Abstract. Query-by-example and query-by-keyword both suffer from the problem of "aliasing," meaning that example-images and keywords potentially have variable interpretat...
Hierarchical Incremental Class Learning (HICL) is a new task decomposition method that addresses the pattern classification problem. HICL is proven to be a good classifier but clos...
—In this paper we describe our approach whose objective is to apply MOCOCO concepts to e-learning. After a short presentation of MOCOCO (Mobility, COoperation, Contextua-lisation...
Abstract. In multi-instance learning, each example is described by a bag of instances instead of a single feature vector. In this paper, we revisit the idea of performing multi-ins...
This paper introduces the concepts of asking point and expected answer type as variations of the question focus. They are of particular importance for QA over semistructured data,...
Alexander Mikhailian, Tiphaine Dalmas, Rani Pinchu...