<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>
<head>
<meta content="text/html;charset=ISO-8859-1" http-equiv="Content-Type">
</head>
<body bgcolor="#ffffff" text="#3333ff">
<div><font face="Calibri">-----------------------------------------<b>Extended
Deadline : 9th March 2010 6:00 PM PST</b>-----------------------------------------<br>
<br>
1st International Workshop on Formalisms and
Methodology for Learning by Reading (FAM-LbR)<br>
NAACL 2010 Workshop<br>
June 5-6, 2010</font></div>
<div><font face="Calibri">(</font><a
href="http://www.rutumulkar.com/FAM-LbR.php"><font face="Calibri">http://www.rutumulkar.com/FAM-LbR.php</font></a><font
face="Calibri"> )</font><br>
</div>
<div><font face="Calibri">NOTE: NEW DEADLINE FOR PAPERS IS <b>MARCH 9,
6:00 PM PST</b> </font></div>
<div><font face="Calibri"><br>
Call for Papers<br>
<br>
It has been a long term vision of Artificial Intelligence to develop
Learning by Reading systems that can capture knowledge from naturally
occurring texts, convert it into a deep logical notation and perform
some inferences/reasoning on them. Such systems directly build on
relatively mature areas of research, including Information Extraction
(for picking out relevant information from the text), Commonsense and
AI Reasoning (for deriving inferences from the knowledge acquired),
Bootstrapped Learning (for using the learned knowledge to expand the
knowledge base) and Question Answering (for providing evaluation
mechanisms for Learning by Reading systems). In Natural Language
Processing, statistical learning techniques have provided new
solutions and breakthroughs in various areas over the last decade. In
Knowledge Representation and Reasoning, systems have achieved
impressive performance and scale in far more complex problems than the
past.<br>
<br>
Learning by Reading is a two-part process. One part deals with
extracting interesting information from naturally occurring texts, and
the other is to use this extracted knowledge to expand the knowledge
base and consequently the system's inference capabilities. Previous
systems have chosen either a "broad and shallow" or a
"narrow and deep" knowledge acquisition and reasoning
strategy. These techniques are constrained by either their limited
reasoning ability or their extreme domain dependence.<br>
<br>
The goal of this workshop is to draw together researchers to explore
the nature and degree of integration possible between symbolic and
statistical techniques for knowledge acquisition and reasoning. In
particular, given these developments, what is the role of commonsense
knowledge and reasoning in language understanding? What are the
limitations of each style of processing, and how can they be overcome
by complementary strengths of the other? What are appropriate
evaluation metrics for Learning by Reading systems?<br>
<br>
We specifically invite papers of two kinds:
- innovative ideas and new approaches that have had some but not
exhaustive testing
- empirical results based on tested ideas that provide baselines for
future work
</font><br>
<br>
<font face="Calibri">Topics of interest include (but are not limited to)<br>
------------------------------ ----------------------<br>
Unguided and targeted (goal-directed) machine reading<br>
Wikipedia and web based machine reading<br>
Knowledge extraction from text vs. using pre-built knowledge
resources<br>
Learning temporal sequences, causality, and other semantics from
text<br>
Bridging knowledge gaps in text through inference<br>
Ontology learning or expansion<br>
Knowledge Integration into evolving models<br>
Abductive/deductive, commonsense, and other reasoning<br>
Bootstrapping learning by Reading systems</font></div>
<div><font face="Calibri"><br>
</font></div>
<div><font face="Calibri">We specifically invite papers of two
kinds:</font></div>
<div><font face="Calibri">- innovative ideas and new approaches that
have had some but not exhaustive testing</font></div>
<div><font face="Calibri">- empirical results based on tested ideas
that provide baselines for future work</font></div>
<div><font face="Calibri"><br>
<br>
Important Dates<br>
---------------------</font></div>
<div><font face="Calibri"><b>Mar 9, 2010</b>
Submission due date <------ NOTE: NEW
DEADLINE<br>
<b>6:00 PM PST</b><br>
</font></div>
<div><font face="Calibri">Mar 30, 2010
Notification of acceptance<br>
Apr 12, 2010 Camera ready papers due<br>
Jun 5-6, 2010 Workshops<br>
<br>
<br>
</font><br>
<font face="Calibri">Submission Instructions<br>
------------------------------<br>
</font><font face="Calibri">Authors are invited to submit papers on
original, unpublished work. Submissions should be formatted using the <a
href="http://naaclhlt2010.isi.edu/authors.html">NAACL 2010 stylefiles</a>,
and must not exceed 8 pages plus one page for references. Reviewing
will be blind. As reviewing will be blind, the paper should not include
the authors' names and affiliations. Furthermore, self-references that
reveal the author's identity, e.g., "We previously showed (Smith, 1991)
...", should be avoided. Instead, use citations such as "Smith
previously showed (Smith, 1991) ...". (Do not use anonymous citations.)
Do not include acknowledgments. Papers that do not conform to these
requirements will be rejected without review. All submissions must be
made online through the <a
href="https://www.softconf.com/naaclhlt2010/FAMLbR/">START system</a>.
</font><br>
<br>
<font face="Calibri">The deadline for submission is <b>9th March 2009,
6:00 PM</b></font><br>
<br>
<br>
<font face="Calibri"><br>
Location<br>
---------<br>
FAM-LbR is held with NAACL 2010 (June 1-6, 2010) in downtown Los
Angeles. Local information can be found from the conference website
(</font><a href="http://naaclhlt2010.isi.edu/index.html"><font
face="Calibri">http://naaclhlt2010.isi.edu/index.html</font></a><font
face="Calibri">).<br>
<br>
<br>
Related Workshops and Conferences<br>
------------------------------ ----<br>
Machine Reading, AAAI Spring Symposium 2007 (</font><a
href="http://www.cs.washington.edu/homes/pjallen/aaaiss07/index.htm"><font
face="Calibri">http://www.cs.washington.edu/homes/pjallen/aaaiss07/index.htm</font></a><font
face="Calibri">)</font></div>
<div><font face="Calibri">Learning by Reading and Learning to Read,
AAAI Spring Symposium 2009 (</font><a
href="http://www.coral-lab.org/%7Eoates/aaai2009ss/"><font
face="Calibri">http://www.coral-lab.org/~oates/aaai2009ss/</font></a><font
face="Calibri">)<br>
K-CAP 2009 (</font><a href="http://kcap09.stanford.edu/"><font
face="Calibri">http://kcap09.stanford.edu/</font></a><font
face="Calibri">)<br>
<br>
<br>
Organizers<br>
-----------<br>
Rutu Mulkar-Mehta<br>
James Allen<br>
Jerry Hobbs<br>
Eduard Hovy<br>
Bernardo Magnini<br>
Chris Manning<br>
<br>
Contact Information<br>
--------------------<br>
Please email Rutu Mulkar-Mehta (</font><a
href="mailto:me@rutumulkar.com"><font face="Calibri">me@rutumulkar.com</font></a><font
face="Calibri">) for
any further questions.</font></div>
<div class="moz-signature">-- <br>
<font face="calibri" size="3"><b> Rutu Mulkar-Mehta </b><br>
4676 Admiralty Way, Suite 1001,<br>
Marina Del Rey<br>
90292<br>
<br>
email: <a href="mailto=me@rutumulkar.com">me@rutumulkar.com</a><br>
url: <a href="http://www.rutumulkar.com">http://www.rutumulkar.com</a>
</font></div>
</body>
</html>