PhD scholarship in ML at Aix-Marseille University

This PhD thesis aims at understanding how inter?‐individual
relationships are established,
managed and evolve during conversations. This work proposes to extend
the agent-based
notion of "interactional profile" (“leader”, “follower”…) to dyads
(the two people discussing) in order
to better characterize dynamic patterns such as convergence,
divergence, avoidance,...
This project uses data science on large spoken conversational data
sets in multiple languages
(English, French and Mandarin), as well as on task-focused real-life
conversation from call
centers, to identify the linguistic traces of interpersonal
relationships and their dynamics.
Tools from machine learning and natural language processing provides
methodological
knowledge for the scientific exploration of language through big data
sets, and allow a fine-grained
discovery and prediction of behaviors in novel data.
The PhD is fully funded during 3 years as part of the DOC2AMU European
H2020 COFUND
program, including personalized training, travel expenses, and
conferences attendance.
Preferred background are linguistics or computer science but anyone with strong
interest in natural language conversations and ability / desire to
develop computing skills
is welcomed to apply.
A condition for application is that they should not have spent more than 1 year
in France during the last 3 years. French language is not required.
Aix Marseille University, the largest French University, is ideally located
on the Mediterranean coast, and only 1h30 away from the Alps.
Official Deadline for Application: April, 10th (but contact us as soon
as possible)
More info and application:
http://doc2amu.univ-amu.fr/en/language-underpinnin...
Feel free to contact us for more information:
Laurent Prévot: laurent.prevot-AT-univ-amu.fr
www.lpl-aix.fr/person/prevot
Benoît Favre: benoit.favre-AT-univ-amu.fr
pageperso.lif.univ-mrs.fr/~benoit.favre/