Searcharxiv⌕ Search

arXiv subjects

Florin Pop

Publications and source records attributed to Florin Pop.

36 records · Page 2Linked to original sources
arXiv2023

RoBERTweet: A BERT Language Model for Romanian Tweets

Developing natural language processing (NLP) systems for social media analysis remains an important topic in artificial intelligence research. This article introduces RoBERTweet, the first Transformer architecture trained on Romanian tweets. Our RoBERTweet comes in two versions, following the base and large architectures of BERT. The corpus used for pre-training the models represents a novelty for the Romanian NLP community and consists of all tweets collected from 2008 to 2022. Experiments show that RoBERTweet models outperform the previous general-domain Romanian and multilingual language models on three NLP tasks with tweet inputs: emotion detection, sexist language identification, and named entity recognition. We make our models and the newly created corpus of Romanian tweets freely available.

cs.CL↗
arXiv2022

TA-DA: Topic-Aware Domain Adaptation for Scientific Keyphrase Identification and Classification (Student Abstract)

Keyphrase identification and classification is a Natural Language Processing and Information Retrieval task that involves extracting relevant groups of words from a given text related to the main topic. In this work, we focus on extracting keyphrases from scientific documents. We introduce TA-DA, a Topic-Aware Domain Adaptation framework for keyphrase extraction that integrates Multi-Task Learning with Adversarial Training and Domain Adaptation. Our approach improves performance over baseline models by up to 5% in the exact match of the F1-score.

cs.CL↗
arXiv2012

A Simulation Model for Evaluating Distributed Systems Dependability

In this paper we present a new simulation model designed to evaluate the dependability in distributed systems. This model extends the MONARC simulation model with new capabilities for capturing reliability, safety, availability, security, and maintainability requirements. The model has been implemented as an extension of the multithreaded, process oriented simulator MONARC, which allows the realistic simulation of a wide-range of distributed system technologies, with respect to their specific components and characteristics. The extended simulation model includes the necessary components to inject various failure events, and provides the mechanisms to evaluate different strategies for replication, redundancy procedures, and security enforcement mechanisms, as well. The results obtained in simulation experiments presented in this paper probe that the use of discrete-event simulators, such as MONARC, in the design and development of distributed systems is appealing due to their efficiency and scalability.

cs.DC↗
arXiv2011

An Architectural Model for a Grid based Workflow Management Platform in Scientific Applications

With recent increasing computational and data requirements of scientific applications, the use of large clustered systems as well as distributed resources is inevitable. Although executing large applications in these environments brings increased performance, the automation of the process becomes more and more challenging. While the use of complex workflow management systems has been a viable solution for this automation process in business oriented environments, the open source engines available for scientific applications lack some functionalities or are too difficult to use for non-specialists. In this work we propose an architectural model for a grid based workflow management platform providing features like an intuitive way to describe workflows, efficient data handling mechanisms and flexible fault tolerance support. Our integrated solution introduces a workflow engine component based on ActiveBPEL extended with additional functionalities and a scheduling component providing efficient mapping between tasks and available resources.

cs.DC↗
arXiv2011

DistHash: A robust P2P DHT-based system for replicated objects

Over the Internet today, computing and communications environments are significantly more complex and chaotic than classical distributed systems, lacking any centralized organization or hierarchical control. There has been much interest in emerging Peer-to-Peer (P2P) network overlays because they provide a good substrate for creating large-scale data sharing, content distribution and application-level multicast applications. In this paper we present DistHash, a P2P overlay network designed to share large sets of replicated distributed objects in the context of large-scale highly dynamic infrastructures. We present original solutions to achieve optimal message routing in hop-count and throughput, provide an adequate consistency approach among replicas, as well as provide a fault-tolerant substrate.

cs.DC↗
arXiv2011

Towards an IO intensive Grid application instrumentation in MedioGRID

Obtaining high performance in IO intensive applications requires systems that support reliable fast transfer, data replication, and caching. In this paper we present an architecture designed for supporting IO intensive applications in MedioGRID, a system for real-time processing of satellite images, operating in a Grid environment. The solution ensures that applications which are processing geographical data have uniform access to data and is based on continuous monitoring of the data transfers using MonALISA and its extensions. The MedioGRID architecture is also built on Globus, Condor and PBS and based on this middleware we aim to extract information about the running systems. The results obtained in testing MedioGRID system for large data transfers show that monitoring system provides a very good view of system evolution.

cs.DC↗
arXiv2011

Intelligent strategies for DAG scheduling optimization in Grid environments

The paper presents a solution to the dynamic DAG scheduling problem in Grid environments. It presents a distributed, scalable, efficient and fault-tolerant algorithm for optimizing tasks assignment. The scheduler algorithm for tasks with dependencies uses a heuristic model to optimize the total cost of tasks execution. Also, a method based on genetic algorithms is proposed to optimize the procedure of resources assignment. The experiments used the MonALISA monitoring environment and its extensions. The results demonstrate very good behavior in comparison with other scheduling approaches for this kind of DAG scheduling algorithms.

cs.DC↗
arXiv2011

OpenPh - Numerical Physics Library

Numerical physics has gained a lot of importance in the last decade, its efficiency being motivated and sustained by the growth of computational power. This paper presents a concept that is to be developed in the next few years: OpenPh. OpenPh is a numerical physics library that makes use of the advantages of both open source software and MATLAB programming. Its aim is to deliver the instruments for providing numerical and graphical solutions for various physics problems. It has a modular structure, allowing the user to add new modules to the existing ones and to create its own modules according to its needs, being virtually unlimited extendable. The modules of OpenPh are implemented using MATLAB engine because it is the best solution used in engineering and science, providing a wide range of optimized methods to accomplish even the toughest jobs. Current version of OpenPh includes two modules, the first one providing tools for quantum physics and the second one for mechanics. The quantum physics module deals with the photoelectric effect, the radioactive decay of carbon-11, and the Schrödinger equation - particle in a box. The classical mechanics module includes the study of the uniform circular motion, the forced damped harmonic oscillations and the vibration of a fixed-fixed string.

cs.DL↗
arXiv2011

Clasificarea distribuita a mesajelor de e-mail

A basic component in Internet applications is the electronic mail and its various implications. The paper proposes a mechanism for automatically classifying emails and create dynamic groups that belong to these messages. Proposed mechanisms will be based on natural language processing techniques and will be designed to facilitate human-machine interaction in this direction.

cs.HC↗
arXiv2011

Resource CoAllocation for Scheduling Tasks with Dependencies, in Grid

Scheduling applications on wide-area distributed systems is useful for obtaining quick and reliable results in an efficient manner. Optimized scheduling algorithms are fundamentally important in order to achieve optimized resources utilization. The existing and potential applications include many fields of activity like satellite image processing and medicine. The paper proposes a scheduling algorithm for tasks with dependencies in Grid environments. CoAllocation represents a strategy that provides a schedule for task with dependencies, having as main purpose the efficiency of the schedule, in terms of load balancing and minimum time for the execution of the tasks.

cs.DC↗
arXiv2011

Advance Reservation of Resources for Task Execution in Grid Environments

The paper proposes a solution for the Grid scheduling problem, addressing in particular the requirement of high performance an efficient algorithm must fulfill. Advance Reservation engages a distributed, dynamic, fault-tolerant and efficient strategy which reserves resources for future task execution. The paper presents the main features of the strategy, the functioning mechanism the strategy is based on and the methods used for evaluating the algorithm.

cs.DC↗
arXiv2009

Critical Analysis of Middleware Architectures for Large Scale Distributed Systems

Distributed computing is increasingly being viewed as the next phase of Large Scale Distributed Systems (LSDSs). However, the vision of large scale resource sharing is not yet a reality in many areas - Grid computing is an evolving area of computing, where standards and technology are still being developed to enable this new paradigm. Hence, in this paper we analyze the current development of middleware tools for LSDS, from multiple perspectives: architecture, applications and market research. For each perspective we are interested in relevant technologies used in undergoing projects, existing products or services and useful design issues. In the end, based on this approach, we draw some conclusions regarding the future research directions in this area.

cs.DC↗
arXiv2009

Robust Failure Detection Architecture for Large Scale Distributed Systems

Failure detection is a fundamental building block for ensuring fault tolerance in large scale distributed systems. There are lots of approaches and implementations in failure detectors. Providing flexible failure detection in off-the-shelf distributed systems is difficult. In this paper we present an innovative solution to this problem. Our approach is based on adaptive, decentralized failure detectors, capable of working asynchronous and independent on the application flow. The proposed solution considers an architecture for the failure detectors, based on clustering, the use of a gossip-based algorithm for detection at local level and the use of a hierarchical structure among clusters of detectors along which traffic is channeled. The solution can scale to a large number of nodes, considers the QoS requirements of both applications and resources, and includes fault tolerance and system orchestration mechanisms, added in order to asses the reliability and availability of distributed systems.

cs.DC↗
arXiv2009

Towards a Centralized Scheduling Framework for Communication Flows in Distributed Systems

The overall performance of a distributed system is highly dependent on the communication efficiency of the system. Although network resources (links, bandwidth) are becoming increasingly more available, the communication performance of data transfers involving large volumes of data does not necessarily improve at the same rate. This is due to the inefficient usage of the available network resources. A solution to this problem consists of data transfer scheduling techniques, which manage and allocate the network resources in an efficient manner. In this paper we present several online and offline data transfer optimization techniques, in the context of a centrally controlled distributed system.

cs.DS↗
arXiv2008

Optimization of Decentralized Scheduling for Physic Applications in Grid Environments

This paper presents a scheduling framework that is configured for, and used in physic systems. Our work addresses the problem of scheduling various computationally intensive and data intensive applications that are required for extracting information from satellite images. The proposed solution allows mapping of image processing applications onto available resources. The scheduling is done at the level of groups of concurrent applications. It demonstrates a very good behavior for scheduling and executing groups of applications, while also achieving a near-optimal utilization of the resources.

cs.DC↗
arXiv2004

Hochschild Cohomology of Factors with Property $Γ$

The main result of this paper is that the k^{\rm th} continuous Hochschild cohomology groups H^k(\cl M,\cl M) and H^k(\cl M,B(H)) of a von Neumann factor ${\cl M}\subseteq B(H) of type {\rm II}_1 with property Gamma are zero for all positive integers k. The method of proof involves the construction of hyperfinite subfactors with special properties and a new inequality of Grothendieck type for multilinear maps. We prove joint continuity in the $\|\cdot\|_2$-norm of separately ultraweakly continuous multilinear maps, and combine these results to reduce to the case of completely bounded cohomology which is already solved.

math.OA↗