Université Côte d’Azur, CNRS, Inria, I3S, France
Title: Integrating machine predictions and argumentative explanations for explanatory argument-based dialogue
-- Context -- Argument(ation) mining, the new and rapidly growing area of Natural Language Processing (NLP) and computational models of argument, aims at the automatic recognition of argument structures in large resources of natural language texts. In the clinical domain, argument mining has been proved to be beneficial in providing us with methods to automatically detect in text the argumentative structures that are at the basis of Evidence-Based Medicine (EBM).
While neural networks for medical diagnosis have become exceedingly accurate in many areas, their ability to explain how they achieve their outcome remains problematic. The goal of this project is to enable clinical prediction systems to engage in argument-based explanatory dialogues with humans, whereby clinicians will be able to argue with the system in natural language. In particular, we focus on elaborating argumentative explanations to diagnosis predictions, so that to support clinicians to make informative decisions.
The postdoc positions is funded by the CHIST-ERA ANTIDOTE project.
-- Keywords -- Evidence-based decision making in medicine, argument-based explanation, explanatory natural language dialogues
-- Research fields -- Artificial Intelligence, Natural Language Processing, Machine Learning
-- Research group -- WIMMICS (http://wimmics.inria.fr/ <http://wimmics.inria.fr/>) is a research team of Université Côte d’Azur (UCA), Inria, CNRS. The research fields of the team are graph-oriented knowledge representation, reasoning and operationalization to model and support actors, actions and interactions in web-based epistemic communities.
-- Candidate profile -- The candidate must hold a PhD in Computer Science, with a specialization in Artificial Intelligence or Natural Language Processing. The candidate must have strong skills on Machine Learning frameworks and good English skills in writing and communication.
-- Application process -- Apply by sending an email directly to the supervisors (Elena Cabrio <elena.cabrio at univ-cotedazur.fr <mailto:elena.cabrio at univ-cotedazur.fr>> and Serena Villata <serena.villata at univ-cotedazur.fr <mailto:serena.villata at univ-cotedazur.fr>>).
Deadline for applications: *** March 30th, 2022 ***
The application must include: - Curriculum vitŠ. - Motivation Letter. - At least one letter of recommendation.
-------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 3645 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20220308/b1a566d7/attachment.txt>