22 October: fyi -- phd funding, Grenoble

Index of October 2001 | Index of year: 2001 | Full index


PhD studentship in information extraction from running texts

Profile:

The Content Analysis group at Xerox Research Centre Europe (XRCE)
invites applications for a PhD research studentship in the domain of
automatic information extraction from running English texts, with
special emphasis on biological texts. Our research agenda
concerns theories, methods, tools and systems that make it possible to
uncover the content of natural language texts. To learn more about our
activities visit our web site at http://www.xrce.xerox.com/

Project:

The proposed PhD research will focus on refining the type of
information collected by existing information extraction systems.
The research will bear on the one hand on the exploration of
circumstances (e.g.localization, experimental conditions)
associated with core events, and on the other hand on identifying
meta-information attached to the events such as quotation source
(author, reference), modalities, scope of validity. Here is an
example of the kind of analysis expected (The sentence is taken
from a scientific paper on genetics) :

"(14) suggest that the rescue of the arrested-seed phenotype is
caused by the reactivation of the paternally derived wild-type MEA
allele in the developing seed,"

The core event:

"the rescue of the arrested-seed phenotype is caused by the
reactivation of the paternally derived wild-type MEA allele"

The circumstance related to the core event:

"in the developing seed"

The meta-information:

"(14) suggest"

Although the recognition and differentiation of these levels of
information is of high importance in most information extraction
tasks, they have not been treated in a coherent way up to now. The
theoretical challenge of the thesis is the definition of the
representation of the contents and the form of both components in
a language-independent way, their mapping into linguistic
realizations in English, as well as the participation in the
construction of a prototype for English texts in a special domain.
To carry out this task the PhD student will have at her/his
disposal the high-level syntactic and semantic analysis tools
developed in XRCE.

XRCE has a dynamic international team - the working language being
English. The working conditions are excellent in exceptional
surroundings in a residential suburb of Grenoble. The applicant
should have fluent reading and writing skills in English.

Send your CV and application letter to
Jean-Pierre Chanod (Jean-Pierre.Chanod@xrce.xerox.com)
Xerox Research Centre Europe
6. chemin Maupertuis
38240 Meylan
France




Index of October 2001 | Index of year: 2001 | Full index