Machine Learning Applied to Argumentative Reasoning

The Inria center at Université Côte d'Azur includes 42 research teams and 9 support services. The center’s staff (about 500 people) is made up of scientists of different nationalities, engineers, technicians and administrative staff. The teams are mainly located on the university campuses of Sophia Antipolis and Nice as well as Montpellier, in close collaboration with research and higher education laboratories and establishments (Université Côte d'Azur, CNRS, INRAE, INSERM ...), but also with the regional economic players.

With a presence in the fields of computational neuroscience and biology, data science and modeling, software engineering and certification, as well as collaborative robotics, the Inria Centre at Université Côte d'Azur  is a major player in terms of scientific excellence through its results and collaborations at both European and international levels.

This research topic may potentially lead to a PhD thesis, depending on the candidate's profile.

Context:
Argumentation systems are powerful theories and tools for representing and managing contradictory information in an explainable way. They can be highly valuable, for example, in understanding and analysing political debates, or providing decision support to doctors when generating and evaluating medical diagnoses, or assisting judges in evaluating different legal defences in a court of law.

To reason automatically about this type of problem and identify acceptable arguments, various mathematical functions, known as semantics, have been defined in the literature (which can be considered as algorithms). You will find following a reference presenting these argumentative semantics:

• Baroni, Pietro, Martin Caminada, and Massimiliano Giacomin. “An introduction to argumentation semantics.” The knowledge engineering review 26.4 (2011): 365-410.

However, calculating these acceptable arguments, can take a significant amount of time for large argumentation graphs. As a result, for several years now, a solver competition have been established to compute argument acceptability efficiently; see ICCMA (International Competition on Computational Models of Argumentation). These solvers are mainly SAT solvers. The idea is to explore the potential of machine learning (ML) models in achieving the same performance as symbolic approches on this computationally hard task.

Here are some bibliographic references on existing work on this topic:

• Craandijk, Dennis, and Floris Bex. “Deep learning for abstract argumentation semantics.” arXiv preprint arXiv:2007.07629 (2020).
• Cibier, Paul, and Jean-Guy Mailly. “Graph Convolutional Networks and Graph Attention Networks for Approximating Arguments Acceptability–Technical Report.” arXiv preprint arXiv:2404.18672 (2024).
• Malmqvist, Lars, Tangming Yuan, and Peter Nightingale. “Approximating problems in abstract argumentation with graph convolutional networks.” Artificial Intelligence 336 (2024): 104209.

Supervisors:
You will be supervised by Victor David (INRIA researcher at Sophia Antipolis) and Serena Villata (CNRS Director of research at Sophia Antipolis).

Objective:
You will study different existing machine learning (ML) approaches that efficiently compute argument acceptability, with the goal of developing a new model competitive with the state of the art.

• 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
• Contribution to mutual insurance (subject to conditions)

Traineeship grant depending on attendance hours.