[Elsnet-list] PhD position in Entity Disambiguation in the Language Speech and Interfaces Group, University of Trento

Massimo Poesio massimo.poesio at unitn.it
Fri Apr 9 13:37:49 CEST 2010


PHD POSITION IN ENTITY DISAMBIGUATION IN THE LANGUAGE SPEECH AND
INTERFACES GROUP, UNIVERSITY OF TRENTO

A PhD studentship in statistical models for entity disambiguation will
be available in the 3-year PhD program offered by the University of
Trento's ICT Doctoral School

          http://ict.unitn.it

The ICT PhD program (start date: November 2010) is taught in English
by an international faculty. The PhD candidate will join the Language,
Speech and Interfaces group, an interdisciplinary group of researchers
studying spoken interaction, content mining and retrieval, and
multimodal interfaces:

http://www.disi.unitn.it/research/research_programs/lsi

LSI is part of the larger network of research groups focusing on Human
Language Technology and related topics in the Trento region, that is
quickly becoming one of the areas with the highest concentration of
NLP researchers in Europe.

* Project Outline *

Entity Disambiguation is the task of determining which mentions of
entities (persons, organizations, locations) refer to the same object,
in the same document or across collection of documents. This task is a
growing area of research as a supporting technology both for
entity-based document search (as in http://pipl.com/) and for content
extraction (as in http://www.opencalais.com/) and was the subject of a
recent Johns Hopkins CLSP Workshop
(http://www.clsp.jhu.edu/ws07/groups/elerfed/) and of a regular series
of workshops.

Themes of particular interest for this project are disambiguation of
non-standard entity types such as product names and temporal
expressions, particularly in digital libraries; and the use of
relational information and topic models such as Latent Dirichlet
Allocation.

* Application Information *

The successful candidate will have a strong computational background,
including familiarity with machine learning and/or statistical
methods. Familiarity with natural language processing would also be
highly desirable.

The official call of the Information and Communication Technology
Doctoral School, and application details, are available at the page:

http://ict.unitn.it/

We strongly encourage a preliminary expression of interest in the
project. Please contact Massimo Poesio (massimo.poesio at unitn.it), attaching
a CV in pdf or txt format, or a link to an online CV.


More information about the Elsnet-list mailing list