The newly established research group on
“Computational Models of Misunderstanding for Complex Instructional Text”
invites applications for two PhD positions or one postdoc and one PhD
student. The posts are funded by the German Research Foundation
(DFG—Deutsche Forschungs- gemeinschaft) through the DFG Emmy Noether
Programme, which provides funding for independent junior research
groups (similar to an ERC Starting Grant / NSF CAREER Award). The group
will be headed by Michael Roth and located at the Institute for Natural
Language Processing at the University of Stuttgart in Germany.
The project will be concerned with the systematic analysis and
computational modelling of text passages that can lead to
misunderstandings. A substantial amount of previous work has studied
misunderstandings in dialogue, but suitable resources for written language
are scarce because misunderstandings cannot be observed directly from a
text. Since readers and writers typically do not interact, it is important
for authors to ensure that texts leave no room for misinterpretation.
Otherwise, for example, medical instructions may be followed incorrectly,
and route directions may not guide navigators to their desired
destination. The goal of this project is to create the resources and
methods necessary to prevent such outcomes.
The announced positions will be part of a collaborative research effort,
which includes local contributors as well as collaborations with external
partners at the University of Edinburgh and Pompeu Fabra University in
Barcelona. One of the available positions will focus on the linguistic
analysis and modelling of potential sources of misunderstanding, as well
as on extrinsic evaluations within existing semantic analysis tasks (e.g.
SRL). The focus of the other position will be on developing neural
end-to-end models and adaptations to downstream applications (e.g. MT).
Both positions will be open from March 2019 and available for three years
(with the possibility of extensions). The salary is according to salary
group TV-L E13, 75% for PhD students (approx. 3,000 EUR gross per month),
up to 100% for postdocs (approx. EUR 4,000).
University of Stuttgart
Successful applicants will have a background in linguistics, machine
learning, and/or computational linguistics, with a particular interest in
semantics and pragmatics. Programming skills and the ability to work in a
group are taken for granted.
The candidate should be able to work and communicate in English (no proficiency of German is required).
About University of Stuttgart
The University of Stuttgart is a research-intensive university with a predominantly engineering and natural science orientation and its special profile includes linking these subject areas with humanities and social sciences. Its excellent position is reflected in both its projects, sponsored by the excellence initiative of the Federal Government and the States, the excellence cluster „Simulation Technology“ and the graduate school „Advanced Manufacturing Engineering“. Furthermore, the University of Stuttgart is currently supported with four special research areas by Deutsche Forschungsgemeinschaft (DFG) (German Research Foundation), a trans-regional special research field as well as four transfer areas coordinating university. The ranking of Deutsche Forschungsgemeinschaft (German Research Foundation) and Centrum für Hochschulentwicklung CHE (Centre for Higher Education Development) regularly shows the University of Stuttgart to be particularly strong in the field of research. And in terms of third party fun