Multi-dimensional evaluation is the dominant paradigm for human evaluation in Natural Language Generation (NLG), i.e., evaluating the generated text from multiple explainable dimensions, such as coherence and fluency. However, automatic evaluation in NLG is still dominated by similarity-based metrics, and we lack a reliable framework for a more comprehensive evaluation of advanced models. In this paper, we propose a unified multi-dimensional evaluator UniEval for NLG. We re-frame NLG evaluation as a Boolean Question Answering (QA) task, and by guiding the model with different questions, we can use one evaluator to evaluate from multiple dimensions. Furthermore, thanks to the unified Boolean QA format, we are able to introduce an intermediate learning phase that enables UniEval to incorporate external knowledge from multiple related tasks and gain further improvement. Experiments on three typical NLG tasks show that UniEval correlates substantially better with human judgments than existing metrics. Specifically, compared to the top-performing unified evaluators, UniEval achieves a 23% higher correlation on text summarization, and over 43% on dialogue response generation. Also, UniEval demonstrates a strong zero-shot learning ability for unseen evaluation dimensions and tasks. Source code, data and all pre-trained evaluators are available on our GitHub repository (https://github.com/maszhongming/UniEval).

The advent of deep learning (DL) gave rise to significant breakthroughs in Reinforcement Learning (RL) research. Deep Reinforcement Learning (DRL) algorithms have reached super-human level skills when applied to vision-based control problems as such in Atari 2600 games where environment states were extracted from pixel information. Unfortunately, these environments are far from being applicable to highly dynamic and complex real-world tasks as in autonomous control of a fighter aircraft since these environments only involve 2D representation of a visual world. Here, we present a semi-realistic flight simulation environment Harfang3D Dog-Fight Sandbox for fighter aircrafts. It is aimed to be a flexible toolbox for the investigation of main challenges in aviation studies using Reinforcement Learning. The program provides easy access to flight dynamics model, environment states, and aerodynamics of the plane enabling user to customize any specific task in order to build intelligent decision making (control) systems via RL. The software also allows deployment of bot aircrafts and development of multi-agent tasks. This way, multiple groups of aircrafts can be configured to be competitive or cooperative agents to perform complicated tasks including Dog Fight. During the experiments, we carried out training for two different scenarios: navigating to a designated location and within visual range (WVR) combat, shortly Dog Fight. Using Deep Reinforcement Learning techniques for both scenarios, we were able to train competent agents that exhibit human-like behaviours. Based on this results, it is confirmed that Harfang3D Dog-Fight Sandbox can be utilized as a 3D realistic RL research platform.

We propose a general purpose Bayesian inference algorithm for expensive likelihoods, replacing the stochastic term in the Langevin equation with a deterministic density gradient term. The particle density is evaluated from the current particle positions using a Normalizing Flow (NF), which is differentiable and has good generalization properties in high dimensions. We take advantage of NF preconditioning and NF based Metropolis-Hastings updates for a faster convergence. We show on various examples that the method is competitive against state of the art sampling methods.

Federated Recommendation (FR) has received considerable popularity and attention in the past few years. In FR, for each user, its feature vector and interaction data are kept locally on its own client thus are private to others. Without the access to above information, most existing poisoning attacks against recommender systems or federated learning lose validity. Benifiting from this characteristic, FR is commonly considered fairly secured. However, we argue that there is still possible and necessary security improvement could be made in FR. To prove our opinion, in this paper we present FedRecAttack, a model poisoning attack to FR aiming to raise the exposure ratio of target items. In most recommendation scenarios, apart from private user-item interactions (e.g., clicks, watches and purchases), some interactions are public (e.g., likes, follows and comments). Motivated by this point, in FedRecAttack we make use of the public interactions to approximate users' feature vectors, thereby attacker can generate poisoned gradients accordingly and control malicious users to upload the poisoned gradients in a well-designed way. To evaluate the effectiveness and side effects of FedRecAttack, we conduct extensive experiments on three real-world datasets of different sizes from two completely different scenarios. Experimental results demonstrate that our proposed FedRecAttack achieves the state-of-the-art effectiveness while its side effects are negligible. Moreover, even with small proportion (3%) of malicious users and small proportion (1%) of public interactions, FedRecAttack remains highly effective, which reveals that FR is more vulnerable to attack than people commonly considered.

Agent-based modelling (ABM) is a facet of wider Multi-Agent Systems (MAS) research that explores the collective behaviour of individual `agents', and the implications that their behaviour and interactions have for wider systemic behaviour. The method has been shown to hold considerable value in exploring and understanding human societies, but is still largely confined to use in academia. This is particularly evident in the field of Urban Analytics; one that is characterised by the use of new forms of data in combination with computational approaches to gain insight into urban processes. In Urban Analytics, ABM is gaining popularity as a valuable method for understanding the low-level interactions that ultimately drive cities, but as yet is rarely used by stakeholders (planners, governments, etc.) to address real policy problems. This paper presents the state-of-the-art in the application of ABM at the interface of MAS and Urban Analytics by a group of ABM researchers who are affiliated with the Urban Analytics programme of the Alan Turing Institute in London (UK). It addresses issues around modelling behaviour, the use of new forms of data, the calibration of models under high uncertainty, real-time modelling, the use of AI techniques, large-scale models, and the implications for modelling policy. The discussion also contextualises current research in wider debates around Data Science, Artificial Intelligence, and MAS more broadly.

The U.S Army is rolling out a strategy focused on software, data and artificial intelligence practices, a move officials believe will clarify for industry what the service needs to transform into a high-tech, digital-forward force and how, exactly, it plans to get there. The strategy, which will be unveiled during the Association of the U.S. Army's annual conference, is meant to help "pivot our programs to adopt modern software practices, adopt data-centricity, and get us to artificial intelligence, machine learning and [figuring] out where the right applications of that are so that we can really enable commanders in the field to make data-driven, fast decisions," Jennifer Swanson, the deputy assistant secretary of the Army for data engineering and software, told Defense News in an interview ahead of the event. Swanson's title alone hints at the transformation underway for the Army's acquisition branch. When she was hired earlier this year, she was chief systems engineer. The strategy arrives as the Army conducts a massive overhaul of its virtual footprint and computer infrastructure in order to better prepare for potential conflicts with China and Russia.

Artificial intelligence is giving finance a boost -- through robo advising, its ability to improve fraud detection and claims processing, and more. Despite the upsides, there are risks and public policy challenges that must be considered, said Gary Gensler, chair of the Securities and Exchange Commission and a former professor at MIT Sloan. "I think that we're living in a truly transformational time," said Gensler, who spoke at the recent AI Policy Forum summit at MIT. Artificial intelligence is "every bit as transformational as the internet," especially when it comes to predictive data analytics, "but it comes with some risks." During the conversation, Gensler shared his thoughts on how artificial intelligence is changing finance. Having solid predictive models is crucial in AI, whether it's in social media or in driverless cars.

This guidance is part of a wider collection about using AI in the public sector. AI has the potential to change the way we live and work. Embedding AI across all sectors has the potential to create thousands of jobs and drive economic growth. By one estimate, AI's contribution to the United Kingdom could be as large as 5% of GDP by 2030. A number of public sector organisations are already successfully using AI for tasks ranging from fraud detection to answering customer queries.

Did you miss a session from MetaBeat 2022? Head over to the on-demand library for all of our featured sessions here. Expectations were high when the White House released its Blueprint for an AI Bill of Rights on Tuesday. Developed by the White House Office of Science and Technology Policy (OSTP), the blueprint is a non-binding document that outlines five principles that should guide the design, use and deployment of automated systems, as well as technical guidance toward implementing the principles, including recommended action for a variety of federal agencies. For many, high expectations for dramatic change led to disappointment, including criticism that the AI Bill of Rights is "toothless" against artificial intelligence (AI) harms caused by big tech companies and is just a "white paper."

But the design faces an uphill climb in the halls of the Pentagon, military experts said. Russia's war in Ukraine has shown the promise and peril of tank technology in a modern battlefield. Military strategists worry how useful tanks might be in a potential war against China, the U.S. military's chief rival. Outfitting lethal machines with artificial intelligence also concerns military skeptics.