<html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class=""><div class=""><div class="">The SMILES (Sensorimotor Interaction, Language and Embodiment of Symbols) Workshop will take place virtually at the ICDL 2020, on 2nd & 3rd November 2020.</div><div class=""><br class=""></div><div class="">* Call for abstracts and papers:</div><div class="">- *** Deadline: extended to 12th of October 2020 ***</div><div class=""> - paper abstracts: 2 pages</div><div class=""> - long papers: 4-6 pages</div><div class="">- Submissions: <a href="mailto:smiles.conf@gmail.com" class="">smiles.conf@gmail.com</a></div><div class="">- Papers format: free format, but similar shape to ICDL conference <a href="https://cis.ieee.org/publications/t-cognitive-and-developmental-systems/tcds-information-for-authors" class="">https://cis.ieee.org/publications/t-cognitive-and-developmental-systems/tcds-information-for-authors</a></div><div class="">- Workshop dates: 2nd & 3rd November 2020 afternoons (1 to 6 pm CET)</div><div class=""><br class=""></div><div class="">* Workshop Short Description</div><div class="">On the one hand, models of sensorimotor interaction are embodied in the environment and in the interaction with other agents. On the other hand, recent Deep Learning development of Natural Language Processing (NLP) models allow to capture increasing language complexity (e.g. compositional representations, word embedding, long term dependencies). However, those NLP models are disembodied in the sense that they are learned from static datasets of text or speech. How can we bridge the gap from low-level sensorimotor interaction to high-level compositional symbolic communication? The SMILES workshop will address this issue through an interdisciplinary approach involving researchers from (but not limited to):</div><div class="">- Sensori-motor learning,</div><div class="">- Emergent communication in multi-agent systems,</div><div class="">- Chunking of perceptuo-motor gestures (gestures in a general sense: motor, vocal, ...),</div><div class="">- Sensori-motor learning,</div><div class="">- Symbol grounding and symbol emergence,</div><div class="">- Compositional representations for communication and action sequence,</div><div class="">- Hierarchical representations of temporal information,</div><div class="">- Language processing and acquisition in brains and machines,</div><div class="">- Models of animal communication,</div><div class="">- Understanding composition and temporal processing in neural network models, and</div><div class="">- Enaction, active perception, perception-action loop.</div><div class=""><br class=""></div><div class="">* More info</div><div class="">- workshop website : <a href="https://sites.google.com/view/smiles-workshop/" class="">https://sites.google.com/view/smiles-workshop/</a></div><div class="">- contact: <a href="mailto:smiles.conf@gmail.com" class="">smiles.conf@gmail.com</a></div><div class="">- organizers: Xavier Hinaut, Clement Moulin-Frier, Silvia Pagliarini, Joni Zhong, Loo CHU KIONG, Michael Spranger, Tadahiro Taniguchi</div><div class="">- ICDL conference website: <a href="https://cdstc.gitlab.io/icdl-2020/" class="">https://cdstc.gitlab.io/icdl-2020/</a></div></div><div class=""><br class=""></div><br class=""><div class="">
Xavier Hinaut<br class="">Inria Researcher (CR)<br class="">Mnemosyne team, Inria<br class="">LaBRI, Université de Bordeaux<br class="">Institut des Maladies Neurodégénératives<br class="">+33 5 33 51 48 01<br class=""><a href="http://www.xavierhinaut.com" class="">www.xavierhinaut.com</a><br class=""><br class=""><br class=""></div></body></html>