[PlanetKR] CFP: IJCAI Workshop on Learning by Reading and its Applications in Intelligent Question-Answering

Rutu Mulkar-Mehta me at rutumulkar.com
Thu Feb 17 06:48:02 EST 2011

Joint Workshop FAM-LbR/KRAQ'11
Learning by Reading and its Applications in Intelligent Question-Answering
with IJCAI 2011
July 18, 2011

Call for Papers

It has been a long term dream of AI to develop systems that can emulate 
human levels of language understanding and reasoning. Recent 
foundational, methodological and technological developments in Knowledge 
Representation (e.g. ontologies, knowledge bases incorporating various 
forms of incompleteness or uncertainty), Reasoning (e.g. data 
fusion-integration, argumentation, decision theory, fuzzy logic, 
incomplete knowledge bases, etc.), Natural Language Processing (such as 
information extraction, relation detection) and formal pragmatics (user 
models, intentions, etc.) make it possible to foresee the elaboration of 
much more accurate, cooperative and robust systems dedicated to 
understanding, learning and answering questions from textual data, 
operating either on open or closed domains. The time is right to start 
placing the pieces from all these different areas to develop a unified 
system for Learning by Reading and Automated Question Answering.

Until now, most approaches for QA and Learning by Reading have been 
either "narrow and deep" or "broad and shallow". Many text mining 
systems embody the latter. An important question arises whether a "broad 
and deep" approach is a possibility at this stage.

The goal of this workshop is to bring together researchers from 
different backgrounds (AI, NLP, linguistics, HLT and pragmatics) to 
explore possibilities of integrating the different techniques for 
building a system for Learning by Reading and/or Automated Question 
Answering. The workshop will be focused on models for intelligently 
analyzing data and cooperatively responding to the user queries. This 
includes areas such as AI models for processing data coming e.g. from 
search engines and models that provide users with explanations and 
arguments about response contents and the way they have been elaborated. 
Numerous interesting questions arise, including, how can we evaluate 
such systems automatically or semi-automatically? Is it possible to run 
such systems on a massive scale? What role does commonsense play in 
reasoning of textual data? Is it possible to extract this commonsense 
knowledge automatically?

Topics of interest include (but are not limited to)

     * Language processing:
           o Analysis of existing language resources such as Wikipedia
           o Language analysis (such as question processing, answer 
           o Language generation and Explanation production
     * Reasoning aspects:
           o Abductive/deductive, commonsense, and other reasoning
           o Reasoning under uncertainty or with incomplete knowledge, 
models for explanation production and argumentation
           o Information fusion-integration,
           o Knowledge extraction from text vs. using pre-built 
knowledge resources
           o Bridging knowledge gaps in text through inference
           o Knowledge Integration into evolving models
           o Bootstrapping Learning
     * Pragmatic dimensions of intelligently answering questions:
           o User intentions, plans and goals recognition and production
           o Conversational implicatures in responses, principles for 
the design of cooperative systems.
           o Learning temporal sequences, causality, and other semantics 
from text
           o Ontology learning, population, or expansion
     * Applications:
           o Question answering of semi-structured documents such as 
           o Multimedia question answering, where you question a more or 
less formal representation of the media objects
           o Spoken question answering (increasing uncertainty caused by 
the speech recognition)
     * Evaluation:
           o Automatic Evaluation of learned Knowledge
           o Intrinsic evaluation of inference methods
           o Data-intensive vs Knowledge-intensive methods
           o Portability techniques for closed domains.

Submission Information

We welcome short papers (max 4 pages), describing projects or ongoing 
research and long papers (max. 6 pages), that relate more established 
results. Papers must be sent in .pdf format. The following information 
MUST be included:

     * Title
     * Authors' names, affiliations, and email addresses
     * Topic(s) of the above list, as appropriate
     * Abstract (short summary up to 5 lines)

Important Dates

March 14, 2011 - Paper Submission
April 25, 2011 - Acceptance Notification
May 16, 2011 - Camera ready paper due

FAM-LbR/KRAQ 2011 is held with IJCAI 2011 (July 18, 2011) in downtown 
Barcelona. Local information can be found from the conference website.

Organizing Co-Chairs

Rutu Mulkar-Mehta (me at rutumulkar.com), Patrick Saint-Dizier 
(stdizier at irit.fr)
Eduard Hovy (hovy at isi.edu), Marie-Francine Moens (Sien.Moens at cs.kuleuven.be)
Bernardo Magnini (magnini at fbk.eu)
Chris Welty (welty at us.ibm.com)
*Rutu Mulkar-Mehta *
Ph.D. Candidate
4676 Admiralty Way, Suite 1001,
Marina Del Rey

email: me at rutumulkar.com <mailto=me at rutumulkar.com>
url: http://www.rutumulkar.com
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://discuss.it.uts.edu.au/pipermail/planetkr/attachments/20110216/750ee770/attachment.html 

More information about the PlanetKR mailing list