Post-Doc available in Paris with Dr. Justine Cassell and colleagues at
Inria/PRAIRIE Research Center for Interdisciplinary Research on
Artificial Intelligence.

TITLE: The role of rapport in human-conversational agent interaction:
Modeling conversation to improve task performance in human-agent
Interaction

CONTRACT TYPE : Fixed-term contract, renewable

CONTEXT: The objective of this project is to build embodied
conversational agents (also known as ECAs, or virtual humans, or
chatbots, or multimodal dialogue systems) that have the ability to
engage their users in both social and task talk, where the social talk
serves to improve task performance. In order to achieve this objective,
we model human-human conversation, and integrate the models into ECAs,
and then evaluate their performance.

Depending on the candidate's experience, she or he can be hired as
postdoc, or as "jeune chercheur", which is a more advanced position.

ASSIGNMENT
The post doc chosen for this project should have a broad range of skills
at the intersection of Cognitive Science and Computer Science. These
skills should include several of the following:
- The analysis and synthesis of conversational behavior, as the team
will be using human behavior as the basis for the implementation of a
conversational agent.
- The construction of a corpus of data, as the team will be gathering a
corpus of data on the social aspects of human-human conversation
within a particular domain, and annotating and analyzing those data.
- Development of computational models from the results of the data
analysis as well as based on relevant prior literature, deep
reinforcement learning, and other tools.
- The implementation of data-driven computational models of social
phenomena into a functioning ECA (Embodied Conversational Agent) using
machine learning approaches to dialogue systems, such as deep
reinforcement learning and LSTM (among others).
- Evaluating research, as the team will evaluate whether the new models
improve the performance of the ECA.

The candidate will be able to help decide the domain of the research, as
applications of the work can be as varied as virtual personal assistants
such as Alexa, Siri, and Google Now and intelligent tutoring systems.

For more information on the project, potential candidates should look at
the SARA (Socially-Aware Robot Assistant) website at
http://articulab.hcii.cs.cmu.edu/projects/sara/ and read some of the
publications associated with the project, here
http://articulab.hcii.cs.cmu.edu/publications/

MAIN ACTIVITIES
- Design and carry out experiments
- Analyze their results
- Implement modules in working socially-aware dialogue systems
- Write articles
- Present work in conferences

SKILLS AND COMPETENCES REQUIRED:

- Technical competencies: Solid competence in deep learning applied to
dialogue systems, competence in statistics, advanced competence in
programming in language such as Python and C++, and use of tools such
as Tensorflow and Pytorch.
- Languages: French, English
- Relational competences : ability to work in a team, and collaborate
with others from different disciplines and backgrounds. Ability to
manage other team members.

ADDITIONAL COMPETENCES:
Theoretical background in one or several of the following: cognitive
science, linguistics, conversational analysis, sociolinguistics, social
cognition, learning science.

INSTRUCTIONS TO APPLY

1) letter of motivation describing the subject of the doctoral thesis,
and how the candidate's past experience prepares him/her to work on
this topic
2) CV
3) Names and contact information for 2 or 3 people who can write letters
of recommendation (DO NOT ATTACH THE LETTERS - WE WILL REQUEST THE
LETTERS)

NO APPLICATIONS OR PARTS OF APPLICATIONS WILL BE ACCEPTED BY EMAIL. ALL
APPLICATIONS MUST BE SUBMITTED ONLINE ON THE INRIA WEBSITE.  For more
information and to apply, please see
https://recrutement.inria.fr/classic/offre/show/2904