Université de Sherbrooke

About: Université de Sherbrooke is a education organization based out in Sherbrooke, Quebec, Canada. It is known for research contribution in the topics: Population & Receptor. The organization has 14922 authors who have published 28783 publications receiving 792511 citations. The organization is also known as: Universite de Sherbrooke & Sherbrooke University.

Multimodal Language Analysis with Recurrent Multistage Fusion

Abstract: Computational modeling of human multimodal language is an emerging research area in natural language processing spanning the language, visual and acoustic modalities. Comprehending multimodal language requires modeling not only the interactions within each modality (intra-modal interactions) but more importantly the interactions between modalities (cross-modal interactions). In this paper, we propose the Recurrent Multistage Fusion Network (RMFN) which decomposes the fusion problem into multiple stages, each of them focused on a subset of multimodal signals for specialized, effective fusion. Cross-modal interactions are modeled using this multistage fusion approach which builds upon intermediate representations of previous stages. Temporal and intra-modal interactions are modeled by integrating our proposed fusion approach with a system of recurrent neural networks. The RMFN displays state-of-the-art performance in modeling human multimodal language across three public datasets relating to multimodal sentiment analysis, emotion recognition, and speaker traits recognition. We provide visualizations to show that each stage of fusion focuses on a different subset of multimodal signals, learning increasingly discriminative multimodal representations.

A systems‐based dynamic knowledge transfer capacity model

Abstract: Purpose – The purpose of this paper is twofold: to understand how recent developments in systems thinking and social construction can influence understanding of knowledge transfer (KT); and to propose a new systems‐based knowledge transfer model.Design/methodology/approach – The paper is a review of the literature on knowledge transfer, systems thinking and social construction leads to the proposal of a new KT paradigm.Findings – The Dynamic Knowledge Transfer Capacity model (DKTC) found in this paper identifies the components required for social systems to generate, disseminate and use new knowledge to meet their needs. The model includes pre‐existing conditions, (need and prior knowledge) and four categories of capacities (generative, disseminative, absorptive and adaptive/responsive) that social systems must possess for KT to take place.Research limitations/implications – The paper shows that the DKTC model is particularly well suited to analyzing complex systems with multiple stakeholders as opposed t...