<html>
<head>
<meta http-equiv="Content-Type" content="text/html;
charset=ISO-8859-1">
</head>
<body bgcolor="#FFFFFF" text="#000000">
Taxonomy Extraction with Applications in Semantics (TEXAS)<br>
<div class="moz-forward-container"> <a moz-do-not-send="true"
class="moz-txt-link-freetext"
href="http://emnlp2014.org/workshops/TEXAS/call.html">http://emnlp2014.org/workshops/TEXAS/call.html</a><br>
<br>
At EMNLP 2014, 29 October 2014, Doha, Qatar<br>
<br>
** Submission deadline: July 26, 2014 **<br>
<br>
Taxonomies form the backbone of knowledge-based systems by
organizing knowledge in a machine interpretable manner and
facilitating information integration. Hierarchical structures
provide valuable input in knowledge-intensive applications such as
question answering and textual entailment and are useful tools for
browsing and navigation of document collections, especially when
applied for exploration and discovery. <br>
<br>
The TEXAS workshop aims to provide a venue for presenting and
discussing approaches that evaluate taxonomy extraction, and its
subtasks (term/concept extraction, term/concept relation
discovery, taxonomy construction and cleaning) in the context of
semantic applications such as: entity search, entity
disambiguation and linking, information integration and
summarization, knowledge acquisition, knowledge sharing, inference
in NLP tasks (question answering, textual entailment), etc. In
this way, progress towards automatically constructed hierarchies
can be measured relative to other tasks and real-world
applications. <br>
<p> Expected research topics of relevance to the workshop: </p>
<ul>
<li>application-based evaluation of taxonomies in question
answering, document browsing,document clustering, expert
finding or other applications;</li>
<li>using automatically constructed taxonomies for searching,
browsing and organizing information</li>
<li>constructing taxonomies for/from social media</li>
<li>probabilistic models for topic hierarchies (hierarchical
topic modelling) </li>
<li>constructing taxonomies using hierarchical clustering </li>
<li>using distributional models for taxonomy construction </li>
<li>acquisition and modelling of categorical structure and
modelling human category acquisition </li>
<li>constructing topic categorization systems and subject
hierarchies </li>
<li>constructing hierarchical faceted metadata structures </li>
<li>methods for transforming semi-structured knowledge resources
into taxonomies </li>
<li>merging and aligning existing resources for taxonomy
construction </li>
<li>comparing, aligning and evaluating existing hierarchical
structures </li>
<li>domain glossary acquisition and extracting taxonomies from
definitions </li>
<li>constructing application/domain specific taxonomies from
existing resources (lexical resources,Linked Open Data,
Wikipedia category structure, semantic networks)</li>
<li>using different hierarchical structures (e.g., tree, DAG)
and relation types (e.g., hyponymy, meronymy) for taxonomy
construction</li>
<li>attaching Named Entities to hierarchical structures and
using Named Entities to drive taxonomy construction by
extensional analysis</li>
<li>multilinguality and taxonomies: constructing and using
multilingual taxonomies</li>
</ul>
--------------------------------------------------------------------------------<br>
Paper Submissions<br>
<br>
Submissions should be made electronically, using Softconf at <a
moz-do-not-send="true" class="moz-txt-link-freetext"
href="https://www.softconf.com/emnlp2014/texas2014/">https://www.softconf.com/emnlp2014/texas2014/</a>.<br>
Submissions should follow the two-column format of ACL 2014
proceedings and should not exceed 8 pages of content and one
additional references page. The LaTeX style files and the
Microsoft Word style files tailored for this year's conference are
available at: <a moz-do-not-send="true"
class="moz-txt-link-freetext"
href="http://emnlp2014.org/call.html">http://emnlp2014.org/call.html</a>.<br>
<br>
The reviewing of papers will be double-blind, so please make sure
your paper shows the title, but no author information. You should
likewise not have any self identifying references anywhere in the
paper submitted for review. For example, rather than this: "We
showed previously (Smith, 2001), ...", use citations such as:
"Smith (2001) previously showed ...". References to your own work
in thesis proposals should also be anonymized. You may for example
write it as “in X (2000) we showed”, etc. and do not add your
papers in the reference list. <br>
<br>
Important Dates<br>
- Paper submission: July 26, 2014<br>
- Paper notification: August 26, 2014<br>
- Camera ready: September 15<br>
- Workshop: October 29, 2014<br>
<br>
Further information: <a moz-do-not-send="true"
class="moz-txt-link-freetext"
href="http://emnlp2014.org/workshops/TEXAS/call.html">http://emnlp2014.org/workshops/TEXAS/call.html</a><br>
<br>
Workshop Organisers:<br>
Georgeta Bordea - Unit for Natural Language Processing, Insight,
National University of Ireland, Galway<br>
Paul Buitelaar - Unit for Natural Language Processing, Insight,
National University of Ireland, Galway<br>
Stefano Faralli - Linguistic Computing Laboratory, Dept. of
Computer Science, Sapienza University of Rome, Italy<br>
Roberto Navigli - Linguistic Computing Laboratory, Dept. of
Computer Science, Sapienza University of Rome, Italy<br>
</div>
<br>
The TEXAS workshop is supported by the following projects:
“MultiJEDI” ERC Starting Grant (<a href="http://multijedi.org/">http://multijedi.org/</a>),
lead by Prof. Roberto Navigli at the Linguistic Computing Laboratory
of the Sapienza University of Rome, Italy; Linked Data and Text
Mining research area (<a href="http://nlp.deri.ie/">http://nlp.deri.ie/</a>),
lead by Dr. Paul Buitelaar at INSIGHT (<a
href="http://www.insight-centre.org/">http://www.insight-centre.org/</a>),
the Irish Centre for Data Analytics, National University of Ireland,
Galway.<br>
</body>
</html>