Developing artificial learning systems that can understand and generate natural language has been one of the long-standing goals of artificial intelligence. Recent decades have witnessed an impressive progress on both of these problems, giving rise to a new family of approaches. Especially, the advances in deep learning over the past couple of years have led to neural approaches to natural language generation (NLG). These methods combine generative language learning techniques with neural-networks based frameworks. With a wide range of applications in natural language processing, neural NLG (NNLG) is a new and fast growing field of research. In this state-of-the-art report, we investigate the recent developments and applications of NNLG in its full extent from a multidimensional view, covering critical perspectives such as multimodality, multilinguality, controllability and learning strategies. We summarize the fundamental building blocks of NNLG approaches from these aspects and provide detailed reviews of commonly used preprocessing steps and basic neural architectures. This report also focuses on the seminal applications of these NNLG models such as machine translation, description generation, automatic speech recognition, abstractive summarization, text simplification, question answering and generation, and dialogue generation. Finally, we conclude with a thorough discussion of the described frameworks by pointing out some open research directions.

The UiPath platform combines core robotic process automation (RPA) capabilities with tools for process discovery and analytics to report precisely the business impact. The core capabilities make it easy to build, deploy, and manage software robots (SRs) that emulate humans' interactions with information systems to perform certain tasks in business processes (BPs). Firstly, the BPs to be automated are designed, created, or recorded. They are created using drag-and-drop activities within a workflow. Then SRs work to perform BPs and an orchestrator acting as a control center designates tasks/processes to SRs and evaluates the efficiency of each one.

Women in AI Ireland in collaboration with Women in Research Ireland present this live virtual event: Artificial Intelligence #BreaktheBias. With this event, we celebrate technical competencies in Artificial Intelligence for both industry and academia by highlighting different pathways from academia to industry and challenges therein to mark the International Women's Day 2022! Dr. Georgiana Ifrim is an Associate Professor at the School of Computer Science, UCD, co-lead of the SFI Centre for Research Training in Machine Learning (ML-Labs) and SFI Funded Investigator with the Insight Centre for Data Analytics and VistaMilk SFI Centre. Dr Ifrim holds a PhD and MSc in Machine Learning, from Max-Planck Institute for Informatics, Germany, and a BSc in Computer Science, from University of Bucharest, Romania. Her research focuses on effective approaches for large scale sequence learning, time series classification and text mining.

On March 8, International Women's Day (IWD) we celebrate the political, socioeconomic and cultural achievements of women and the women right's movement towards gender equality. "Whilst the social and political rights of women are greater in some places than others, there is no country where gender equality has been achieved" says Mary Evans, professor at the London School of Economics and Political Science in her book "The persistence of gender inequality" (Polity Press 2017). In 2022 this situation has not changed either globally or at the European level as indicated in the EU Gender Equality index for 2020 where the average of the EU is 67.4% and the maximum is Sweden with 83.8%. Although there has been a clear commitment from the European Union on gender equality (specially in innovation and science), there are still structural forms of inequality that must be challenged and changed. It is not the aim of this article to analyse or comment on those, but to show what is being done and is available, especially in the European Union, for us to contribute as individuals and as a community towards gender equality in the field of robotics.

While Ukraine is yet to become a member of the North Atlantic Treaty Organization (NATO), the country has been accepted as a contributing participant to the NATO Cooperative Cyber Defence Centre of Excellence (CCDCOE). CCDCOE is a NATO-accredited cyberdefense hub that member nations use for research, training, and exercises covering several areas, including technology, strategy, operations, and law. Although this does not make Ukraine a NATO member, it will likely tighten collaboration and allow it to gain access to NATO member nations' cyber-expertise and share its own. "Ukraine's presence in the Centre will enhance the exchange of cyber expertise, between Ukraine and CCDCOE member nations," said Colonel Jaak Tarien, Director of NATO CCDCOE. "Ukraine could bring valuable first-hand knowledge of several adversaries within the cyber domain to be used for research, exercises and training," Minister of Defence of Estonia Kalle Laanet added that Ukraine "has valuable experience from previous cyber-attacks to provide significant value to the NATO CCDCOE."

Decision-making AI agents are often faced with two important challenges: the depth of the planning horizon, and the branching factor due to having many choices. Hierarchical reinforcement learning methods aim to solve the first problem, by providing shortcuts that skip over multiple time steps. To cope with the breadth, it is desirable to restrict the agent's attention at each step to a reasonable number of possible choices. The concept of affordances (Gibson, 1977) suggests that only certain actions are feasible in certain states. In this work, we model "affordances" through an attention mechanism that limits the available choices of temporally extended options. We present an online, model-free algorithm to learn affordances that can be used to further learn subgoal options. We investigate the role of hard versus soft attention in training data collection, abstract value learning in long-horizon tasks, and handling a growing number of choices. We identify and empirically illustrate the settings in which the paradox of choice arises, i.e. when having fewer but more meaningful choices improves the learning speed and performance of a reinforcement learning agent.

Damaging earthquakes can strike at any time. While we can't prevent them from occurring, we can make sure casualties, economic loss and disruption of essential services are kept to a minimum. Building more resilient cities is key to withstanding earthquake disasters. If we had a better idea of when earthquakes would strike, authorities could initiate local emergency, evacuation and shelter plans. But unfortunately, this is not the case.

Preventing and detecting intrusions and attacks on wireless networks has become an important and serious challenge. On the other hand, due to the limited resources of wireless nodes, the use of monitoring nodes for permanent monitoring in wireless sensor networks in order to prevent and detect intrusion and attacks in this type of network is practically non-existent. Therefore, the solution to overcome this problem today is the discussion of remote-control systems and has become one of the topics of interest in various fields. Remote monitoring of node performance and behavior in wireless sensor networks, in addition to detecting malicious nodes within the network, can also predict malicious node behavior in future. In present research, a network intrusion detection system using feature selection based on a combination of Whale optimization algorithm (WOA) and genetic algorithm (GA) and sample-based classification is proposed. In this research, the standard data set KDDCUP1999 has been used in which the characteristics related to healthy nodes and types of malicious nodes are stored based on the type of attacks in the network. The proposed method is based on the combination of feature selection based on Whale optimization algorithm and genetic algorithm with KNN classification in terms of accuracy criteria, has better results than other previous methods. Based on this, it can be said that the Whale optimization algorithm and the genetic algorithm have extracted the features related to the class label well, and the KNN method has been able to well detect the misconduct nodes in the intrusion detection data set in wireless networks.

It is well known the sample covariance has a consistent bias in the spectrum, for example spectrum of Wishart matrix follows the Marchenko-Pastur law. We in this work introduce an iterative algorithm 'Concent' that actively eliminate this bias and recover the true spectrum for small and moderate dimensions.

Contrastive Language--Image Pre-training (CLIP) has shown remarkable success in learning with cross-modal supervision from extensive amounts of image--text pairs collected online. Thus far, the effectiveness of CLIP has been investigated primarily in general-domain multimodal problems. This work evaluates the effectiveness of CLIP for the task of Medical Visual Question Answering (MedVQA). To this end, we present PubMedCLIP, a fine-tuned version of CLIP for the medical domain based on PubMed articles. Our experiments are conducted on two MedVQA benchmark datasets and investigate two MedVQA methods, MEVF (Mixture of Enhanced Visual Features) and QCR (Question answering via Conditional Reasoning). For each of these, we assess the merits of visual representation learning using PubMedCLIP, the original CLIP, and state-of-the-art MAML (Model-Agnostic Meta-Learning) networks pre-trained only on visual data. We open source the code for our MedVQA pipeline and pre-training PubMedCLIP. CLIP and PubMedCLIP achieve improvements in comparison to MAML's visual encoder. PubMedCLIP achieves the best results with gains in the overall accuracy of up to 3%. Individual examples illustrate the strengths of PubMedCLIP in comparison to the previously widely used MAML networks. Visual representation learning with language supervision in PubMedCLIP leads to noticeable improvements for MedVQA. Our experiments reveal distributional differences in the two MedVQA benchmark datasets that have not been imparted in previous work and cause different back-end visual encoders in PubMedCLIP to exhibit different behavior on these datasets. Moreover, we witness fundamental performance differences of VQA in general versus medical domains.