Corpora: Ph.D. and postdoctoral positions, ILK / CL, Tilburg University

[Antal van den Bosch]

           Ph.D. position      &     Postdoctoral position

                 ILK / Computational Linguistics
               Tilburg University, The Netherlands


The Induction of Linguistic Knowledge (ILK) research group has open
positions for one Ph.D. student and one postdoc for a new project
funded by the Flemish-Dutch Committee of the National Foundations for
Research in the Netherlands and Belgium, entitled

  Automatic text analysis and machine learning for prosody

Work in this bi-national project will be carried out in close
cooperation with ILK's sister group CNTS (Center for Dutch Language
and Speech), University of Antwerp, Belgium. The project involves
three new positions in total. The project team will be working with
Antal van den Bosch (ILK, Tilburg), Walter Daelemans (CNTS, Antwerp)
(coordinators), Hans Paijmans (ILK, Tilburg), Steven Gillis (CNTS,
Antwerp), and Marc Swerts (CNTS, Antwerp, and IPO, Eindhoven).

The project aims at investigating the generation of prosodic structure
for a text-to-speech synthesis system. Accurate prosody is one of the
most crucial developments needed to get speech synthesis at a level of
pleasant fluency. Within the project, prosody generation is considered
a natural language processing problem rather than a speech technology
problem: it is defined as the prediction of prosodic markers (accents and
breaks) by means of automatic analyses of written texts, and is less
concerned about how these markers need to be interpreted in terms of
appropriate melodic, durational and other prosodic features when the
text is converted into speech.

The central question is whether prosody generation can be accurately
performed by (a) robust automatic analysis of texts using techniques
from information retrieval and natural language processing, and (b)
advanced machine learning systems and meta-learning systems such as
combiners and boosting ensembles. The target language will be Dutch.


[1] Ph.D. position (four years)

Working in the ILK team, the Ph.D. student will be focusing on methods
for semi-automatic annotation of prosody in text, and on
evaluation. The semi-automatic annotation part builds forth on work on
the ILK Prosodical Annotator project developed by Bertjan Busser (ILK,
Tilburg), and involves a user interface in which the human annotator
is assisted by a machine learning module making educated guesses. The
evaluation part deals with developing methods (including (perceptual)
tests with real users) for estimating the quality of prosody, both
within the annotated corpus and in the prosody system developed within
the complete project.  The project works towards a Ph.D. thesis
finished in the fourth year.

The ideal candidate has a graduate/Masters level in (computational)
linguistics or a related area, preferrably with a background in speech
technology or system evaluation, and should have basic programming
skills. Knowledge of Dutch is an advantage. Currently, a full-time
Ph.D. position has a gross monthly salary of NLG 2398 (approx. 1100
euros) in the first year, increasing to NLG 4077 (approx. 1850 euros)
in the fourth year. Before January 2001 first-year salaries of
Ph.D.s are expected to be raised by 25% (6% in the fourth year).

Target starting date:     January 1, 2001.
Deadline for application: October 15, 2000.


[2] Postdoc position (three years)

The ILK postdoc will be working on testing the general applicability,
on implementation and on integration of methods for automatic text
analysis (both from information retrieval and extraction and from
natural language processing) into a working prosody generation
system. In the first year, the accent will be on gathering a
(semi-automatically) annotated and (automatically) analysed corpus of
Dutch prosody, a subcorpus of the 120-million word ILK corpus of
annotated Dutch newspaper text joined with a similar corpus for
Flemish. Later on, the postdoc will be focusing on integrating the
Tilburg and Antwerp subprojects and evaluating the prosody generation
system (with the ILK Ph.D.).

Candidates should have a Ph.D. and experience in a related area
(computer science, (computational) linguistics, speech technology),
and a proven track of scientific publications. Programming skills
(Perl or C) are required. Knowledge of Dutch is an advantage. Salary
depends on experience, with a minimum gross monthly salary of
approx. NLG 5000 (approx. 2270 euros).

Target starting date: flexible from January 1, 2001.
Deadline for application: October 15, 2000.


For more information on both positions, contact Antal van den Bosch
via email (Antal.vdnBosch at kub.nl) or phone (+31.13.4663117).
Applications for both positions should include cover letter, CV, and
names of two references, and should be sent before the application
deadline of October 15, 2000 by regular mail to

  C. de Graaf
  director, Faculty of Arts
  Tilburg University
  P.O. Box 90153
  NL-5000 LE Tilburg
  The Netherlands

In your letter, either make reference to vacancy code VNC-AIO for the
Ph.D. position, or to VNC-PD for the postdoc position.


---------------------------------------------------------------------
For more background information on the research groups participating
in the project, visit

 ILK webpage:  http://ilk.kub.nl/
 CNTS webpage: http://cnts.uia.ac.be/cnts/

Please note that the ILK group has a third job opening: candidates are
sought for a full-time Ph.D. position on a joint Tilburg-Eindhoven
project entitled "Learning to communicate: Machine learning of
dialogue strategies". Information on this job opening can be found at

  http://ilk.kub.nl/jobs/ilk2000-c.html

---------------------------------------------------------------------