The task of modeling claim severities is addressed when data not consistent with the classical regression assumptions. This framework common in several lines business within insurance and reinsurance, where catastrophic losses or heterogeneous sub-populations result difficult to model. Their correct analysis required for pricing products, some most prevalent recent specifications this direction...

This paper introduces a neural network capable of dynamically adapting its architecture to realize time variant non-linear input-output maps. This network has its roots in the mixture of experts framework but uses a localized model for the gating network. Modules or experts are grown or pruned depending on the complexity of the modeling problem. The structural adaptation procedure addresses the...

Frame identification, which is finding the exact evoked frame for a target word in given sentence, fundamental and crucial prerequisite semantic parsing. It generally seen as classification task words, whose contextual representations are usually obtained using neural network like BERT an encoder, enriched with joint learning model or knowledge of FrameNet. However, distinction at fine-grained ...