|09:00 - 09:05||Welcome|
|09:05 - 09:35||Francesco-Alessio Ursini and Aijun Huang: Objects and Nouns: Ontologies and Relations|
|09:35 - 10:05||Simon Dobnik, Robin Cooper and Staffan Larsson: Type Theory with Records: a General Framework for Modelling Spatial Language|
|10:05 - 10:25||Coffee break|
|10:25 - 10:55||Robert Ross and John Kelleher - Using the Situational Context to Resolve Frame of Reference Ambiguity in Route Description|
|10:55 - 11:25||Raveesh Meena, Johan Boye, Gabriel Skantze and Joakim Gustafson - Using a Spoken Dialogue System for Crowdsourcing Street-level Geographic Information|
|11:25 - 11:55||Robert Ross: Looking Back at Daisie: A Retrospective View on Situated Dialogue Systems Development|
|11:55 - 12:00||Concluding remarks|
Situated agents must be able to interact with the physical environment that are located in with their conversational partner. Such an agent receives information both from its conversational partner and the physical world which it must integrate appropriately. Furthermore, since both the world and the language are changeable from one context to another it must be able to adapt to such changes or to learn from new information. Embodied and situated language processing is trying to solve challenges in natural language processing such as word sense disambiguation and interpretation of words in discourse as well as it gives us new insights about human cognition, knowledge, meaning and its representation. Research in vision relies on information represented in natural language, for example in the form ontologies, as this captures how humans partition and reason about the world. On the other hand, gestures and sign language are languages that are expressed and interpreted as visual information.
The Second Workshop on Action, Perception and Language (APL’2) is a continuation of a successful APL workshop held at SLTC 2012 in Lund and is intended to a be a networking and community building event for researchers that are interested in any form of interaction of natural language with the physical world in a computational framework. Example areas include semantic theories of human language, action and perception, situated dialogue, situated language acquisition, grounding of language in action and perception, spatial cognition, generation and interpretation of gestures, generation and interpretation of scene descriptions from images and videos, integrated robotic systems and others. We welcome papers that describe either theoretical and practical solutions as well as work in progress.
Research connecting language and the world is a burgeoning research area to which several international conferences and workshops are devoted. It intends to connect several scientific communities (natural language technology, computer vision, robotics, localisation and navigation). Traditionally, natural language technology has worked separate from the other fields but research in the last 15 years has shown that there exist many synergies between them and that hybrid approaches may provide better solutions to many challenging problems, for example interpretation and generation of spatial language and object recognition. We hope that the APL workshop collocated with the SLTC conference would become a local forum that would lead to new collaborations between computer vision and natural language communities in Sweden.
Image of a Crispin apple courtesy of New York Apple Association, © New York Apple Association.
Anja Belz (University of Brighton), Johan Boye (KTH), Ellen Breitholtz (University of Gothenburg), Robin Cooper (University of Gothenburg), Nigel Crook (Oxford Brookes University), Kees Van Deemter (University of Aberdeen), Simon Dobnik (University of Gothenburg), Jens Edlund (KTH), Raquel Fernández (University of Amsterdam), Joakim Gustafson (KTH), Pat Healey (Queen Mary, University of London), Anna Hjalmarsson (KTH), Christine Howes (University of Gothenburg), John Kelleher (DIT), Emiel Krahmer (Tilburg University), Torbjörn Lager (University of Gothenburg), Shalom Lappin (King's College, London), Staffan Larsson (University of Gothenburg), Pierre Lison (University of Oslo), Peter Ljunglöf (University of Gothenburg/Chalmers), Joanna Isabelle Olszewska (University of Gloucestershire), Stephen Pulman (University of Oxford), Matthew Purver (Queen Mary, University of London), Robert Ross (DIT), David Schlangen (Bielefeld University), Gabriel Skantze (KTH), Holger Schultheis (University of Bremen), and Mats Wirén (Stockholm University)
Please submit your abstract as a pdf document with your author details removed through EasyChair here.
The submitted abstracts will be published on the workshop web-page and the authors will be given an opportunity to present their work at the workshop as oral presentations and/or posters (depending on the type and number of submissions).
Following the workshop the contributing authors will be invited to submit full-length (8 page) papers to be published in the CEUR Workshop Proceedings (ISSN 1613-0073) online.