A BSTRACT Knowledge graph embedding research has overlooked the problem of probability calibration. We show popular embedding models are indeed uncalibrated. That means probability estimates associated to predicted triples are unreliable. We present a novel method to calibrate a model when ground truth negatives are not available, which is the usual case in knowledge graphs. We propose to use Platt scaling and isotonic regression alongside our method. Experiments on three datasets with ground truth negatives show our contribution leads to well calibrated models when compared to the gold standard of using negatives. We get significantly better results than the uncalibrated models from all calibration methods. We show isotonic regression offers the best the performance overall, not without tradeoffs. We also show that calibrated models reach state-of-the-art accuracy without the need to define relation-specific decision thresholds. 1 I NTRODUCTION Knowledge graph embedding models are neural architectures that learn vector representations (i.e.

This paper presents an automated tool called Morphy for datamorphic testing. It classifies software test artefacts into test entities and test morphisms, which are mappings on testing entities. In addition to datamorphisms, metamorphisms and seed test case makers, Morphy also employs a set of other test morphisms including test case metrics and filters, test set metrics and filters, test result analysers and test executers to realise test automation. In particular, basic testing activities can be automated by invoking test morphisms. Test strategies can be realised as complex combinations of test morphisms. Test processes can be automated by recording, editing and playing test scripts that invoke test morphisms and strategies. Three types of test strategies have been implemented in Morphy: datamorphism combination strategies, cluster border exploration strategies and strategies for test set optimisation via genetic algorithms. This paper focuses on the datamorphism combination strategies by giving their definitions and implementation algorithms. The paper also illustrates their uses for testing both traditional software and AI applications with three case studies.

Answer Set Programming (ASP) is nowadays a dominant rule-based knowledge representation tool. Though existing ASP variants enjoy efficient implementations, generating an answer set remains intractable. The goal of this research is to define a new \asp-like rule language, 4SP, with tractable model generation. The language combines ideas of ASP and a paraconsistent rule language 4QL. Though 4SP shares the syntax of \asp and for each program all its answer sets are among 4SP models, the new language differs from ASP in its logical foundations, the intended methodology of its use and complexity of computing models. As we show in the paper, 4QL can be seen as a paraconsistent counterpart of ASP programs stratified with respect to default negation. Although model generation of well-supported models for 4QL programs is tractable, dropping stratification makes both 4QL and ASP intractable. To retain tractability while allowing non-stratified programs, in 4SP we introduce trial expressions interlacing programs with hypotheses as to the truth values of default negations. This allows us to develop a~model generation algorithm with deterministic polynomial time complexity. We also show relationships among 4SP, ASP and 4QL.

--This position paper presents a synthesis viewpoint of blockchains from two orthogonal perspectives: fault-tolerant distributed systems and game theory. Specifically, we formulate a new game-theoretical problem in the context of blockchains and sketch a closed-form Nash equilibrium to the problem. Blockchains have drawn much research interest, way beyond its first realization, Bitcoin [3], a cryptocurrency application built upon blockchains. From system perspectives, various facets, especially performance and scalability, have been intensively studied by multiple computer systems communities including but not limited to: computer security [7], distributed systems [11], and database systems [9]. Works on the theoretical foundation of blockchains are, however, comparatively limited, and mostly in the cryptocurrency context [6], [8], [10], usually in a permissionless setup where nodes are free to join or leave the blockchain network. In permissioned blockchains such as Hyperledger Fabric [2], where Practical Byzantine Fault-Tolerance [4] (PBFT) is the de facto consensus protocol, much work focused on PBFT and its variants without in-depth reasoning on the node's (or, user's) rationality--analyses simply assume that a node is either faulty or non-faulty.

Toyota Motor Corp. has unveiled an upgraded version of its human-shaped T-HR3 robot. The robot, which is controlled remotely by a person wearing a headset and wiring on his or her arms and hands, now has faster and smoother finger movements because the controlling device is lighter and easier to use. Such a robot could, in the future, be used to perform surgery in a distant place where a doctor cannot travel. It also might allow people to feel like they're participating in events they can't actually attend. In a recent demonstration in Tokyo, a person wearing a headset and wiring made the robot move in exactly the same way he was moving, waving or making dance-like movements.

PARIS – France has officially deployed its first armed drones, three American-built Reapers fitted with laser-guided missiles, in its fight against a jihadi insurrection in Africa's Sahel region, Defense Minister Florence Parly announced Thursday. The drones, which have already since 2014 provided surveillance support to the French anti-jihadi Barkhane mission in Mali, Niger and Burkina Faso, will from now on also be able to strike targets, she said. France joins a small club of countries, including the United States, Britain and Israel, that use armed, distance-piloted aircraft in combat. The Reapers will each carry two 250-kg (550-pound) laser-guided bombs, and are entering service after a series of operational tests carried out from the airbase in the Niger capital Niamey. "Their main missions remain surveillance and intelligence … but these can be extended to strikes," Parly said.

The Talking Tech podcast is available for you every day with a quick hit on the latest tech news, gadget reviews, opinion on tech trends and interviews with insiders. On this page, you'll find quick links to all of our shows. Please rate and review the show on Apple Podcasts and "Favorite" us on Stitcher to help Talking Tech reach a wider audience. We have a new Alexa/Talking Tech skill! Follow USA TODAY's Jefferson Graham (@jeffersongraham) on Twitter, Instagram and YouTube.

Toyota has revealed the next update of its T-HR3 humanoid'avatar' service robot ahead of next year's Olympic Games. The robot is capable of flexible movements that mirror the actions of its human operators up to six miles away, almost in real time. Using a 5G connection and a human controller connected to wiring and a VR headset, the new T-HR3 is now able to execute more difficult tasks than before. This includes walking in a smoother, more natural manner and even preparing drinks, as demonstrated at this year's International Robotic Exhibition in Tokyo. The new and improved T-HR3 – which was first launched in 2017 – grasps a cocktail shaker at this year's International Robotic Exhibition in Tokyo'Avatar robots like T-HR3, which possess an actual body, are capable of going beyond VR to physically influence the real world,' said T-HR3 Development Team Leader Tomohisa Moridaira.

Scientists have pulled inspiration from insects in order to create a tiny, resilient robot. Referred to as'DEAnsect', this bug-like robot is made of soft materials, carries five times its weight and moves its artificial muscles 400 times a second. What makes this creation so unique that it is able to withstand multiple hits from a fly swatter, being folded or squashed without being damaged – making this robot design ideal for performing various tasks. DEAnsect was developed by a team from École Polytechnique Fédérale de Lausanne (EPFL) in Switzerland working with the Integrated Actuators Laboratory (LAI) and colleagues from the University of Cergy-Pontoise, France. DEAnsect is designed with dielectric elastomer actuators (DEAs),which is a type of hair-thin artificial muscle that propels it forward through vibrations. Scientists have pulled inspiration from insects in order to create a tiny, resilient robot.

People's understanding of supposedly'equivalent' words used to express emotions -- such as love, fear or anxiety -- vary greatly between different languages, a study found. Researchers studied words describing emotion in more than 2,000 languages and found'significant variation' in how emotions are expressed across cultures. For example, the researchers found that among the languages of the Pacific Islands, the words equivalent to the English word'surprise' are closely associated with'fear'. In contrast, the words for surprise in the languages of south-east Asia are more closely connected to concepts like'hope' and'wanting'. The team also found words with no equivalent in other languages, like Portuguese's'saudade', a deep melancholy for something lost, which has no English counterpart.