Search

Building a computer system, which can automatically answer questions in the human language, speech or text, is a long-standing goal of the Artificial Intelligence (AI) field. Question analysis, the task of extracting important information from the input question, is the first and crucial step towards a question answering system. In this paper, we focus on the task of Vietnamese question analysis in the education domain. Our goal is to extract important information expressed by named entities in an input question, such as university names, campus names, major names, and teacher names. We present several extraction models that utilize the advantages of both traditional statistical methods with handcrafted features and more recent advanced deep neural networks with automatically learned features. Our best model achieves 88.11% in the F1 score on a corpus consisting of 3,600 Vietnamese questions collected from the fan page of the International School, Vietnam National University, Hanoi.

Despite continuous advances in studying human diseases and drug screening methodology, only a small fraction of drug candidates achieve approval for clinical use due to the lack of efficacy and/or adverse effects. A major challenge in studying human diseases and in identifying drug candidates that target these diseases, is the lack of an effective model that captures different aspects of human physiology. Studies are still heavily reliant on monolayer cell cultures or on animal models, neither of which can fully recapitulate the human body and its disease stages. Microphysiological systems/organs-on-a-chip (MPS/OOC) are designed to bridge the gap between monolayer cell culture and animal models. This body of research aims to develop novel MPS/OOC supported by a true living human vasculature to mimic human organ functions, model human diseases, and utilize these platforms to advance drug discovery and development.

National audience; Nous étudions l’impact du choix de la méthode de partitionnement sur une nouvelle classe de modèle graphique probabiliste, la forêt d’arbres latents. L’apprentissage de ce modèle repose sur le partitionnement itératif de variables observées et latentes. Le contexte d’étude est une utilisation en bioinformatique.