Knowledge bases are useful resources for many natural language processing tasks, however, they are far from complete. In this paper, we define a novel entity representation as a mixture of its neighborhood in the knowledge base and apply this technique on TransE--a well-known embedding model for knowledge base completion. Experimental results show that the neighborhood information significantly helps to improve the results of the TransE model, leading to better performance than obtained by other state-of-theart embedding models on three benchmark datasets for triple classification, entity prediction and relation prediction tasks.

Technology is changing the way we live. Innovative products like smartwatches, virtual assistants like Siri and Cortana, and self-driving cars are raising the bar on expectations. So why shouldn't that change be reflected in the way we work? Business Insider spoke to Dave Wright, the chief strategy officer at cloud computing business ServiceNow about what they're doing to improve processes and productivity and the workplace, as well as trends we're likely to see in the future. But first if you're not sure what ServiceNow does, here's how Wright explains it.

However, the "Ghost in the Shell" star is ready to end her marriage with Dauriac by filing for a divorce, which many believe will lead to a custody battle over their 3-year-old daughter, Rose Dorothy Dauriac. Johansson and Dauriac started dating in 2012. They eventually became an item, got engaged in 2013 and tied the knot on Oct. 1, 2014, after the "Avengers" star gave birth to their daughter. Unfortunately, two years after Johansson and Dauriac tied the knot, the couple split, US Weekly reported. The pair had been very private when it came to their relationship.

Knowledge bases of real-world facts about entities and their relationships are useful resources for a variety of natural language processing tasks. However, because knowledge bases are typically incomplete, it is useful to be able to perform link prediction or knowledge base completion, i.e., predict whether a relationship not in the knowledge base is likely to be true. This paper combines insights from several previous link prediction models into a new embedding model STransE that represents each entity as a low-dimensional vector, and each relation by two matrices and a translation vector. STransE is a simple combination of the SE and TransE models, but it obtains better link prediction performance on two benchmark datasets than previous embedding models. Thus, STransE can serve as a new baseline for the more complex models in the link prediction task.

Artificial intelligence experts point to looming danger amid unpredictable technology and fears that technology could'seduce us into warfare' Experts in artificial intelligence, lawyers and activists organized by the Campaign to Stop Killer Robots gathered at the United Nations on Tuesday to warn against a growing reliance on cheap drones and "stupid AI" that can be unpredictable in the real world. "Terminator always comes up," Toby Walsh, a professor of artificial intelligence at the University of New South Wales, told reporters on Tuesday, referring to the sci-fi cyborg on a mission to wipe out mankind. "But it's not really Terminator that we're worried about at the moment. I think that Terminator is perhaps 50 or so years away." But there are concerning technologies "only a few years, at best, away", Walsh said, and with semi-autonomous systems, such as drones, "it would take very little to remove the human from that loop and replace them with a computer".

Nearly two-thirds of consumers are worried about home IoT devices listening in on their conversations, according to a Gartner survey released Monday. Those jitters aren't too surprising after recent news items about TV announcers inadvertently activating viewers' Amazon Echos, or about data from digital assistants being used as evidence in criminal trials. But privacy concerns are just one hurdle smart homes still have to overcome, according to the survey. In fact, Gartner found that most consumers don't feel they need what smart homes offer. Consumer IoT is still in an early-adopter phase, Gartner concluded from the online survey, which was conducted in the second half of last year in the U.S., U.K., and Australia.

We spoke to The Daily Beast to help make sense of ISIL's growing use of armed consumer drones in the conflict in Syria and Iraq. Meanwhile, we assisted The Verge in confirming that the jail sentence given to a Seattle man for crashing his drone during a parade was in fact unprecedented in the history of U.S. domestic drone use. A suspected U.S. drone strike in Pakistan killed two individuals near the border of Afghanistan. If confirmed, it would be the first U.S. drone strike in Pakistan under the Trump administration. The U.S. launched over 20 airstrikes in Yemen, targeting al-Qaeda in the Arab Peninsula.

Science fiction has long been obsessed with the idea of alien life forms and how they may appear. Over the years we have seen little green men, bug-eyed monsters and predatory killers take to the silver and smaller screens to represent our idea of life from outer space. But scientific fact may hold the key to a more realistic depiction of creatures and plants which have adapted to meet the harsh challenges of alien worlds. In the hunt for extra-terrestrial life, astronomers often try to find Earth-sized planets in what is called the'habitable zone' of their host star. This means they are orbiting at the correct distance for liquid water to exist on the planet.

In my last blog, I discussed how digital complacency could put your business at risk and how technological change is fast outpacing businesses' ability to adapt. This trend continues its relentless pursuit to consume those who choose to answer today's questions with yesterday's thinking. Furthermore, yet another transformational technology is now redefining the industry, and it has the potential to change everything. Machine learning is a type of artificial intelligence (AI) that provides computers with the ability to learn without being explicitly programmed. Machine learning focuses on the development of computer programs that can teach themselves to grow and change when exposed to new data.

Peter Shulman, an associate history professor at Case Western Reserve University in Ohio, was lecturing on the reemergence of the Ku Klux Klan in the 1920s when a student asked an odd question: Was President Warren Harding a member of the KKK? He confessed that he was not aware of that allegation, but that Harding had been in favor of anti-lynching legislation, so it seemed unlikely. But then a second student pulled out his phone and announced that yes, Harding had been a Klan member, and so had four other presidents. For most of its history, Google did not answer questions. Users typed in what they were looking for and got a list of web pages that might contain the desired information.