Description du projet
Prédire automatiquement ce qui est vrai et ce qui est faux
L’extension de la portée d’Internet et des médias, ainsi que les événements percutants récents, ont rendu nécessaire la vérification rapide et facile des faits en ligne. Malheureusement, des facteurs de complication tels que les quantités massives de données signifient que même la vérification des faits basée sur l’apprentissage automatique rencontre des difficultés pour réaliser efficacement cette tâche ou pour expliquer son processus de vérification des faits. C’est là qu’intervient le projet ExplainYourself, financé par le Conseil européen de la recherche, qui favorisera la vérification des faits de manière explicable. Étant donné que les méthodes de vérification automatique des faits recourent souvent à des réseaux neuronaux profonds opaques, le projet proposera une vérification des faits explicable. Les approches actuelles ne sont pas en mesure de fournir des explications variées, destinées à des utilisateurs ayant différents besoins en matière d’information.
Objectif
ExplainYourself proposes to study explainable automatic fact checking, the task of automatically predicting the veracity of textual claims using machine learning (ML) methods, while also producing explanations about how the model arrived at the prediction. Automatic fact checking methods often use opaque deep neural network models, whose inner workings cannot easily be explained. Especially for complex tasks such as automatic fact checking, this hinders greater adoption, as it is unclear to users when the models' predictions can be trusted. Existing explainable ML methods partly overcome this by reducing the task of explanation generation to highlighting the right rationale. While a good first step, this does not fully explain how a ML model arrived at a prediction. For knowledge intensive natural language understanding (NLU) tasks such as fact checking, a ML model needs to learn complex relationships between the claim, multiple evidence documents, and common sense knowledge in addition to retrieving the right evidence. There is currently no explainability method that aims to illuminate this highly complex process. In addition, existing approaches are unable to produce diverse explanations, geared towards users with different information needs.
ExplainYourself radically departs from existing work in proposing methods for explainable fact checking that more accurately reflect how fact checking models make decisions, and are useful to diverse groups of end users. It is expected that these innovations will apply to explanation generation for other knowledge-intensive NLU tasks, such as question answering or entity linking. To achieve this, ExplainYourself builds on my pioneering work on explainable fact checking as well as my interdisciplinary expertise.
Champ scientifique
Mots‑clés
Programme(s)
- HORIZON.1.1 - European Research Council (ERC) Main Programme
Thème(s)
Régime de financement
ERC - Support for frontier research (ERC)Institution d’accueil
1165 Kobenhavn
Danemark