Author: jg
Date: Wed Apr 9 16:10:13 2014
New Revision: 1586005
URL: http://svn.apache.org/r1586005
Log:
some fixes for workshop page + generated HTML
Added:
uima/site/trunk/uima-website/docs/coling14.html
Modified:
uima/site/trunk/uima-website/xdocs/coling14.xml
Added: uima/site/trunk/uima-website/docs/coling14.html
URL:
http://svn.apache.org/viewvc/uima/site/trunk/uima-website/docs/coling14.html?rev=1586005&view=auto
==============================================================================
--- uima/site/trunk/uima-website/docs/coling14.html (added)
+++ uima/site/trunk/uima-website/docs/coling14.html Wed Apr 9 16:10:13 2014
@@ -0,0 +1,303 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
"http://www.w3.org/TR/html4/loose.dtd";>
+
+
+ <!--
====================================================================== -->
+ <!-- GENERATED FILE, DO NOT EDIT, EDIT THE XML FILE IN xdocs INSTEAD! -->
+ <!--
====================================================================== -->
+ <html>
+ <head>
+ <meta http-equiv="Content-Type" content="text/html;
charset=iso-8859-1"/>
+ <style type="text/css">@import "stylesheets/base.css";</style>
+ <meta name="author" value="
+ UIMA dev team">
+ <meta name="email" value="uima-...@apache.org">
+
+
+
+ <title>Apache UIMA - UIMA Workshop at COLING 2014 in
Dublin/Ireland</title>
+ </head>
+
+ <body>
+ <div class="topLogos">
+ <table border="0" width="100%" cellspacing="0">
+ <!-- TOP IMAGE -->
+ <tr>
+ <td align='LEFT'>
+ <a href="index.html">
+ <img style="border: 1px solid black;"
src="./images/UIMA_banner2tlpTm.png" alt="UIMA project logo" border="0"/>
+ </a>
+ </td>
+ <td align='CENTER'>
+ <div class="pageBanner">UIMA Workshop at COLING 2014
in Dublin/Ireland</div>
+ </td>
+ <td align='RIGHT'>
+ <a href="http://www.apache.org";>
+ <img src="./images/asf-logo-on-white-smallTm.png" alt="Apache UIMA"
border="0"/>
+ </a>
+ </td>
+ </tr>
+ </table>
+ <hr noshade="" size="1"/>
+ </div>
+ <table border="0" width="100%" cellspacing="4">
+ <tr>
+ <td align='RIGHT' colspan="2">
+ <form method="get" action="http://www.google.com/search";>
+ Search the site
+ <input type="text" name="q" size="25" maxlength="255"
value="" />
+ <input type="hidden" name="sitesearch"
value="http://uima.apache.org/"; />
+ <input name="Search" value="Search Site" type="submit"/>
+ </form>
+ </td>
+ </tr>
+ <tr> <!-- LEFT SIDE NAVIGATION -->
+ <td width="20%" valign="top">
+
+
+
+
+
+
+ <!-- regular menu -->
+ <div class="navBar">
+ <br/>
+ <div class="navBarItem"> <div
class="navPartHeading">General</div>
+ </div>
+ <div class="navBar">
+ <div class="navBarItem"> <a href="./index.html">Home</a>
+ </div>
+ <div class="navBarItem"> <a
href="./downloads.cgi">Downloads</a>
+ </div>
+ <div class="navBarItem"> <a
href="./documentation.html">Documentation</a>
+ </div>
+ <div class="navBarItem"> <a
href="./news.html">News</a>
+ </div>
+ <br style="line-height: .5em"/>
+ <div class="navBarItem"> <a
href="./mail-lists.html">Mailing Lists</a>
+ </div>
+ <div class="navBarItem"> <a
href="./mail-lists.html#Apache_UIMA_Forums">Forums</a>
+ <a
href="http://news.gmane.org/gmane.comp.apache.uima.general";
target="_blank"><em> Users</em> <img src="images/offsitelink.png" /></a>
+ <a href="http://news.gmane.org/gmane.comp.apache.uima.devel";
target="_blank"><em>Dev</em> <img src="images/offsitelink.png" /></a>
+ </div>
+ <div class="navBarItem"> <a
href="http://cwiki.apache.org/confluence/display/UIMA/Powered+by+Apache+UIMA";
target="_blank">Powered By UIMA <img src="images/offsitelink.png"/></a>
+ </div>
+ <br style="line-height: .5em"/>
+ <div class="navBarItem"> <a
href="http://issues.apache.org/jira/browse/uima"; target="_blank">Issue tracker
<img src="images/offsitelink.png"/></a>
+ </div>
+ <div class="navBarItem"> <a
href="http://cwiki.apache.org/confluence/display/UIMA/"; target="_blank">Wiki
<img src="images/offsitelink.png"/></a>
+ </div>
+ </div>
+ <br/>
+ <div class="navBarItem"> <div class="navPartHeading">Scaleout
Frameworks</div>
+ </div>
+ <div class="navBar">
+ <div class="navBarItem"> <a
href="./doc-uimaas-what.html">UIMA-AS</a>
+ </div>
+ <div class="navBarItem"> <a
href="./doc-uimaducc-whatitam.html">UIMA-DUCC</a>
+ </div>
+ </div>
+ <br/>
+ <div class="navBarItem"> <div
class="navPartHeading">Components & Tools</div>
+ </div>
+ <div class="navBar">
+ <div class="navBarItem"> <a
href="./sandbox.html#uima-addons-annotators">Annotators</a>
+ </div>
+ <div class="navBarItem"> <a
href="./toolsServers.html">Tools & Servers</a>
+ </div>
+ <div class="navBarItem"> <a
href="./sandbox.html">Addons and Sandbox</a>
+ </div>
+ <div class="navBarItem"> <a
href="./ruta.html">UIMA Ruta</a>
+ </div>
+ <div class="navBarItem"> <a
href="./uimafit.html">uimaFIT</a>
+ </div>
+ <div class="navBarItem"> <a
href="./external-resources.html">External Resources</a>
+ </div>
+ </div>
+ <br/>
+ <div class="navBarItem"> <div
class="navPartHeading">Community</div>
+ </div>
+ <div class="navBar">
+ <div class="navBarItem"> <a
href="./get-involved.html">Get Involved</a>
+ </div>
+ <div class="navBarItem"> <a
href="./contribution-policy.html">Contribution Policies</a>
+ </div>
+ <div class="navBarItem"> <a
href="./faq.html">FAQ</a>
+ </div>
+ <div class="navBarItem"> <a
href="./project-guidelines.html">Project Guidelines</a>
+ </div>
+ </div>
+ <br/>
+ <div class="navBarItem"> <div
class="navPartHeading">Development</div>
+ </div>
+ <div class="navBar">
+ <div class="navBarItem"> <a
href="./dev-quick.html">Quick Start: building</a>
+ </div>
+ <div class="navBarItem"> <a
href="./building-uima.html">Building from Source</a>
+ </div>
+ <div class="navBarItem"> <a
href="./one-time-setup.html">One-time setups</a>
+ </div>
+ <div class="navBarItem"> <a
href="./svn.html">Source Code</a>
+ </div>
+ <div class="navBarItem"> <a
href="./distribution.html">Creating a Distribution</a>
+ </div>
+ <div class="navBarItem"> <a
href="./release.html">Doing a UIMA release</a>
+ </div>
+ <div class="navBarItem"> <a
href="./eclipse-update-site.html">Eclipse Update Sites</a>
+ </div>
+ <div class="navBarItem"> <a
href="./codeConventions.html">Code Conventions</a>
+ </div>
+ <div class="navBarItem"> <a
href="./uima-specification.html">UIMA Specification (OASIS)</a>
+ </div>
+ <div class="navBarItem"> <a
href="./team-list.html">Project Team</a>
+ </div>
+ <div class="navBarItem"> <a
href="./maven-design.html">Maven Use</a>
+ </div>
+ <div class="navBarItem"> <a
href="./updating-website.html">Updating this Website</a>
+ </div>
+ </div>
+ <br/>
+ <div class="navBarItem"> <div class="navPartHeading">Events
and Conferences</div>
+ </div>
+ <div class="navBar">
+ <div class="navBarItem"> <a href="./gscl13.html">GSCL
2013</a>
+ </div>
+ <div class="navBarItem"> <a
href="./iks09.html">IKS 2009</a>
+ </div>
+ <div class="navBarItem"> <a
href="./gscl09.html">GSCL 2009</a>
+ </div>
+ <div class="navBarItem"> <a
href="./lsm09.html">LSM 2009</a>
+ </div>
+ <div class="navBarItem"> <a
href="./lrec08.html">LREC 2008</a>
+ </div>
+ <div class="navBarItem"> <a
href="./gldv07.html">GLDV 2007</a>
+ </div>
+ </div>
+ <br/>
+ <div class="navBarItem"> <div class="navPartHeading">ASF</div>
+ </div>
+ <div class="navBar">
+ <div class="navBarItem"> <a
href="http://www.apache.org/licenses/"; target="_blank">License <img
src="images/offsitelink.png"/></a>
+ </div>
+ <div class="navBarItem"> <a
href="http://www.apache.org/foundation/thanks.html"; target="_blank">ASF
Sponsors <img src="images/offsitelink.png"/></a>
+ </div>
+ <div class="navBarItem"> <a
href="http://www.apache.org/foundation/sponsorship.html"; target="_blank">ASF
Sponsorship <img src="images/offsitelink.png"/></a>
+ </div>
+ <div class="navBarItem"> <a
href="http://www.apache.org/security"; target="_blank">Security <img
src="images/offsitelink.png"/></a>
+ </div>
+ </div>
+ </div>
+ </td>
+ <td width="80%" align="left" valign="top">
+ <div
class="sectionTable">
+ <table class="sectionTable">
+ <tr><td>
+ <a name="UIMA Workshop at COLING 2014 in Dublin/Ireland"><h1><img
src="images/UIMA_4sq50tightCropSolid.png"/> UIMA Workshop at COLING 2014
in Dublin/Ireland</h1></a>
+ </td></tr>
+ <tr><td>
+ <blockquote class="sectionBody">
+ <p>
+ There will be a workshop with a strong focus on UIMA, as part of the
+ <a href="http://glicom.upf.edu/OIAF4HLT/";>Workshop on Open Infrastructures
and Analysis Frameworks for HLT</a>
+ at <a href="http://www.coling-2014.org/";>COLING 2014</a>, the 25th
International Conference on Computational Linguistics.
+ Please find the CFP below.
+</p>
+ <p>
+<blockquote>
+<h1
id="workshop-on-open-infrastructures-and-analysis-frameworks-for-hlt">Workshop
on Open Infrastructures and Analysis Frameworks for HLT</h1>
+<p>http://glicom.upf.edu/OIAF4HLT/</p>
+<p>At the 25th International Conference on Computational Linguistics (COLING
2014)<br />Helix Conference Centre at Dublin City University (DCU)<br />23-29
August 2014</p>
+<h2 id="description">Description</h2>
+<p>Recent advances in digital storage and networking, coupled with the
extension of human language technologies (HLT) into ever broader areas and the
persistence of difficulties in software portability, have led to an increased
focus on development and deployment of web-based infrastructures that allow
users to access tools and other resources and combine them to create novel
solutions that can be efficiently composed, tuned, evaluated, disseminated and
consumed. This in turn engenders collaborative development and deployment among
individuals and teams across the globe. It also increases the need for robust,
widely available evaluation methods and tools, means to achieve
interoperability of software and data from diverse sources, means to handle
licensing for limited access resources distributed over the web, and, perhaps
crucially, the need to develop strategies for multi-site collaborative work.</p>
+<p>For many decades, NLP has suffered from low software engineering standards
causing a limited degree of re-usability of code and interoperability of
different modules within larger NLP systems. While this did not really hamper
success in limited task areas (such as implementing a parser), it caused
serious problems for building complex integrated software systems, e.g., for
information extraction or machine translation. This lack of integration has led
to duplicated software development, work-arounds for programs written in
different (versions of) programming languages, and ad-hoc tweaking of
interfaces between modules developed at different sites.</p>
+<p>In recent years, two main frameworks, UIMA and GATE, have emerged that aim
to allow the easy integration of varied tools through common type systems and
standardized communication methods for components analysing unstructured
textual information, such as natural language. Both frameworks offer a solid
processing infrastructure that allows developers to concentrate on the
implementation of the actual analytics components. An increasing number of
members of the NLP community have adopted one of these frameworks as a platform
for facilitating the creation of reusable NLP components that can be assembled
to address different NLP tasks depending on their order, combination and
configuration. Analysis frameworks also reduce the problem of reproducibility
of NLP results by formalising solution composition and making language
processing tools shareable.</p>
+<p>Very recently, several efforts have been devoted to the development of web
service platforms for NLP. These platforms exploit the growing number of
web-based tools and services available for tasks related to HLT, including
corpus annotation, configuration and execution of NLP pipelines, and evaluation
of results and automatic parameter tuning. These platforms can also integrate
modules and pipelines from existing frameworks such as UIMA and GATE, in order
to achieve interoperability with a wide variety of modules from different
sources.</p>
+<p>Many of the issues and challenges surrounding these developments have been
addressed individually in particular projects and workshops, but there are
ramifications that cut across all of them. We therefore feel that this is the
moment to bring together participants representing the range of interests that
comprise the comprehensive picture for community-driven, distributed,
collaborative, web-based development and use for language processing software
and resources. This includes those engaged in development of infrastructures
for HLT as well as those who will use these services and infrastructures,
especially for multi-site collaborative work.</p>
+<h3 id="workshop-objectives">Workshop Objectives</h3>
+<p>The overall goal of this workshop is to provide a forum for discussion of
the requirements for an envisaged open âglobal laboratoryâ for HLT research
and development and establish the basis of a community effort to develop and
support it. To this end, the workshop will include both presentations
addressing the issues and challenges of developing, deploying, and using the
global laboratory for distributed and collaborative efforts and discussion that
will identify next steps for moving forward, fostering community-wide
awareness, and establishing and encouraging communication among the various
players.</p>
+<p>It aims at bringing together members of the NLP community specifically
users, developers or providers of components and tools for these frameworks in
order to explore and discuss the opportunities and challenges in using such
platforms for modern, well-engineered NLP applications.</p>
+<p>The challenge of creating reusable and interoperable components raises
particular interest and are affected by legal issues, such as potentially
incompatible licenses of components and tools as well as the technical aspects
of packaging and distribution of components. Also, tools are important, for
example to assemble complex processing pipelines, to manage the bodies of data
that are to be analysed and to visualize, explore, and further deploy the
analysis results. Further challenges are involved in embedding framework based
analysis within applications or using it in distributed computing scenarios,
such as deployment of and access to required resources. Finally, the
preservation of analysis results, their provenance and reproducibility are of
particular interest to the scientific user community.</p>
+<h3 id="topics">Topics</h3>
+<p>Workshop topics include, but are not limited to:</p>
+<ul>
+<li>processing of very large data collections: scale-out, parallelization, and
performance optimization</li>
+<li>advanced applications driven by an NLP framework</li>
+<li>sophisticated tools to build and manage complex processing pipelines</li>
+<li>analysis of results: exploration, evaluation, visualization, and
statistical analysis</li>
+<li>experience reports combining components from different sources, as well as
solutions to interoperability issues</li>
+<li>experience reports combining different frameworks (e.g.
GATE/UIMA/WebLicht/etc.)</li>
+<li>UIMA components with a special focus on genericity and type-system
independence</li>
+<li>repositories of ready-to-use components for UIMA and/or GATE</li>
+<li>distribution of components: documentation, licensing and packaging</li>
+<li>developing for UIMA or GATE: simplified APIs, debugging, unit testing, and
limitations of the frameworks</li>
+<li>combining annotation type systems in processing frameworks (GATE, UIMA,
etc.) with standardization efforts, such as done in the ISO TC37/SC4 or TEI
contexts.</li>
+<li>use of NLP frameworks in real-world "industry" settings</li>
+<li>reports on current projects and frameworks, their challenges and proposed
or implemented solutions, including efforts to address interoperability</li>
+<li>issues and challenges of multi-site collaborative projects, including
reports of implemented or proposed strategies</li>
+<li>pipeline management, including authentication, strategies for passing
resources through disparate tools and across hosting nodes, and licensing</li>
+<li>development and use of evaluation environments that facilitate assessment
of HLT component performance, iterative application development, and
replication of results</li>
+<li>community awareness and implementation of open infrastructures, including
how to engage the community, establish confidence in the process, and promote
use</li>
+</ul>
+<h2 id="dates">Dates</h2>
+<p>Paper Submission Deadline: 2nd May 2014<br />Author Notification Deadline:
6th June 2014<br />Camera-Ready Paper Deadline: 27th June 2014<br />Workshop:
23rd August 2014</p>
+<h2 id="organisers">Organisers</h2>
+<p>Nancy Ide<br />Department of Computer Science, Vassar College</p>
+<p>James Pustejovsky<br />Department of Computer Science, Brandeis
University</p>
+<p>Eric Nyberg<br />Language Technologies Institute, School of Computer
Science, Carnegie Mellon University</p>
+<p>Christopher Cieri<br />Linguistic Data Consortium, University of
Pennsylvania</p>
+<p>Jonathan Wright<br />Linguistic Data Consortium, University of
Pennsylvania</p>
+<p>Jens Grivolla<br />GLiCom, Universitat Pompeu Fabra</p>
+<p>Kalina Bontcheva<br />Department of Computer Science, University of
Sheffield</p>
+<h2 id="program-committee">Program Committee</h2>
+<p>confirmed:</p>
+<ul>
+<li>Richard Eckart de Castilho, TU Darmstadt</li>
+<li>Peter Klügl, Universität Würzburg</li>
+<li>Jens Grivolla, Universitat Pompeu Fabra</li>
+<li>Renaud Richardet, Ãcole Polytechnique Fédérale De Lausanne</li>
+<li>Michael Tanenblatt, Thomas J. Watson Research Center</li>
+<li>Azad Dehghan, University of Manchester</li>
+<li>Leon Derczynski, University of Sheffield</li>
+<li>Horacio Saggion, Universitat Pompeu Fabra</li>
+<li>Carlos RodrÃguez-Penagos, Barcelona Media</li>
+<li>Joan Codina, Universitat Pompeu Fabra</li>
+<li>Mark A. Greenwood, University of Sheffield</li>
+<li>Marie-Jean Meurs, Concordia University</li>
+<li>Kamel Nebhi, University of Geneva</li>
+<li>Bahar Sateli, Semantic Software Lab, Concordia University</li>
+<li>René Witte, Semantic Software Lab, Concordia University</li>
+<li>Graham Wilcock, Helsinki</li>
+<li>Torsten Zesch, University of Duisburg-Essen</li>
+<li>Yoshinobu Kano, PRESTO, Japan Science and Technology Agency</li>
+<li>Mohammad AL Asswad, Cornell University</li>
+</ul>
+</blockquote>
+
+</p>
+ </blockquote>
+ </p>
+ </td></tr>
+ </table>
+ </td>
+ </tr>
+ <!-- FOOTER -->
+ <tr><td colspan="2">
+ <hr noshade="" size="1"/>
+ </td></tr>
+ <tr><td colspan="2">
+ <table class="pageFooter">
+ <tr>
+ <td><a href="index.html">Home</a></td>
+ <td><a href="privacy-policy.html">Privacy Policy</a></td>
+ <td style="font-size:75%">
+ Copyright © 2006-2013, The Apache Software
Foundation.<br/>
+ Apache UIMA, UIMA, the Apache UIMA logo and the Apache Feather
logo are trademarks of The Apache Software Foundation.<br/>
+ All other marks mentioned may be trademarks or registered
trademarks of their respective owners.
+ </td>
+ <td><a href="mailto:d...@uima.apache.org";>Contact
us</a></td>
+ </tr>
+ </table>
+ </td></tr>
+ </table>
+ </body>
+ </html>
+
Modified: uima/site/trunk/uima-website/xdocs/coling14.xml
URL:
http://svn.apache.org/viewvc/uima/site/trunk/uima-website/xdocs/coling14.xml?rev=1586005&r1=1586004&r2=1586005&view=diff
==============================================================================
--- uima/site/trunk/uima-website/xdocs/coling14.xml (original)
+++ uima/site/trunk/uima-website/xdocs/coling14.xml Wed Apr 9 16:10:13 2014
@@ -39,113 +39,75 @@ under the License.
<p>
-<pre>
-Workshop on Open Infrastructures and Analysis Frameworks for HLT
-================================================================
-
-http://glicom.upf.edu/OIAF4HLT/
-
-At the 25th International Conference on Computational Linguistics (COLING
2014)
-Helix Conference Centre at Dublin City University (DCU)
-23-29 August 2014
-
-Description
------------
-
-Recent advances in digital storage and networking, coupled with the extension
of human language technologies (HLT) into ever broader areas and the
persistence of difficulties in software portability, have led to an increased
focus on development and deployment of web-based infrastructures that allow
users to access tools and other resources and combine them to create novel
solutions that can be efficiently composed, tuned, evaluated, disseminated and
consumed. This in turn engenders collaborative development and deployment among
individuals and teams across the globe. It also increases the need for robust,
widely available evaluation methods and tools, means to achieve
interoperability of software and data from diverse sources, means to handle
licensing for limited access resources distributed over the web, and, perhaps
crucially, the need to develop strategies for multi-site collaborative work.
-
-For many decades, NLP has suffered from low software engineering standards
causing a limited degree of re-usability of code and interoperability of
different modules within larger NLP systems. While this did not really hamper
success in limited task areas (such as implementing a parser), it caused
serious problems for building complex integrated software systems, e.g., for
information extraction or machine translation. This lack of integration has led
to duplicated software development, work-arounds for programs written in
different (versions of) programming languages, and ad-hoc tweaking of
interfaces between modules developed at different sites.
-
-In recent years, two main frameworks, UIMA and GATE, have emerged that aim to
allow the easy integration of varied tools through common type systems and
standardized communication methods for components analysing unstructured
textual information, such as natural language. Both frameworks offer a solid
processing infrastructure that allows developers to concentrate on the
implementation of the actual analytics components. An increasing number of
members of the NLP community have adopted one of these frameworks as a platform
for facilitating the creation of reusable NLP components that can be assembled
to address different NLP tasks depending on their order, combination and
configuration. Analysis frameworks also reduce the problem of reproducibility
of NLP results by formalising solution composition and making language
processing tools shareable.
-
-Very recently, several efforts have been devoted to the development of web
service platforms for NLP. These platforms exploit the growing number of
web-based tools and services available for tasks related to HLT, including
corpus annotation, configuration and execution of NLP pipelines, and evaluation
of results and automatic parameter tuning. These platforms can also integrate
modules and pipelines from existing frameworks such as UIMA and GATE, in order
to achieve interoperability with a wide variety of modules from different
sources.
-
-Many of the issues and challenges surrounding these developments have been
addressed individually in particular projects and workshops, but there are
ramifications that cut across all of them. We therefore feel that this is the
moment to bring together participants representing the range of interests that
comprise the comprehensive picture for community-driven, distributed,
collaborative, web-based development and use for language processing software
and resources. This includes those engaged in development of infrastructures
for HLT as well as those who will use these services and infrastructures,
especially for multi-site collaborative work.
-
-
-### Workshop Objectives
-
-The overall goal of this workshop is to provide a forum for discussion of the
requirements for an envisaged open âglobal laboratoryâ for HLT research and
development and establish the basis of a community effort to develop and
support it. To this end, the workshop will include both presentations
addressing the issues and challenges of developing, deploying, and using the
global laboratory for distributed and collaborative efforts and discussion that
will identify next steps for moving forward, fostering community-wide
awareness, and establishing and encouraging communication among the various
players.
-
-It aims at bringing together members of the NLP community specifically users,
developers or providers of components and tools for these frameworks in order
to explore and discuss the opportunities and challenges in using such platforms
for modern, well-engineered NLP applications.
-
-The challenge of creating reusable and interoperable components raises
particular interest and are affected by legal issues, such as potentially
incompatible licenses of components and tools as well as the technical aspects
of packaging and distribution of components. Also, tools are important, for
example to assemble complex processing pipelines, to manage the bodies of data
that are to be analysed and to visualize, explore, and further deploy the
analysis results. Further challenges are involved in embedding framework based
analysis within applications or using it in distributed computing scenarios,
such as deployment of and access to required resources. Finally, the
preservation of analysis results, their provenance and reproducibility are of
particular interest to the scientific user community.
-
-### Topics
-
-Workshop topics include, but are not limited to:
-
-- processing of very large data collections: scale-out, parallelization, and
performance optimization
-- advanced applications driven by an NLP framework
-- sophisticated tools to build and manage complex processing pipelines
-- analysis of results: exploration, evaluation, visualization, and statistical
analysis
-- experience reports combining components from different sources, as well as
solutions to interoperability issues
-- experience reports combining different frameworks (e.g.
GATE/UIMA/WebLicht/etc.)
-- UIMA components with a special focus on genericity and type-system
independence
-- repositories of ready-to-use components for UIMA and/or GATE
-- distribution of components: documentation, licensing and packaging
-- developing for UIMA or GATE: simplified APIs, debugging, unit testing, and
limitations of the frameworks
-- combining annotation type systems in processing frameworks (GATE, UIMA,
etc.) with standardization efforts, such as done in the ISO TC37/SC4 or TEI
contexts.
-- use of NLP frameworks in real-world "industry" settings
-- reports on current projects and frameworks, their challenges and proposed or
implemented solutions, including efforts to address interoperability
-- issues and challenges of multi-site collaborative projects, including
reports of implemented or proposed strategies
-- pipeline management, including authentication, strategies for passing
resources through disparate tools and across hosting nodes, and licensing
-- development and use of evaluation environments that facilitate assessment of
HLT component performance, iterative application development, and replication
of results
-- community awareness and implementation of open infrastructures, including
how to engage the community, establish confidence in the process, and promote
use
-
-Dates
------
-Paper Submission Deadline: 2nd May 2014
-Author Notification Deadline: 6th June 2014
-Camera-Ready Paper Deadline: 27th June 2014
-Workshop: 23rd August 2014
-
-Organisers
-----------
-Nancy Ide
-Department of Computer Science, Vassar College
-
-James Pustejovsky
-Department of Computer Science, Brandeis University
-
-Eric Nyberg
-Language Technologies Institute, School of Computer Science, Carnegie Mellon
University
-
-Christopher Cieri
-Linguistic Data Consortium, University of Pennsylvania
-
-Jonathan Wright
-Linguistic Data Consortium, University of Pennsylvania
-
-Jens Grivolla
-GLiCom, Universitat Pompeu Fabra
-
-Kalina Bontcheva
-Department of Computer Science, University of Sheffield
-
-Program Committee
------------------
-
-* Richard Eckart de Castilho, TU Darmstadt
-* Peter Klügl, Universität Würzburg
-* Jens Grivolla, Universitat Pompeu Fabra
-* Renaud Richardet, Ãcole Polytechnique Fédérale De Lausanne
-* Michael Tanenblatt, Thomas J. Watson Research Center
-* Azad Dehghan, University of Manchester
-* Leon Derczynski, University of Sheffield
-* Horacio Saggion, Universitat Pompeu Fabra
-* Carlos RodrÃguez-Penagos, Barcelona Media
-* Joan Codina, Universitat Pompeu Fabra
-* Mark A. Greenwood, University of Sheffield
-* Marie-Jean Meurs, Concordia University
-* Kamel Nebhi, University of Geneva
-* Bahar Sateli, Semantic Software Lab, Concordia University
-* René Witte, Semantic Software Lab, Concordia University
-* Graham Wilcock, Helsinki
-* Torsten Zesch, University of Duisburg-Essen
-* Yoshinobu Kano, PRESTO, Japan Science and Technology Agency
-* Mohammad AL Asswad, Cornell University
-</pre>
+<blockquote>
+<h1
id="workshop-on-open-infrastructures-and-analysis-frameworks-for-hlt">Workshop
on Open Infrastructures and Analysis Frameworks for HLT</h1>
+<p>http://glicom.upf.edu/OIAF4HLT/</p>
+<p>At the 25th International Conference on Computational Linguistics (COLING
2014)<br />Helix Conference Centre at Dublin City University (DCU)<br />23-29
August 2014</p>
+<h2 id="description">Description</h2>
+<p>Recent advances in digital storage and networking, coupled with the
extension of human language technologies (HLT) into ever broader areas and the
persistence of difficulties in software portability, have led to an increased
focus on development and deployment of web-based infrastructures that allow
users to access tools and other resources and combine them to create novel
solutions that can be efficiently composed, tuned, evaluated, disseminated and
consumed. This in turn engenders collaborative development and deployment among
individuals and teams across the globe. It also increases the need for robust,
widely available evaluation methods and tools, means to achieve
interoperability of software and data from diverse sources, means to handle
licensing for limited access resources distributed over the web, and, perhaps
crucially, the need to develop strategies for multi-site collaborative work.</p>
+<p>For many decades, NLP has suffered from low software engineering standards
causing a limited degree of re-usability of code and interoperability of
different modules within larger NLP systems. While this did not really hamper
success in limited task areas (such as implementing a parser), it caused
serious problems for building complex integrated software systems, e.g., for
information extraction or machine translation. This lack of integration has led
to duplicated software development, work-arounds for programs written in
different (versions of) programming languages, and ad-hoc tweaking of
interfaces between modules developed at different sites.</p>
+<p>In recent years, two main frameworks, UIMA and GATE, have emerged that aim
to allow the easy integration of varied tools through common type systems and
standardized communication methods for components analysing unstructured
textual information, such as natural language. Both frameworks offer a solid
processing infrastructure that allows developers to concentrate on the
implementation of the actual analytics components. An increasing number of
members of the NLP community have adopted one of these frameworks as a platform
for facilitating the creation of reusable NLP components that can be assembled
to address different NLP tasks depending on their order, combination and
configuration. Analysis frameworks also reduce the problem of reproducibility
of NLP results by formalising solution composition and making language
processing tools shareable.</p>
+<p>Very recently, several efforts have been devoted to the development of web
service platforms for NLP. These platforms exploit the growing number of
web-based tools and services available for tasks related to HLT, including
corpus annotation, configuration and execution of NLP pipelines, and evaluation
of results and automatic parameter tuning. These platforms can also integrate
modules and pipelines from existing frameworks such as UIMA and GATE, in order
to achieve interoperability with a wide variety of modules from different
sources.</p>
+<p>Many of the issues and challenges surrounding these developments have been
addressed individually in particular projects and workshops, but there are
ramifications that cut across all of them. We therefore feel that this is the
moment to bring together participants representing the range of interests that
comprise the comprehensive picture for community-driven, distributed,
collaborative, web-based development and use for language processing software
and resources. This includes those engaged in development of infrastructures
for HLT as well as those who will use these services and infrastructures,
especially for multi-site collaborative work.</p>
+<h3 id="workshop-objectives">Workshop Objectives</h3>
+<p>The overall goal of this workshop is to provide a forum for discussion of
the requirements for an envisaged open âglobal laboratoryâ for HLT research
and development and establish the basis of a community effort to develop and
support it. To this end, the workshop will include both presentations
addressing the issues and challenges of developing, deploying, and using the
global laboratory for distributed and collaborative efforts and discussion that
will identify next steps for moving forward, fostering community-wide
awareness, and establishing and encouraging communication among the various
players.</p>
+<p>It aims at bringing together members of the NLP community specifically
users, developers or providers of components and tools for these frameworks in
order to explore and discuss the opportunities and challenges in using such
platforms for modern, well-engineered NLP applications.</p>
+<p>The challenge of creating reusable and interoperable components raises
particular interest and are affected by legal issues, such as potentially
incompatible licenses of components and tools as well as the technical aspects
of packaging and distribution of components. Also, tools are important, for
example to assemble complex processing pipelines, to manage the bodies of data
that are to be analysed and to visualize, explore, and further deploy the
analysis results. Further challenges are involved in embedding framework based
analysis within applications or using it in distributed computing scenarios,
such as deployment of and access to required resources. Finally, the
preservation of analysis results, their provenance and reproducibility are of
particular interest to the scientific user community.</p>
+<h3 id="topics">Topics</h3>
+<p>Workshop topics include, but are not limited to:</p>
+<ul>
+<li>processing of very large data collections: scale-out, parallelization, and
performance optimization</li>
+<li>advanced applications driven by an NLP framework</li>
+<li>sophisticated tools to build and manage complex processing pipelines</li>
+<li>analysis of results: exploration, evaluation, visualization, and
statistical analysis</li>
+<li>experience reports combining components from different sources, as well as
solutions to interoperability issues</li>
+<li>experience reports combining different frameworks (e.g.
GATE/UIMA/WebLicht/etc.)</li>
+<li>UIMA components with a special focus on genericity and type-system
independence</li>
+<li>repositories of ready-to-use components for UIMA and/or GATE</li>
+<li>distribution of components: documentation, licensing and packaging</li>
+<li>developing for UIMA or GATE: simplified APIs, debugging, unit testing, and
limitations of the frameworks</li>
+<li>combining annotation type systems in processing frameworks (GATE, UIMA,
etc.) with standardization efforts, such as done in the ISO TC37/SC4 or TEI
contexts.</li>
+<li>use of NLP frameworks in real-world "industry" settings</li>
+<li>reports on current projects and frameworks, their challenges and proposed
or implemented solutions, including efforts to address interoperability</li>
+<li>issues and challenges of multi-site collaborative projects, including
reports of implemented or proposed strategies</li>
+<li>pipeline management, including authentication, strategies for passing
resources through disparate tools and across hosting nodes, and licensing</li>
+<li>development and use of evaluation environments that facilitate assessment
of HLT component performance, iterative application development, and
replication of results</li>
+<li>community awareness and implementation of open infrastructures, including
how to engage the community, establish confidence in the process, and promote
use</li>
+</ul>
+<h2 id="dates">Dates</h2>
+<p>Paper Submission Deadline: 2nd May 2014<br />Author Notification Deadline:
6th June 2014<br />Camera-Ready Paper Deadline: 27th June 2014<br />Workshop:
23rd August 2014</p>
+<h2 id="organisers">Organisers</h2>
+<p>Nancy Ide<br />Department of Computer Science, Vassar College</p>
+<p>James Pustejovsky<br />Department of Computer Science, Brandeis
University</p>
+<p>Eric Nyberg<br />Language Technologies Institute, School of Computer
Science, Carnegie Mellon University</p>
+<p>Christopher Cieri<br />Linguistic Data Consortium, University of
Pennsylvania</p>
+<p>Jonathan Wright<br />Linguistic Data Consortium, University of
Pennsylvania</p>
+<p>Jens Grivolla<br />GLiCom, Universitat Pompeu Fabra</p>
+<p>Kalina Bontcheva<br />Department of Computer Science, University of
Sheffield</p>
+<h2 id="program-committee">Program Committee</h2>
+<p>confirmed:</p>
+<ul>
+<li>Richard Eckart de Castilho, TU Darmstadt</li>
+<li>Peter Klügl, Universität Würzburg</li>
+<li>Jens Grivolla, Universitat Pompeu Fabra</li>
+<li>Renaud Richardet, Ãcole Polytechnique Fédérale De Lausanne</li>
+<li>Michael Tanenblatt, Thomas J. Watson Research Center</li>
+<li>Azad Dehghan, University of Manchester</li>
+<li>Leon Derczynski, University of Sheffield</li>
+<li>Horacio Saggion, Universitat Pompeu Fabra</li>
+<li>Carlos RodrÃguez-Penagos, Barcelona Media</li>
+<li>Joan Codina, Universitat Pompeu Fabra</li>
+<li>Mark A. Greenwood, University of Sheffield</li>
+<li>Marie-Jean Meurs, Concordia University</li>
+<li>Kamel Nebhi, University of Geneva</li>
+<li>Bahar Sateli, Semantic Software Lab, Concordia University</li>
+<li>René Witte, Semantic Software Lab, Concordia University</li>
+<li>Graham Wilcock, Helsinki</li>
+<li>Torsten Zesch, University of Duisburg-Essen</li>
+<li>Yoshinobu Kano, PRESTO, Japan Science and Technology Agency</li>
+<li>Mohammad AL Asswad, Cornell University</li>
+</ul>
+</blockquote>
</p>
