<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=utf-8">
</head>
<body text="#000000" bgcolor="#FFFFFF">
<div class="moz-forward-container"><br>
<meta http-equiv="content-type" content="text/html; charset=utf-8">
Pozdravljeni!<br>
Pošiljam najavo dogodka v organizaciji odseka E7, v sklopu
Solomonovih seminarjev.<br>
Ali moram še koga obvestiti? Hvala in lep pozdrav,<br>
Jolanda <br>
<div class="moz-forward-container">
<blockquote type="cite"
cite="mid:6421f8e2-893b-bd90-0dcb-313c0ebea4ac@ijs.si"> V
torek, 30. januarja 2018 v Veliki predavalnici IJS ob 14 uri
vabljeno predavanje <br>
<br>
*****************************************************************************<br>
<div class="moz-forward-container">Professor Sophia Ananiadou,
School of Computer Science, <br>
Director, National Centre for Text Mining <br>
Manchester Institute of Biotechnology <br>
University of Manchester <br>
<br>
Naslov predavanja: "Enriching Pathways using Text Mining" <br>
<br>
ABSTRACT: Pathway models are valuable resources that help
us to <br>
understand the various mechanisms underpinning complex
biological <br>
processes. Their curation is typically carried out through
manual <br>
inspection of the scientific literature, a
knowledge-intensive and <br>
laborious task. Text mining methods are used to automate
model <br>
reconstruction by increasing the speed and reliability of
discovery <br>
and extracting evidence from the literature . Complex
information from <br>
the literature is automatically extracted and then mapped to
reactions <br>
in existing pathway models. Information from the literature
(events) <br>
can act as corroborative evidence of the validity of these
reactions <br>
in a model or help to extend it. In addition, by
contextualising the <br>
textual evidence (extracting uncertainty, negation), we can
provide <br>
additional confidence measures for linking and ranking
information <br>
from the literature for model curation and ultimately
experimental <br>
design. In addition, visual analytics methods can act as the
nexus <br>
between text mining methods and modellers by providing an
interactive <br>
way to explore and analyse the statements linked with
pathways. <br>
<br>
SHORT BIO: <br>
Sophia Ananiadou is Professor in Computer Science, School of
Computer <br>
Science, The University of Manchester and Director of the
National <br>
Centre for Text Mining. Since 2005, she has successfully
directed <br>
NaCTeM to be currently a fully sustainable centre, carrying
out novel, <br>
world-leading research on text mining that then informs the
provision <br>
of services, tools, resources and infrastructure to a
variety of users <br>
from translational medicine, biology, biodiversity,
humanities, <br>
health, and social sciences. Research she has led has
advanced the <br>
state of the art in text mining and contributed in novel
ways to: <br>
automatic extraction of terminology and term variation;
development of <br>
robust taggers for biomedical text; automatic extraction of
events and <br>
their interpretation using machine learning methods;
development of <br>
large scale terminological resources for biomedicine and
biodiversity; <br>
linking textual evidence with metabolic and signaling
pathways; <br>
association mining and hypothesis generation; supporting the
<br>
development of systematic reviews using novel topic modeling
and <br>
clustering methods and the development of interoperable text
mining <br>
infrastructure to facilitate all the above applications
(Argo). Her <br>
team achieved top performance is several text mining
challenges, e.g. <br>
BioCreaTive (2010, 2013, 2015), BioNLP (2011, 2013). <br>
<br>
---------- <br>
Professor Sophia Ananiadou, School of Computer Science, <br>
Director, National Centre for Text Mining <br>
Manchester Institute of Biotechnology <br>
University of Manchester <br>
131 Princess Street, M1 7DN <br>
<a class="moz-txt-link-abbreviated"
href="http://www.nactem.ac.uk" moz-do-not-send="true">www.nactem.ac.uk</a>
[1] <br>
<a class="moz-txt-link-abbreviated"
href="mailto:sophia.ananiadou@manchester.ac.uk"
moz-do-not-send="true">sophia.ananiadou@manchester.ac.uk</a>
<br>
<a class="moz-txt-link-freetext"
href="http://www.nactem.ac.uk/staff/sophia.ananiadou/"
moz-do-not-send="true">http://www.nactem.ac.uk/staff/sophia.ananiadou/</a>
<br>
tel: +44 (0)161 306 3092 <br>
<br>
Links: <br>
------ <br>
[1] <a class="moz-txt-link-freetext"
href="http://www.nactem.ac.uk" moz-do-not-send="true">http://www.nactem.ac.uk</a>
</div>
</blockquote>
<br>
</div>
</div>
</body>
</html>