Logic List Mailing Archive

LaCATODA 2010: Linguistic and Cognitive Approaches to Dialog Agents

29 Mar - 1 Apr 2010
Leicester, U.K.

--------------------------------------------------
CALL FOR PAPERS
--------------------------------------------------
Linguistic and Cognitive Approaches To Dialog Agents (LaCATODA 2010)
http://sig.media.eng.hokudai.ac.jp/AISB10/LaCATODA2010/Home.html
At AISB2010 Convention
Leicester, UK
29th March – 1st April 2010

The age of information explosion gives us a whole new spectrum of
possibilities for creating an intelligent machine. Many marvelous ideas of
the dawn of Artificial Intelligence research faced problems of exceptions
and the impossibility of manual input of all needed knowledge, but today
we have vast amounts of data from sensors and text so that we can rethink
classical AI methods and approaches. The increased use of WWW, RFID,
Bluetooth, etc. could allow us to determine standard human behaviors,
emotions or even moral reasoning according to the Wisdom of Crowds
hypothesis. Collective input data could also help to retrieve knowledge
about the physical world we live in. By combining Natural Language
Processing methods with cognitive approaches, we can discover a new range
of intelligent systems that understand us, our environment and our
feelings. In this context, we see a role for NLP and cognitive approaches
to play in developing a new generation of user-friendly, safe systems
that, through interaction with the user and the world, can learn how to
reason, behave or speak naturally. We are interested in original papers on
systems and ideas for systems that use common sense knowledge and
reasoning, affective computing, cognitive methods, learning from broad
sets of data and acquiring knowledge, or language and user preferences.
The symposium intends to spark an interdisciplinary discussion on joining
forces to return AI to its original, broader and deeper goals which are
currently represented by AGI – Artificial General Intelligence.

TOPICS
of interest include but are not limited to (in alphabetical order):

- Affective computing
- Agent-based information retrieval
- Artificial humor
- Common sense knowledge and reasoning
- Computational cognition
- Daily life dialog systems
- Emotional intelligence simulation
- Ethical reasoning
- Language acquisition
- NLP text mining techniques
- Preference models
- Unlimited question answering
- User modeling
- Wisdom of Crowds approaches
- World knowledge acquisition
- Systems and approaches combining above topics

VENUE

The workshop will take place at De Montfort University in Leicester, as
part of the AISB 2010 Convention
(http://www.aisb.org.uk/convention/aisb10/), from March 31st to 1st
April, 2010. All participants must be registered for the AISB 2010
Convention and the registration for LaCATODA'10 is included in the
convention registration fee.

IMPORTANT DATES

Paper submission deadline: Monday 11th January 2010
Notification of acceptance: Monday 8th February 2010
Deadline for camera-ready submission: Monday 1st March 2010
Symposium date: 29th March - 1st April 2010
LaCATODA’10 will be held on Day 2 (30th March).

SUBMISSION GUIDELINES

Types of submission: Full and short papers.
Full papers will be reviewed in accordance with standard peer review
mechanism with a minimum of two reviewers.
The full papers are expected to be up to 8 pages.
Short papers are extended abstracts of up to 4 pages. One reviewer will
review short papers.
We invite submissions of high-quality papers describing original research
on different approaches to artificial dialog algorithms their
implementation, their supporting theories, and their applications.
Paper submission: click EasyChair link:
http://www.easychair.org/conferences/?conf=lacatoda10
The submission formats/templates to be used will be posted on the AISB
site soon: http://www.aisb.org.uk/convention/aisb10/AISB2010.html

PROGRAM COMMITTEE

Aladdin Ayesh, De Montfort University, UK
Kenji Araki, Hokkaido University, Japan
Haris Dindo, University of Palermo, Italy
Pawel Dybala, Hokkaido University,  Japan
Ben Goertzel, Novamente, USA
Yasutomo Kimura, Otaru University of Commerce, Japan
Fumito Masui, Kitami Institute fo Technology, Japan
Koji Murakami, Nara Institute of Science and Technology, Japan
Michal Ptaszynski, Hokkaido University,  Japan
Marcin Skowron, Austrian Research Institute of Artificial Intelligence,
Austria
Masato Tokuhisa,  Tottori University, Japan
Zygmunt Vetulani,  Adam Mickiewicz University, Poland

SYMPOSIUM CHAIR

Rafal Rzepka, Hokkaido University, Japan
kabura@media.eng.hokudai.ac.jp

TEL: (+81)(11)706-6535
FAX: (+81)(11)709-6277

Language Media Laboratory
Research Group of Information Media Science and Technology
Division of Media and Network Technologies
Graduate School of Information Science and Technology
Hokkaido University,
Kita-ku Kita 14 Nishi 9,
060-0814 Sapporo, Japan

BACKGROUND

During the IJCAI 2009 Invited Panel on "AAAI Study on Long-Term AI
Futures", top AI researchers presented their thoughts on what kind of
problems we need to tackle in the following decades. One dominating motive
was to make a machine that is safe and understands human needs. We propose
that in order to achieve this goal we must work on systems that combine
various skills that lead to a broader and deeper understanding of human
behavior, emotions and everyday life. The knowledge needed for this goal
is more available than ever. We can easily switch from a "building
knowledge for a system" approach to a "building systems for knowledge"
approach. For example, the classic dialog system ELIZA was built to use
the user’s utterances simply to pretend that it understands the lan
guage.
More than two decades later, the ALICE system showed that creating a
knowledge database for a talking agent increases its conversation skills.
However, we know that teaching a machine to talk about anything is very
laborious and inefficient. In the era of the Internet it is easier to
retrieve knowledge about a given topic and combine it with other elements
needed for understanding as goal/plan analysis or reasons/consequences
acquisition. Most researchers concentrate on single aspects of these
problems, so we decided to gather all interested developers together in
order to exchange our ideas and talk about methods for achieving a higher
level of more natural and safe intelligence. We would also like to discuss
the ethical aspects of systems that are based on uncontrollable data
sources as WWW or real life sensory input, which is one of the biggest
worries for many researchers and people from outside academia.

There are already many cases where researchers of NLP and cognitive
approaches attend the same meetings, for example on emotions. People like
Ben Goertzel started Artificial General Intelligence conferences two years
ago, gathering representatives of various fields with the same goal of
broadening the abilities of machines, as singularity is also one of the
hottest and most discussed problems of AI. Through our symposium we would
like the above-mentioned topics to appeal to an even wider audience by
accepting high-quality full papers and exchange new ideas by welcoming
short papers.