University of Avignon

About: University of Avignon is a education organization based out in Avignon, Provence-Alpes-Côte-d'Azur, France. It is known for research contribution in the topics: Population & Speaker recognition. The organization has 1526 authors who have published 3766 publications receiving 88928 citations.

INEX Tweet Contextualization task

Abstract: A full summary report on the four-year long Tweet Contextualization task.A detail on evaluation metrics and framework we developed for tweet contextualization evaluation.A deep analysis of what the participants suggested in their approaches by categorizing the various methods.A description of the data made available to the community. Microblogging platforms such as Twitter are increasingly used for on-line client and market analysis. This motivated the proposal of a new track at CLEF INEX lab of Tweet Contextualization. The objective of this task was to help a user to understand a tweet by providing him with a short explanatory summary (500 words). This summary should be built automatically using resources like Wikipedia and generated by extracting relevant passages and aggregating them into a coherent summary.Running for four years, results show that the best systems combine NLP techniques with more traditional methods. More precisely the best performing systems combine passage retrieval, sentence segmentation and scoring, named entity recognition, text part-of-speech (POS) analysis, anaphora detection, diversity content measure as well as sentence reordering.This paper provides a full summary report on the four-year long task. While yearly overviews focused on system results, in this paper we provide a detailed report on the approaches proposed by the participants and which can be considered as the state of the art for this task. As an important result from the 4 years competition, we also describe the open access resources that have been built and collected. The evaluation measures for automatic summarization designed in DUC or MUC were not appropriate to evaluate tweet contextualization, we explain why and depict in detailed the LogSim measure used to evaluate informativeness of produced contexts or summaries. Finally, we also mention the lessons we learned and that it is worth considering when designing a task.

Fluid flow phenomena in a single phase coreless induction furnace

Abstract: New measurement techniques for local velocity, magnetic field, and current density have been applied to the study of electromagnetic and hydrodynamic phenomena in a coreless induction furnace containing an aluminum alloy. The action of electromagnetic shields on the intensity and the structure of the liquid metal flow is reported. It is shown that the direction of the fluid flow and the number and sizes of the recirculating cells may be significantly modified; the electromagnetic stirring may also be practically canceled. The influence of the dimensions of the screens on the structure of the liquid metal flow is examined. Finally, the modification of the fluid flow phenomena is explained by the evolution of the electromagnetic force patterns.

A first look into the carbon footprint of federated learning

Abstract: Despite impressive results, deep learning-based technologies also raise severe privacy and environmental concerns induced by the training procedure often conducted in data centers. In response, alternatives to centralized training such as Federated Learning (FL) have emerged. Perhaps unexpectedly, FL in particular is starting to be deployed at a global scale by companies that must adhere to new legal demands and policies originating from governments and the civil society for privacy protection. However, the potential environmental impact related to FL remains unclear and unexplored. This paper offers the first-ever systematic study of the carbon footprint of FL. First, we propose a rigorous model to quantify the carbon footprint, hence facilitating the investigation of the relationship between FL design and carbon emissions. Then, we compare the carbon footprint of FL to traditional centralized learning. We also formalize an early-stage FL optimization problem enabling the community to consider the importance of optimizing the rate of CO2 emissions jointly to the accuracy of neural networks. Finally, we highlight and connect the reported results to the future challenges and trends in FL to reduce its environmental impact, including algorithms efficiency, hardware capabilities, and stronger industry transparency.