2020-02904 - Post-Doctoral Research Visit F/M The role of rapport in human-conversational agent interaction: Modeling conversation to improve task performance in human-agent Interaction
Le descriptif de l’offre ci-dessous est en Anglais

Type de contrat : CDD

Contrat renouvelable : Oui

Niveau de diplôme exigé : Thèse ou équivalent

Autre diplôme apprécié : Ecole d'ingénieur

Fonction : Post-Doctorant

Niveau d'expérience souhaité : De 3 à 5 ans

Contexte et atouts du poste

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. 

Mission confiée

  • 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, using tools such as structural equation modeling 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/>

 

 

Principales activités

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

Compétences

Competences:

Competences Techniques: 
Solid competence in deep learning applied to dialogue systems, competence in statistics, avanced competence in programming in language such as Python and C++, and use of tools such as Tensorflow and Pytorch.

Langue: French, English

Competences relationnelles: ability to work in a team, and collaborate with others from different disciplines and backgrounds. Ability to manage other team members.

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

Avantages

  • Subsidized meals
  • Partial reimbursement of public transport costs
  • Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
  • Possibility of teleworking (after 6 months of employment) and flexible organization of working hours
  • Professional equipment available (videoconferencing, loan of computer equipment, etc.)
  • Social, cultural and sports events and activities
  • Access to vocational training