We present our system for the two subtasks of the shared task on propaganda detection in Arabic, part of WANLP'2022. Subtask 1 is a multi-label classification problem to find the propaganda techniques used in a given tweet. Our system for this task uses XLM-R to predict probabilities for the target tweet to use each of the techniques. In addition to finding the techniques, Subtask 2 further asks to identify the textual span for each instance of each technique that is present in the tweet; the task can be modeled as a sequence tagging problem. We use a multi-granularity network with mBERT encoder for Subtask 2. Overall, our system ranks second for both subtasks (out of 14 and 3 participants, respectively). Our empirical analysis show that it does not help to use a much larger English corpus annotated with propaganda techniques, regardless of whether used in English or after translation to Arabic.

Much of the existing work on text novelty detection has been studied at the topic level, i.e., identifying whether the topic of a document or a sentence is novel or not. Little work has been done at the fine-grained semantic level (or contextual level). For example, given that we know Elon Musk is the CEO of a technology company, the sentence "Elon Musk acted in the sitcom The Big Bang Theory" is novel and surprising because normally a CEO would not be an actor. Existing topic-based novelty detection methods work poorly on this problem because they do not perform semantic reasoning involving relations between named entities in the text and their background knowledge. This paper proposes an effective model (called PAT-SND) to solve the problem, which can also characterize the novelty. An annotated dataset is also created. Evaluation shows that PAT-SND outperforms 10 baselines by large margins.

A fundamental ability of an intelligent web-based agent is seeking out and acquiring new information. Internet search engines reliably find the correct vicinity but the top results may be a few links away from the desired target. A complementary approach is navigation via hyperlinks, employing a policy that comprehends local content and selects a link that moves it closer to the target. In this paper, we show that behavioral cloning of randomly sampled trajectories is sufficient to learn an effective link selection policy. We demonstrate the approach on a graph version of Wikipedia with 38M nodes and 387M edges. The model is able to efficiently navigate between nodes 5 and 20 steps apart 96% and 92% of the time, respectively. We then use the resulting embeddings and policy in downstream fact verification and question answering tasks where, in combination with basic TF-IDF search and ranking methods, they are competitive results to the state-of-the-art methods.

Federated Learning (FL) is a novel distributed privacy-preserving learning paradigm, which enables the collaboration among several participants (e.g., Internet of Things devices) for the training of machine learning models. However, selecting the participants that would contribute to this collaborative training is highly challenging. Adopting a random selection strategy would entail substantial problems due to the heterogeneity in terms of data quality, and computational and communication resources across the participants. Although several approaches have been proposed in the literature to overcome the problem of random selection, most of these approaches follow a unilateral selection strategy. In fact, they base their selection strategy on only the federated server's side, while overlooking the interests of the client devices in the process. To overcome this problem, we present in this paper FedMint, an intelligent client selection approach for federated learning on IoT devices using game theory and bootstrapping mechanism. Our solution involves the design of: (1) preference functions for the client IoT devices and federated servers to allow them to rank each other according to several factors such as accuracy and price, (2) intelligent matching algorithms that take into account the preferences of both parties in their design, and (3) bootstrapping technique that capitalizes on the collaboration of multiple federated servers in order to assign initial accuracy value for the newly connected IoT devices. Based on our simulation findings, our strategy surpasses the VanillaFL selection approach in terms of maximizing both the revenues of the client devices and accuracy of the global federated learning model.

Science consists on conceiving hypotheses, confronting them with empirical evidence, and keeping only hypotheses which have not yet been falsified. Under deductive reasoning they are conceived in view of a theory and confronted with empirical evidence in an attempt to falsify it, and under inductive reasoning they are conceived based on observation, confronted with empirical evidence and a theory is established based on the not falsified hypotheses. When the hypotheses testing can be performed with quantitative data, the confrontation can be achieved with Machine Learning methods, whose quality is highly dependent on the hypotheses' complexity, hence on the proper insertion of prior information into the set of hypotheses seeking to decrease its complexity without loosing good hypotheses. However, Machine Learning tools have been applied under the pragmatic view of instrumentalism, which is concerned only with the performance of the methods and not with the understanding of their behavior, leading to methods which are not fully understood. In this context, we discuss how prior information and computational power can be employed to solve a learning problem, but while prior information and a careful design of the hypotheses space has as advantage the interpretability of the results, employing high computational power has the advantage of a higher performance. We discuss why learning methods which combine both should work better from an understanding and performance perspective, arguing in favor of basic theoretical research on Machine Learning, in special about how properties of classifiers may be identified in parameters of modern learning models.

TuSimple Holdings Inc., a U.S.-based self-driving trucking company, faces federal investigations into whether it improperly financed and transferred technology to a Chinese startup, according to people with knowledge of the matter. The people said the concurrent probes by the Federal Bureau of Investigation, Securities and Exchange Commission and Committee on Foreign Investment in the U.S., known as Cfius, are examining TuSimple's relationship with Hydron Inc., a startup that says it is developing autonomous hydrogen-powered trucks and is led by one of TuSimple's co-founders. Investigators at the FBI and SEC are looking at whether TuSimple and its executives--principally Chief Executive Xiaodi Hou--breached fiduciary duties and securities laws by failing to properly disclose the relationship, the people familiar with the matter said. They are also probing whether TuSimple shared with Hydron intellectual property developed in the U.S. and whether that action defrauded TuSimple investors by sending valuable technology to an overseas adversary, the people said. A personal, guided tour to the best scoops and stories every day in The Wall Street Journal.

The drones used to attack Russian ships in the Black Sea in Crimea were equipped with Canadian-made parts used in the navigation systems, according to Russia's defence ministry. It said 16 Ukrainian drones attacked the fleet in the Black Sea in the annexed Crimean Peninsula early on Saturday. Russia said its navy "repelled" the assault in the bay of Sevastopol. The Russian military "conducted an examination of Canadian-made navigation modules" found in the shot-down unmanned aerial vehicles. "According to the results of the information recovered from the navigation receiver's memory, it was established that the launch of maritime drones was carried out from the coast near the city of Odesa," the ministry said in a statement on Sunday.

In a recent study published in PLOS Digital Health, researchers reviewed existing literature on the use of artificial intelligence (AI) in health care to characterize the AI applications used in the clinical applications during the coronavirus disease 2019 (COVID-19) pandemic, investigate the location, timing, and extent of AI use in healthcare, and examine the United States (U.S.) regulatory approval processes. Despite the large number of approvals granted by the U.S. Food and Drug Administration (FDA) to AI applications in healthcare in the last six years, the adoption of AI applications in different areas of healthcare has been limited. Furthermore, there is limited information on the development and use of AI applications during the COVID-19 pandemic, unlike the significant and rapid growth in telehealth and vaccine technologies. While previous reviews have reviewed the potential uses, challenges, and impacts of AI applications for COVID-19 clinical response, many of the reviews found methodological flaws and potential biases in the use of AI applications in clinical practice. A scarcity of reviews provides a comprehensive report on the development, testing, and applications of AI in COVID-19 clinical responses.

Russia's blockade of grain exports makes it "impossible" for fully loaded ships to leave port, Ukraine charged Sunday after Moscow claimed drone attacks on its Crimea fleet had exploited the grain corridor safe zone. Kyiv's maritime grain exports were halted after Russia pulled out of a landmark agreement that allowed the vital shipments. The July deal to unlock grain exports signed between Russia and Ukraine and brokered by Turkey and the United Nations, is critical to easing the global food crisis caused by the conflict. "(A) bulk carrier loaded with 40 tons of grain was supposed to leave the Ukraine port today," Infrastructure Minister Oleksandr Kubrakov tweeted. "These foodstuffs were intended for Ethiopians, that are on the verge of famine. But due to the blockage of the'grain corridor' by Russia the export is impossible," the Ukrainian minister said.

WASHINGTON, Oct 28 (Reuters) - Automakers and tech companies face a bumpy road to clearing regulatory roadblocks to deploying autonomous vehicles (AVs) without human controls on public roads, industry officials and lawmakers said. On Wednesday, Ford Motor Co (F.N) and Volkswagen AG (VOWG_p.DE) said they would shutter self-driving startup Argo AI, saying the technology was a long way off. The same is true when it comes to rules around the technology as well. Legislation in Congress has been stalled for more than five years over how to amend regulations to encompass self-driving cars, including the scope of consumer and legal protections. And U.S. regulators have given no indication when they might act on petitions to initially approve a few thousand self-driving cars on U.S. roads without steering wheels or brake pedals.