<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>
<head>
<meta content="text/html; charset=ISO-8859-1"
http-equiv="Content-Type">
<title></title>
</head>
<body bgcolor="#ffffff" text="#000000">
<br>
<br>
<div class="moz-text-html" lang="x-western"> <small><font
color="#3333ff">-------------------------- Final call for
papers --------------------------------<br>
</font></small><small><font color="#3333ff">PAPER SUBMISSION
DEADLINE: March 30, 2011 <br>
<br>
<br>
</font></small><small><font color="#3333ff"> Joint Workshop
FAM-LbR/KRAQ'11<br>
<b>Learning by Reading and its Applications in Intelligent
Question-Answering</b><br>
with IJCAI 2011<br>
July 16-18, 2011<br>
<a class="moz-txt-link-freetext"
href="http://www.rutumulkar.com/FAM-LbR-KRAQ-2011.php">http://www.rutumulkar.com/FAM-LbR-KRAQ-2011.php</a><br>
<br>
Call for Papers<br>
-----------------<br>
<br>
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.<br>
<br>
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.<br>
<br>
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?<br>
<br>
Topics of interest include (but are not limited to)<br>
<br>
* Language processing:<br>
o Analysis of existing language resources such as
Wikipedia<br>
o Language analysis (such as question processing,
answer identification)<br>
o Language generation and Explanation production <br>
* Reasoning aspects:<br>
o Abductive/deductive, commonsense, and other
reasoning<br>
o Reasoning under uncertainty or with incomplete
knowledge, models for explanation production and argumentation<br>
o Information fusion-integration,<br>
o Knowledge extraction from text vs. using pre-built
knowledge resources<br>
o Bridging knowledge gaps in text through inference<br>
o Knowledge Integration into evolving models<br>
o Bootstrapping Learning <br>
* Pragmatic dimensions of intelligently answering
questions:<br>
o User intentions, plans and goals recognition and
production<br>
o Conversational implicatures in responses,
principles for the design of cooperative systems.<br>
o Learning temporal sequences, causality, and other
semantics from text<br>
o Ontology learning, population, or expansion <br>
* Applications:<br>
o Question answering of semi-structured documents
such as wikipedia<br>
o Multimedia question answering, where you question
a more or less formal representation of the media objects<br>
o Spoken question answering (increasing uncertainty
caused by the speech recognition) <br>
* Evaluation:<br>
o Automatic Evaluation of learned Knowledge<br>
o Intrinsic evaluation of inference methods<br>
o Data-intensive vs Knowledge-intensive methods<br>
o Portability techniques for closed domains. <br>
<br>
Submission Information<br>
-----------------<br>
<br>
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:<br>
<br>
* Title<br>
* Authors' names, affiliations, and email addresses<br>
* Topic(s) of the above list, as appropriate<br>
* Abstract (short summary up to 5 lines) <br>
<br>
Important Dates<br>
-----------------<br>
<br>
March 14, 2011 - Paper Submission<br>
April 25, 2011 - Acceptance Notification<br>
May 16, 2011 - Camera ready paper due<br>
Location<br>
<br>
FAM-LbR/KRAQ 2011 is held with IJCAI 2011 (July 16-18, 2011)
in downtown Barcelona. Local information can be found from the
conference website. Please use the IJCAI style sheets to
prepare your submission. Reviewing will not be blind. <br>
<br>
Organizing Co-Chairs<br>
-----------------<br>
<br>
Rutu Mulkar-Mehta (<a class="moz-txt-link-abbreviated"
href="mailto:me@rutumulkar.com">me@rutumulkar.com</a>),
Patrick Saint-Dizier (<a class="moz-txt-link-abbreviated"
href="mailto:stdizier@irit.fr">stdizier@irit.fr</a>)<br>
Eduard Hovy (<a class="moz-txt-link-abbreviated"
href="mailto:hovy@isi.edu">hovy@isi.edu</a>), Marie-Francine
Moens (<a class="moz-txt-link-abbreviated"
href="mailto:Sien.Moens@cs.kuleuven.be">Sien.Moens@cs.kuleuven.be</a>)<br>
Bernardo Magnini (<a class="moz-txt-link-abbreviated"
href="mailto:magnini@fbk.eu">magnini@fbk.eu</a>)<br>
Chris Welty (<a class="moz-txt-link-abbreviated"
href="mailto:welty@us.ibm.com">welty@us.ibm.com</a>)</font></small>
</div>
</body>
</html>