for artificial agents. The focus is both on

(a) how individual technologies can benefit from interdisciplinary research for going beyond the state of art in language-action integration tasks, and

(b) how language processing, visual processing and/or motor control algorithms can be integrated in artificial agents allowing for behaviour generalisation and optimisation.

Workshop Format

The workshop will be a two-day meeting, which will comprise a mix of invited talks, paper presentations and panel discussions.

* Author accepted paper camera ready submission deadline: May 27, 2011

* Workshop date: August 7 & 8, 2011

Invited Speakers

• Yiannis Aloimonos, University of Maryland, USA
  
• Tamara Berg, Stony Brook University, USA

• Tom Dean, Google, USA

• Jerry Feldman, University of Berkeley, USA

• Max Garagnani, MRC – Cognition & Brain Sciences Unit, Cambridge, U.K.

• Barbara Landau, Johns Hopkins University, USA
  

• Giorgio Metta, Italian Institute of Technology, Italy

• Ray Mooney, University of Texas, USA

• Katerina Pastra, Cognitive Systems Research Institute, Greece

• Stanley Peters, Stanford University, USA

• Jeffrey Siskind, Purdue University, USA 
  

• Jun Tani, RIKEN Brain Institute, Japan

• Evelyne Tzoukermann, The MITRE Corporation, USA

• Britta Wrede, University of Bielefeld, Germany

• Gabriella Vigliocco, University College London, U.K.

Invited Panelists

(list to be completed)

• Ruzena Bajcsy, UC Berkeley, USA

• Judith Klavans, University of Maryland, USA
• Vincent Müller, Anatolia College, Greece

Organizing Committee

Katerina Pastra  (kpastra@csri.gr, Cognitive Systems Research Institute, Greece)

Yiannis Aloimonos (yiannis@cs.umd.edu, University of Maryland, USA)

Giorgio Metta (giorgio.metta@iit.it, Italian Institute of Technology, Italy)

Luciano Fadiga (fdl@unife.it, University of Ferrara and Italian Inst. of Technology, Italy)

Sponsors: We gratefully acknowledge sponsorship of this event by Google Research and the EU-Cognition network.