Search

The article emphasizes the critical importance of language generation today, particularly focusing on three key aspects: Multitasking, Multilinguality, and Multimodality, which are pivotal for the Natural Language Generation community. It delves into the activities conducted within the Multi3Generation COST Action (CA18231) and discusses current trends and future perspectives in language generation.

The purpose of this article is to highlight the critical importance of language generation today. In particular, language generation is explored from the following three aspects: multi-modality, multilinguality, which play crucial role for NLG community. We present the activities conducted within the Multi3Generation COST Action (CA18231), as well as current trends and future perspectives for multitask, multilingual and multimodal language generation.

This paper proposes a new paradigm for control plane in Time Sensitive Networks (TSN). An SDN controller proactively instructs network elements on the reconfigurations to perform locally if some specific events occur (e.g., failures, performance degradations). Instructions are given in the form of Finite State Machines (FSMs), which store information related to the actions that each network element should execute to react against a specific event. Thus, if such event occurs, the SDN controller is by-passed reducing reaction (e.g., recovery) time. Such an approach is here implemented for recovery upon failures in TSN. Experiments of failure recovery are carried out and measurements are presented comparing the FSM-based solution with a fully-centralized reactive restoration. Moreover, the proposed approach is compared through simulations against Frame Replication and Elimination for Reliability. Results will show how proactive FSM manipulation can strongly reduce recovery time in SDN-based TSN networks without overloading the network with frame replicas.

In this work, we present and analyze methods and mechanisms for interconnecting a network slice control and management system of the mobile network, with an IEEE Time-Sensitive Network (TSN) control plane. IEEE TSN is gaining momentum as a key technology that is able to provide network service guarantees for Ethernet-based communications. Although Ultra-Reliable Low-Latency Communications (URLLC) have been thoroughly investigated in 5G, incorporating TSN technologies in the Transport Network is expected to unleash the potential of end-to-end deterministic communications, especially in industrial environments and time-critical applications like factory automation.We elaborate on the concepts of a TSN-aware Xhaul network, present a novel architecture, and describe a set of amendments required in order to enable network slicing. With the devised approach, a slice-aware TSN-enabled transport network can be controlled and managed in an end-to-end orchestrated way. Implementation experience and evaluation results are reported using TSN-enabled prototype devices, OpenAirInterface (OAI), and JOX slice orchestrator.

Research into session-based recommendation systems (SBSR) has attracted a lot of attention, but each study focuses on a specific class of methods. This work examines and evaluates a large range of methods, from simpler statistical co-occurrence methods to embeddings and SotA deep learning methods. This paper analyzes theoretical and practical issues in developing and evaluating methods for SBSR in e-commerce applications, where user profiles and purchase data do not exist. The major tasks of SBRS are reviewed and studied, namely: prediction of next-item, next-basket and purchase intent. For physical retail shopping where no information about the current session exists, we treat the previous baskets purchased by the user as previous sessions drawn from a loyalty system. Mobile application scenarios such as push notifications and calling tune recommendations are also presented. Recommender models using graphs, embeddings and deep learning methods are studied and evaluated in all SBRS tasks using different datasets. Our work contributes a number of very interesting findings. Among all tested models, LSTMs consistently outperform other methods of SBRS in all tasks. They can be applied directly because they do not need significant fine-tuning. Additionally, they naturally model the dynamic browsing that happens in e-commerce web applications. On the other hand, another important finding of our work is that graph-based methods can be a good compromise between effectiveness and efficiency. Another important conclusion is that a “temporal locality principle” holds, implying that more recent behavior is better suited for prediction. In order to evaluate these systems further in realistic environments, several session-based recommender methods were integrated into an e-shop and an A/B testing method was applied. The results of this A/B testing are in line with the experimental results, which represents another important contribution of this paper. Finally, important parameters such as efficiency, application of business rules, re-ranking issues, and the utilization of hybrid methods are also considered and tested, providing comprehensive useful insights into SBRS and facilitating the transferability of this research work to other domains and recommendation scenarios.

In recent years, the interest in recommendation systems (RSs) has dramatically increased, as they have become main components of all online stores. The aims of an RS can be multifaceted, related not only to the increase in sales or the convenience of the customer, but may include the promotion of alternative environmentally friendly products or to strengthen policies and campaigns. In addition to accurate suggestions, important aspects of contemporary RSs are therefore to align with the particular marketing goals of the e-shop and with the stances of the targeted audience, ensuring user acceptance, satisfaction, high impact, and achieving sustained usage by customers. The current review focuses on RS related to retail shopping, highlighting recent research efforts towards enhanced e-shops and more efficient sustainable digital marketing and personalized promotion. The reported research was categorized by main approach, key methods, and specialized e-commerce problems addressed, while technological aspects were linked with marketing aspects. The increasing number of papers in the field showed that it has become particularly popular, following the explosive growth in e-commerce and mobile shopping. The problems addressed have expanded beyond the performance of the core algorithms to the business aspects of recommendation, considering user acceptance and impact maximization techniques. Technologies have also shifted from the improvement of classic filtering techniques to complex deep learning architectures, in order to deal with issues such as contextualization, sequence-based methods, and automatic feature extraction from unstructured data. The upcoming goals seem to be even more intelligent recommendations that more precisely adapt not only to users' explicit needs and hidden desires but also to their personality and sensitivity for more sustainable choices. [ABSTRACT FROM AUTHOR]

Time‐Sensitive Networks (TSN) aims at providing a solid underpinning for the support of application connectivity demands across a wide spectrum of use cases and operational environments, such as industrial automation and automotive networks. However, handling network updates in TSN entails additional challenges, stemming from the need to perform both flow rerouting and TSN schedule reconfiguration. To address this issue, we propose a software‐defined network (SDN)‐based approach for low‐overhead TSN network updates, exploiting segment routing over IPv6 (SRv6) for path control. To this end, we introduce the concept of TSN subgraphs in order to quickly reschedule the flows traversing the problematic area and propose a TSN‐aware routing heuristic to minimize the convergence time. We further describe the control plane implementation and its integration into Mininet, which empowers us to conduct a wide range of performance tests. Our evaluation results indicate that our approach yields faster recovery and reduces significantly the number of required reconfigurations upon failures, at the expense of a small SRv6 encoding/decoding overhead. [ABSTRACT FROM AUTHOR]

Research into session-based recommendation systems (SBSR) has attracted a lot of attention, but each study focuses on a specific class of methods. This work examines and evaluates a large range of methods, from simpler statistical co-occurrence methods to embeddings and SotA deep learning methods. This paper analyzes theoretical and practical issues in developing and evaluating methods for SBSR in e-commerce applications, where user profiles and purchase data do not exist. The major tasks of SBRS are reviewed and studied, namely: prediction of next-item, next-basket and purchase intent. For physical retail shopping where no information about the current session exists, we treat the previous baskets purchased by the user as previous sessions drawn from a loyalty system. Mobile application scenarios such as push notifications and calling tune recommendations are also presented. Recommender models using graphs, embeddings and deep learning methods are studied and evaluated in all SBRS tasks using different datasets. Our work contributes a number of very interesting findings. Among all tested models, LSTMs consistently outperform other methods of SBRS in all tasks. They can be applied directly because they do not need significant fine-tuning. Additionally, they naturally model the dynamic browsing that happens in e-commerce web applications. On the other hand, another important finding of our work is that graph-based methods can be a good compromise between effectiveness and efficiency. Another important conclusion is that a "temporal locality principle" holds, implying that more recent behavior is better suited for prediction. In order to evaluate these systems further in realistic environments, several session-based recommender methods were integrated into an e-shop and an A/B testing method was applied. The results of this A/B testing are in line with the experimental results, which represents another important contribution of this paper. Finally, important parameters such as efficiency, application of business rules, re-ranking issues, and the utilization of hybrid methods are also considered and tested, providing comprehensive useful insights into SBRS and facilitating the transferability of this research work to other domains and recommendation scenarios. [ABSTRACT FROM AUTHOR]

Ultra-dense networks (UDNs) are a natural deployment evolution for handling the tremendous traffic increase related to the emerging 5G services, especially in urban environments. However, the associated infrastructure cost may become prohibitive. The evolving paradigm of network slicing can tackle such a challenge while optimizing the network resource usage, enabling multi-tenancy and facilitating resource sharing and efficient service-oriented communications. Indeed, network slicing in UDN deployments can offer the desired degree of customization in not only vanilla radio access network (RAN) designs, but also in the case of disaggregated multi-service RANs. In this article, we devise a novel multi-service RAN environment, RAN runtime, capable of supporting slice orchestration procedures and enabling flexible customization of slices as per tenant needs. Each network slice can exploit a number of services, which can be either dedicated or shared between multiple slices over a common RAN. The novel architecture we present concentrates on the orchestration and management systems. It interacts with the RAN modules, through the RAN runtime, via a number of new interfaces enabling a customized dedicated orchestration logic for each slice. We present results for a disaggregated UDN deployment where the RAN runtime is used to support slice-based multi-service chain creation and chain placement, with an auto-scaling mechanism to increase the performance. [ABSTRACT FROM AUTHOR]

In this paper we address the support of wearable mHealth applications in LTE and future 5G networks following a holistic approach that spans across the elements of a mobile network. The communication requirements change from one application to another so we propose a measurement methodology to facilitate the selection of the user equipment to fulfil these requirements. We also discuss a new network architecture to support traffic prioritization, RAN programmability, low latency and group communications to over-the-top applications. Our proposal is validated using several realistic experimentation platforms and the results show that mHealth systems can benefit from our approach. [ABSTRACT FROM AUTHOR]

The upcoming 5G ecosystem is envisioned to build business-driven network slices to accommodate the different needs of divergent service types, applications, and services in support of vertical industries. In this article, we describe the network slicing concept by unveiling a novel network slicing architecture for integrated 5G communications. Further, we demonstrate its realization for the case of evolved LTE using state-of-the-art technologies. Finally, we elaborate on the LTE-specific requirements toward 5G, and point out existing challenges and open issues. [ABSTRACT FROM PUBLISHER]

This work focuses on the design, analysis and evaluation of Dynamic Weighted Round Robin (DWRR) algorithms that can guarantee CPU service shares in clusters of servers. Our motivation comes from the need to provision multiple server CPUs in cloud-based data center environments. Using stochastic control theory we show that a class of DWRR policies provide the service differentiation objectives, without requiring any knowledge about the arrival and the service process statistics. The member policies provide the data center administrator with trade-off options, so that the communication and computation overhead of the policy can be adjusted. We further evaluate the proposed policies via simulations, using both synthetic and real traces obtained from a medium scale mobile computing application. [ABSTRACT FROM PUBLISHER]

In this paper the classical and generalized numerical Rogers-Ramanujan continued fractions are extended to a polynomial continued fraction in one and two dimensions. Using the new continued fractions, the fundamental recurrence formulas and a fast algorithm, based on matrix formulations, are given for the computation of their transfer functions. The presented matrix formulations can provide a new perspective to the analysis and design of Ladder-continued fraction filters in one and two dimensions signal processing. The simplicity and efficiency of the presented algorithms are illustrated by step-by-step examples. [ABSTRACT FROM AUTHOR]