Many NLP tasks can be regarded as a selection problem from set of options, such classification tasks, multi-choice question answering, etc. Textual entailment (TE) has been shown the state-of-the-art (SOTA) approach to dealing with those problems. TE treats input texts premises (P), options hypotheses (H), then handles by modeling (P, H) pairwise. Two limitations: first, pairwise is unaware oth...

Nous présentons une réalisation purement fonctionnelle et paresseuse de la technique du mode inverse de différentiation algorithmique. Cette technique, qui permet de calculer de manière précise et efficace les dérivées des expressions numériques dans un programme, est devenue indispensable dans plusieurs branches de programmation scientifique. Le mode inverse ou adjoint demande souvent l’usage ...

Data warehouses collect and maintain large amounts of data from several distributed and heterogeneous data sources. Because of security reasons, operational requirements, and technical feasibility it is often impossible for data warehouses to access the data sources directly. Instead data warehouses have to replicate legacy information as detail data in order to be able to maintain their summar...