Search

In recent years, the field of Natural Language Generation (NLG) has been boosted by the recent advances in deep learning technologies. Nonetheless, these new data-intensive methods introduce language-dependent disparities in NLG as the main training data sets are in English. Also, most neural NLG systems use decoder-only (causal) transformer language models, which work well for English, but were not designed with other languages in mind. In this work we depart from the hypothesis that they may introduce generation bias in target languages with less rigid word ordering, subject omission, or different attachment preferences for relative clauses, so that for these target languages other language generation strategies may be more desirable. This paper first compares causal and non-causal language modeling for English and Spanish, two languages with different grammatical structures and over 1.5 billion and 0.5 billion speakers, respectively. For this purpose, we define a novel metric of average causal and non-causal context-conditioned entropy of the grammatical category distribution for both languages as an information-theoretic a priori approach. The evaluation of natural text sources (such as training data) in both languages reveals lower average non-causal conditional entropy in Spanish and lower causal conditional entropy in English. According to this experiment, Spanish is more predictable than English given a non-causal context. Then, by applying a conditional relative entropy metric to text generation experiments, we obtain as insights that the best performance is respectively achieved with causal NLG in English, and with non-causal NLG in Spanish. These insights support further research in NLG in Spanish using bidirectional transformer language models.

Mobile core networks handle critical control functions for delivering services in modern cellular networks. Traditional point-to-point architectures, where network functions are directly connected through standardized interfaces, are being substituted by service-based architectures (SBAs), where core functionalities are finer-grained microservices decoupled from the underlying infrastructure. In this way, network functions and services can be distributed, with scaling and fail-over mechanisms, and can be dynamically deployed, updated, or removed to support slicing. A myriad of network functions can be deployed or removed according to traffic flows, thereby increasing the complexity of connection management. In this context, 3GPP Release 16 defines the service communication proxy (SCP) as a unified communication interface for a set of network functions. In this paper, we propose a novel software-defined networking (SDN)-based solution with the same role for a service mesh architecture where network functions can be deployed anywhere in the infrastructure. We demonstrated its efficiency in comparison with alternative architectures.

Drones may be more advantageous than fixed cameras for quality control applications in industrial facilities, since they can be redeployed dynamically and adjusted to production planning. The practical scenario that has motivated this paper, image acquisition with drones in a car manufacturing plant, requires drone positioning accuracy in the order of 5 cm. During repetitive manufacturing processes, it is assumed that quality control imaging drones will follow highly deterministic periodic paths, stop at predefined points to take images and send them to image recognition servers. Therefore, by relying on prior knowledge about production chain schedules, it is possible to optimize the positioning technologies for the drones to stay at all times within the boundaries of their flight plans, which will be composed of stopping points and the paths in between. This involves mitigating issues such as temporary blocking of line-of-sight between the drone and any existing radio beacons; sensor data noise; and the loss of visual references. We present a self-corrective solution for this purpose. It corrects visual odometer readings based on filtered and clustered Ultra-Wide Band (UWB) data, as an alternative to direct Kalman fusion. The approach combines the advantages of these technologies when at least one of them works properly at any measurement spot. It has three method components: independent Kalman filtering, data association by means of stream clustering and mutual correction of sensor readings based on the generation of cumulative correction vectors. The approach is inspired by the observation that UWB positioning works reasonably well at static spots whereas visual odometer measurements reflect straight displacements correctly but can underestimate their length. Our experimental results demonstrate the advantages of the approach in the application scenario over Kalman fusion, in terms of stopping point detection and trajectory estimation error.

Wireless connectivity is essential for industrial production processes and workflow management. Moreover, the connectivity requirements of industrial devices, which are usually long-term investments, are diverse and require different radio interfaces. In this regard, the 3GPP has studied how to support heterogeneous radio access technologies (RATs) such as Wi-Fi and unlicensed cellular technologies in 5G core networks. In some cases, these technologies coexist in the same spectrum. Dynamic spectrum sharing (DSS), which has already been proven to increase spectrum efficiency in licensed bands, can also be applied to this scenario. In this paper, we propose two solutions for mobile network operators (MNOs) or service providers to dynamically divide (multiplex) the radio resources of a shared channel between a Wi-Fi basic service set (BSS) and one or several carriers of scheduled wireless networks, such as cellular technologies, with a configurable level of sharing granularity. These solutions do not require modifications to the current commercial off-the-shelf (COTS) end devices. We adapt the existing IEEE 802.11 procedures to notify the Wi-Fi stations that they must share channels with different access networks. We demonstrate that our dynamic sharing proposals are also advantageous over direct coexistence and evaluate each of them quantitatively and qualitatively to determine when one or the other is preferable. The evaluation is particularized for IEEE 802.11ac and long-term evolution (LTE) license assisted access (LAA), but the solutions can be easily extended to 5G new radio-unlicensed (5G NR-U) or to any other wireless technology in which the network side schedules end device transmissions.

Short texts are omnipresent in real-time news, social network commentaries, etc. Traditional text representation methods have been successfully applied to self-contained documents of medium size. However, information in short texts is often insufficient, due, for example, to the use of mnemonics, which makes them hard to classify. Therefore, the particularities of specific domains must be exploited. In this article we describe a novel system that combines Natural Language Processing techniques with Machine Learning algorithms to classify banking transaction descriptions for personal finance management, a problem that was not previously considered in the literature. We trained and tested that system on a labelled dataset with real customer transactions that will be available to other researchers on request. Motivated by existing solutions in spam detection, we also propose a short text similarity detector to reduce training set size based on the Jaccard distance. Experimental results with a two-stage classifier combining this detector with a SVM indicate a high accuracy in comparison with alternative approaches, taking into account complexity and computing time. Finally, we present a use case with a personal finance application, CoinScrap, which is available at Google Play and App Store.

Queued Radio Frequency Identification (RFID) networks arise naturally in many applications, where tags are grouped into batches, and each batch must be processed before the next reading job starts. In these cases, the system must be able to handle all incoming jobs, keeping the queue backlogs bounded. This property is called stability. Besides, in RFID networks, it is common that some readers cannot operate at the same time, due to mutual interferences. This fact reduces the maximum traffic that readers can process since they have to share the channel. Synchronous networks share the channel using a TDMA approach. The goal of this work is to analytically determine whether a synchronous queued RFID network attains stable operation under a given incoming traffic. Stability depends on the service rate, which is characterized in this paper using an exact numerical method based on a recursive analytical approach, overcoming the limitations of previous works, which were based on simplifications. We also address different flow optimization problems, such as computing the maximum joint traffic that a network can process stably, selecting the minimal number of readers to process a given total load, or determining the optimal timeslot duration, which are novel in the RFID literature.

Traditionally, the cellular spectrum is allocated to operators (OPs) through auctions, as ideal mechanisms to discover market prices and allocate scarce resources. Even though spectrum is indeed scarce in sub-6 GHz bands, it becomes abundant in millimeter-wave (mmWave) bands. Interestingly, in that context, it is base station (BS) density which is limiting, and thus a critical factor, due to the outage phenomena in urban environments. Facing BS scarcity is one of the main reasons to foster virtualization techniques aimed at improving utilization and lowering costs. We consider a scenario with an infrastructure provider (InP) owner of a number of BSs and a set of OPs with their users (UEs). We propose a three-phase framework to price network infrastructure slices (NISs) and allocate them to OPs and to efficiently associate UEs with those NISs. The framework stages are: 1) an initial association, 2) a distributed auction mechanism across the BSs to allocate resources to Ops, and 3) a re-association process where the OPs can optimize the NISs they are awarded. The auction incentivizes OPs to bid truthfully and the outcome yields both socially optimal NISs and Vickrey-Clarke-Groves (VCG) prices. For the re-association phase, we propose deterministic and stochastic exchange-matching algorithms and demonstrate their convergence to stable matching and stable-optimal matching, respectively.

We present an automatic text expansion system to generate English sentences, which performs automatic Natural Language Generation (NLG) by combining linguistic rules with statistical approaches. Here, “automatic” means that the system can generate coherent and correct sentences from a minimum set of words. From its inception, the design is modular and adaptable to other languages. This adaptability is one of its greatest advantages. For English, we have created the highly precise aLexiE lexicon with wide coverage, which represents a contribution on its own. We have evaluated the resulting NLG library in an Augmentative and Alternative Communication (AAC) proof of concept, both directly (by regenerating corpus sentences) and manually (from annotations) using a popular corpus in the NLG field. We performed a second analysis by comparing the quality of text expansion in English to Spanish, using an ad-hoc Spanish-English parallel corpus. The system might also be applied to other domains such as report and news generation.

In Narrowband Internet of Things (NB-IoT), the control of uplink transmissions is a complex task involving device scheduling, resource allocation in the carrier, and the configuration of link-adaptation parameters. Existing heuristic proposals partially address the problem, but reinforcement learning (RL) seems to be the most effective approach a priori, given its success in similar control problems. However, the low sample efficiency of conventional (model-free) RL algorithms is an important limitation for their deployment in real systems. During their initial learning stages, RL agents need to explore the policy space selecting actions that are, in general, highly ineffective. In an NB-IoT access network this implies a disproportionate increase in transmission delays. In this paper, we make two contributions to enable the adoption of RL in NB-IoT: first, we present a multi-agent architecture based on the principle of task division. Second, we propose a new model-based RL algorithm for link adaptation characterized by its high sample efficiency. The combination of these two strategies results in an algorithm that, during the learning phase, is able to maintain the transmission delay in the order of hundreds of milliseconds, whereas model-free RL algorithms cause delays of up to several seconds. This allows our approach to be deployed, without prior training, in an operating NB-IoT network and learn to control it efficiently without degrading its performance.