Knowledge from diverse application domains is organized as knowledge graphs (KGs) that are stored in RDF engines accessible in the web via SPARQL endpoints. Expressing a well-formed SPARQL query requires information about the graph structure and the exact URIs of its components, which is impractical for the average user. Question answering (QA) systems assist by translating natural language questions to SPARQL. Existing QA systems are typically based on application-specific human-curated rules, or require prior information, expensive pre-processing and model adaptation for each targeted KG. Therefore, they are hard to generalize to a broad set of applications and KGs. In this paper, we propose KGQAn, a universal QA system that does not need to be tailored to each target KG. Instead of curated rules, KGQAn introduces a novel formalization of question understanding as a text generation problem to convert a question into an intermediate abstract representation via a neural sequence-to-sequence model. We also develop a just-in-time linker that maps at query time the abstract representation to a SPARQL query for a specific KG, using only the publicly accessible APIs and the existing indices of the RDF store, without requiring any pre-processing. Our experiments with several real KGs demonstrate that KGQAn is easily deployed and outperforms by a large margin the state-of-the-art in terms of quality of answers and processing time, especially for arbitrary KGs, unseen during the training.

We explore the effectiveness of character-level neural machine translation using Transformer architecture for various levels of language similarity and size of the training dataset on translation between Czech and Croatian, German, Hungarian, Slovak, and Spanish. We evaluate the models using automatic MT metrics and show that translation between similar languages benefits from character-level input segmentation, while for less related languages, character-level vanilla Transformer-base often lags behind subword-level segmentation. We confirm previous findings that it is possible to close the gap by finetuning the already trained subword-level models to character-level.

The accurate assessment of fish stocks is crucial for sustainable fisheries management. However, existing statistical stock assessment models can have low forecast performance of relevant stock parameters like recruitment or spawning stock biomass, especially in ecosystems that are changing due to global warming and other anthropogenic stressors. In this paper, we investigate the use of machine learning models to improve the estimation and forecast of such stock parameters. We propose a hybrid model that combines classical statistical stock assessment models with supervised ML, specifically gradient boosted trees. Our hybrid model leverages the initial estimate provided by the classical model and uses the ML model to make a post-hoc correction to improve accuracy. We experiment with five different stocks and find that the forecast accuracy of recruitment and spawning stock biomass improves considerably in most cases.

Numerous parties are calling for the democratisation of AI, but the phrase is used to refer to a variety of goals, the pursuit of which sometimes conflict. This paper identifies four kinds of AI democratisation that are commonly discussed: (1) the democratisation of AI use, (2) the democratisation of AI development, (3) the democratisation of AI profits, and (4) the democratisation of AI governance. Numerous goals and methods of achieving each form of democratisation are discussed. The main takeaway from this paper is that AI democratisation is a multifarious and sometimes conflicting concept that should not be conflated with improving AI accessibility. If we want to move beyond ambiguous commitments to democratising AI, to productive discussions of concrete policies and trade-offs, then we need to recognise the principal role of the democratisation of AI governance in navigating tradeoffs and risks across decisions around use, development, and profits.

The footprint of Russian President Vladimir Putin's war on Ukraine is growing fast after a weekend in which sea drones crippled a Russian naval vessel and oil tanker. For the first time, the attacks put at risk Russia's commodity exports via the Black Sea, a route that accounts for most of the grain and 15% to 20% of the oil Russia sells daily on global markets. Significantly higher insurance and shipping costs are likely to follow for Moscow, but there are risks to European and global markets, too. The expansion comes as Ukraine's counteroffensive advances more slowly than Kyiv officials planned, and as Saudi Arabia's attempt to catalyze peace talks by hosting a multinational conference showed just how hard it is likely to be to end the bloodshed on terms both sides can accept.

A Russian tanker was damaged in a Ukrainian drone attack in the Kerch Strait, briefly halting traffic on the strategic bridge linking Crimea to Russia on Saturday, a day after one of Moscow's warships was hit in the Black Sea. The number of attacks in the Black Sea has increased from both sides since Moscow exited a deal last month that had allowed Ukrainian grain exports via the shipping hub during the conflict between the two countries. The Russian tanker SIG was hit around 11:20 p.m. Friday south of the Kerch Strait, Russia's Federal Agency for Sea and Inland Water Transport said.

Ukrainian sea drones have attacked a key Russian port on the Black Sea, damaging a naval ship, according to a Ukrainian official, speaking about the latest in a series of strikes inside Russia after Kyiv promised to bring the fight home to the Kremlin. Moscow said it repelled Friday's attack on Novorossiysk, which marked the first time a commercial Russian port has been targeted in the 18-month war. Olenegorsky Gornyak, a landing ship, suffered a serious breach in the attack, carried out by Ukraine's navy and security service, according to a security service official. As a result, the ship is unable to carry out its combat missions, said the official who spoke on the condition of anonymity because he was not authorised to give the information to the media. Ukrainian news agencies carried footage from social media channels that they suggested showed the Olenegorsky Gornyak listing to one side. The ship is designed to transport troops and heavy equipment and was sent for repairs in 2014, according to Russian media reports.

This is based on announcements by Russian and Ukrainian authorities, and local media reports. Ukrainian defence sources have told CNN that sea drones had also been used in an attack on the Kerch Bridge to Crimea in July.

Ukrainian President Volodymyr Zelenskyy warned this week that war is coming to Russia after kamikaze drone attacks targeted skyscrapers in Moscow's financial district, as his country's forces continued to score small-scale territorial successes against Russian troops in Ukraine's east and south. Here is a round-up of the main battlefield events during the 75th week of the war. On July 30, a suspected Ukrainian long-range drone hit a Moscow high-rise building that houses the Ministry of Digital Development, the Economy Ministry and the Ministry of Industrial Development, responsible for military industry. Two days later, another pair of drones was shot down outside Moscow, but a third made it through to the city where it was intercepted by electronic jammers and crashed into a skyscraper, damaging the facade. The attacks came just days after a previous drone raid on the centre of the Russian capital.

With the rapid amassing of spatial-temporal (ST) ocean data, many spatial-temporal data mining (STDM) studies have been conducted to address various oceanic issues, including climate forecasting and disaster warning. Compared with typical ST data (e.g., traffic data), ST ocean data is more complicated but with unique characteristics, e.g., diverse regionality and high sparsity. These characteristics make it difficult to design and train STDM models on ST ocean data. To the best of our knowledge, a comprehensive survey of existing studies remains missing in the literature, which hinders not only computer scientists from identifying the research issues in ocean data mining but also ocean scientists to apply advanced STDM techniques. In this paper, we provide a comprehensive survey of existing STDM studies for ocean science. Concretely, we first review the widely-used ST ocean datasets and highlight their unique characteristics. Then, typical ST ocean data quality enhancement techniques are explored. Next, we classify existing STDM studies in ocean science into four types of tasks, i.e., prediction, event detection, pattern mining, and anomaly detection, and elaborate on the techniques for these tasks. Finally, promising research opportunities are discussed. This survey can help scientists from both computer science and ocean science better understand the fundamental concepts, key techniques, and open challenges of STDM for ocean science.