Descripción del proyecto
Predecir automáticamente qué es un hecho y qué no lo es
El mayor alcance de internet y los medios de comunicación unido a los impactantes acontecimientos recientes han hecho necesaria una verificación rápida y sencilla de los hechos en línea. Por desgracia, factores complicados como la enorme cantidad de datos hacen que incluso la comprobación de hechos basada en el aprendizaje automático tenga dificultades para cumplir eficazmente esta tarea o para explicar mejor su proceso de verificación de hechos. En el proyecto ExplainYourself, financiado por el Consejo Europeo de Investigación, se proporcionará una comprobación de hechos explicable. Dado que los métodos automáticos de comprobación de hechos suelen utilizar redes neuronales profundas opacas, el proyecto proporcionará una comprobación de hechos explicable. Los enfoques existentes son incapaces de producir explicaciones diversas, orientadas a usuarios con diferentes necesidades de información.
Objetivo
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.
Ámbito científico
Palabras clave
Programa(s)
- HORIZON.1.1 - European Research Council (ERC) Main Programme
Régimen de financiación
ERC - Support for frontier research (ERC)Institución de acogida
1165 Kobenhavn
Dinamarca