Knowledge graph embedding aims at modeling entities and relations with low-dimensional vectors. Most previous methods require that all entities should be seen during training, which is unpractical for real-world knowledge graphs with new entities emerging on a daily basis. Recent efforts on this issue suggest training a neighborhood aggregator in conjunction with the conventional entity and relation embeddings, which may help embed new entities inductively via their existing neighbors. However, their neighborhood aggregators neglect the unordered and unequal natures of an entity's neighbors. To this end, we summarize the desired properties that may lead to effective neighborhood aggregators. We also introduce a novel aggregator, namely, Logic Attention Network (LAN), which addresses the properties by aggregating neighbors with both rules- and network-based attention weights. By comparing with conventional aggregators on two knowledge graph completion tasks, we experimentally validate LAN's superiority in terms of the desired properties.

Emily Parker, who covered China for the Wall Street Journal, is the author of "Now I Know Who My Comrades Are: Voices From the Internet Underground." Silicon Valley was once able to write off Chinese tech companies as mere copycats. The big American players, from Twitter to Facebook to Google, all had a Chinese impersonator. But the rise of hugely successful Chinese messaging apps like WeChat -- not to mention all the U.S. tech companies that failed in China -- now make clear that the nation's tech companies should not be underestimated. In his book "AI Superpowers," Kai-Fu Lee, a well-known artificial-intelligence expert, venture capitalist and former president of Google China, argues that China and Silicon Valley will lead the world in AI.

The Maltese government has announced the formation of a taskforce to develop a national artificial intelligence (AI) strategy, Cointelegraph reports Tuesday, Nov. 1 from the Malta Blockchain Summit. The Junior Minister for Financial services, Digital economy and Innovation, Silvio Schembri announced the launch of the governmental initiative "Malta.ai," "After successfully positioning Malta as the'Blockchain Island,' by being the first in the world to regulate DLT (distributed ledger technology) products and services, we now would like to position Malta amongst the top 10 countries in the world with an artificial intelligence policy." The government has already launched a website for its national AI strategy. According to official statements at the Malta Blockchain Summit, AI projects will be monitored by the Malta Digital Innovation Authority -- the same organization that monitors DLT.

Patients and their families often want continuous monitoring and care. Traditional health insurance providers are partnering with telehealth companies, to address those concerns. Anthem is working with American Well, Cigna is working with MDLive, Bupa is working with Babylon Health and Aflac is working with MeMD to deliver benefits of telehealth to it's existing customers. Health insurance providers such as Oscar Health is redefining health-insurance by building the whole customer experience around its own telehealth services. As telehealth continues to replace traditional health care, it is going to inherit some of its challenges. These include increased cost of care due to multiple vendors, complex care pathways, and government policies. However, the question that remains to be answered is will this advanced technology that we call telehealth, be able to redefine the quality, equity and affordability of healthcare throughout the world.

The digital telecommunications receiver is an important context for inference methodology, the key objective being to minimize the expected loss function in recovering the transmitted information. For that criterion, the optimal decision is the Bayesian minimum-risk estimator. However, the computational load of the Bayesian estimator is often prohibitive and, hence, efficient computational schemes are required. The design of novel schemes, striking new balances between accuracy and computational load, is the primary concern of this thesis. Two popular techniques, one exact and one approximate, will be studied. The exact scheme is a recursive one, namely the generalized distributive law (GDL), whose purpose is to distribute all operators across the conditionally independent (CI) factors of the joint model, so as to reduce the total number of operators required. In a novel theorem derived in this thesis, GDL, if applicable, will be shown to guarantee such a reduction in all cases. An associated lemma also quantifies this reduction. For practical use, two novel algorithms, namely the no-longer-needed (NLN) algorithm and the generalized form of the Markovian Forward-Backward (FB) algorithm, recursively factorizes and computes the CI factors of an arbitrary model, respectively. The approximate scheme is an iterative one, namely the Variational Bayes (VB) approximation, whose purpose is to find the independent (i.e. zero-order Markov) model closest to the true joint model in the minimum Kullback-Leibler divergence (KLD) sense. Despite being computationally efficient, this naive mean field approximation confers only modest performance for highly correlated models. A novel approximation, namely Transformed Variational Bayes (TVB), will be designed in the thesis in order to relax the zero-order constraint in the VB approximation, further reducing the KLD of the optimal approximation.

Adversarial examples can be defined as inputs to a model which induce a mistake - where the model output is different than that of an oracle, perhaps in surprising or malicious ways. Original models of adversarial attacks are primarily studied in the context of classification and computer vision tasks. While several attacks have been proposed in natural language processing (NLP) settings, they often vary in defining the parameters of an attack and what a successful attack would look like. The goal of this work is to propose a unifying model of adversarial examples suitable for NLP tasks in both generative and classification settings. We define the notion of adversarial gain: based in control theory, it is a measure of the change in the output of a system relative to the perturbation of the input (caused by the so-called adversary) presented to the learner. This definition, as we show, can be used under different feature spaces and distance conditions to determine attack or defense effectiveness across different intuitive manifolds. This notion of adversarial gain not only provides a useful way for evaluating adversaries and defenses, but can act as a building block for future work in robustness under adversaries due to its rooted nature in stability and manifold theory.

In this paper we address a task of relation mention extraction from noisy data: extracting representative phrases for a particular relation from noisy sentences that are collected via distant supervision. Despite its significance and value in many downstream applications, this task is less studied on noisy data. The major challenges exists in 1) the lack of annotation on mention phrases, and more severely, 2) handling noisy sentences which do not express a relation at all. To address the two challenges, we formulate the task as a semi-Markov decision process and propose a novel hierarchical reinforcement learning model. Our model consists of a top-level sentence selector to remove noisy sentences, a low-level mention extractor to extract relation mentions, and a reward estimator to provide signals to guide data denoising and mention extraction without explicit annotations. Experimental results show that our model is effective to extract relation mentions from noisy data.

China now has seminars to teach other countries how to censor free speech as its'techno-dystopia' spreads, a worrying report has found. Governments worldwide are stepping up use of online tools to suppress dissent and tighten their grip on power, a human rights watchdog study found. Chinese officials have held sessions on controlling information with 36 of the 65 countries assessed, and provided telecom and surveillance equipment to a number of foreign governments, researchers said. India led the world in the number of internet shutdowns, with over 100 reported incidents in 2018 so far, claiming that the moves were needed to halt the flow of disinformation and incitement to violence. Many governments, including Saudi Arabia, are employing'troll armies' to manipulate social media and in many cases drown out the voices of dissidents.

Nasa is building robots that can dig up Martian soil and convert it into rocket fuel. The machines will strip water from the soil and convert it into methane - a compound that has been tipped to power the rockets of the future. They could solve a major problem facing Nasa's deep space plans: How to keep rockets light enough to fly while still carrying enough fuel to get to and from Mars. Nasa plans to send manned missions to Mars in the early 2030s. But before humanity takes its first step on the red planet, the space agency will send a fleet of unmanned vehicles to test the habitability of its arid, dusty surface.

Nearly eight months after one of its autonomous test vehicles hit and killed an Arizona pedestrian, Uber wants to resume testing on public roads. The company has filed an application with the Pennsylvania Department of Transportation to test in Pittsburgh, and it has issued a lengthy safety report pledging to put two human backup drivers in each vehicle and take a raft of other precautions to make the vehicles safe. Company officials acknowledge they have a long way to go to regain public trust after the March 18 crash in Tempe, Arizona, that killed Elaine Herzberg, 49, as she crossed a darkened road outside the lines of a crosswalk. Nearly eight months after one of its autonomous test vehicles hit and killed an Arizona pedestrian, Uber wants to resume testing on public roads. Police said Uber's backup driver in the autonomous Volvo SUV was streaming the television show'The Voice' on her phone and looking downward before crash. The National Transportation Safety Board said the autonomous driving system on the Volvo spotted Herzberg about six seconds before hitting her, but did not stop because the system used to automatically apply brakes in potentially dangerous situations had been disabled.