Goto

Collaborating Authors

Results


SynSetExpan: An Iterative Framework for Joint Entity Set Expansion and Synonym Discovery

arXiv.org Artificial Intelligence

Entity set expansion and synonym discovery are two critical NLP tasks. Previous studies accomplish them separately, without exploring their interdependencies. In this work, we hypothesize that these two tasks are tightly coupled because two synonymous entities tend to have similar likelihoods of belonging to various semantic classes. This motivates us to design SynSetExpan, a novel framework that enables two tasks to mutually enhance each other. SynSetExpan uses a synonym discovery model to include popular entities' infrequent synonyms into the set, which boosts the set expansion recall. Meanwhile, the set expansion model, being able to determine whether an entity belongs to a semantic class, can generate pseudo training data to fine-tune the synonym discovery model towards better accuracy. To facilitate the research on studying the interplays of these two tasks, we create the first large-scale Synonym-Enhanced Set Expansion (SE2) dataset via crowdsourcing. Extensive experiments on the SE2 dataset and previous benchmarks demonstrate the effectiveness of SynSetExpan for both entity set expansion and synonym discovery tasks.


Researchers Use AI to Spot Drone Pilots

#artificialintelligence

Law enforcement and military personnel might finally have a way to track malicious drones and prevent millions of dollars in damage thanks to new artificial intelligence research. Academics at Israel's Ben-Gurion University of the Negev have developed a way to locate the operator of a drone by looking at how the airborne vehicle moves. Locating the pilots of malicious drones is a pressing issue. In December 2018, Gatwick Airport had to close its runways to avoid drones flying dangerously close. Officers believed that it was a deliberate attack on the airport.


Researchers Use AI to Spot Drone Pilots

#artificialintelligence

Law enforcement and military personnel might finally have a way to track malicious drones and prevent millions of dollars in damage thanks to new artificial intelligence research. Academics at Israel's Ben-Gurion University of the Negev have developed a way to locate the operator of a drone by looking at how the airborne vehicle moves. Locating the pilots of malicious drones is a pressing issue. In December 2018, Gatwick Airport had to close its runways to avoid drones flying dangerously close. Officers believed that it was a deliberate attack on the airport.


Improving predictions by nonlinear regression models from outlying input data

arXiv.org Machine Learning

When applying machine learning/statistical methods to the environmental sciences, nonlinear regression (NLR) models often perform only slightly better and occasionally worse than linear regression (LR). The proposed reason for this conundrum is that NLR models can give predictions much worse than LR when given input data which lie outside the domain used in model training. Continuous unbounded variables are widely used in environmental sciences, whence not uncommon for new input data to lie far outside the training domain. For six environmental datasets, inputs in the test data were classified as "outliers" and "non-outliers" based on the Mahalanobis distance from the training input data. The prediction scores (mean absolute error, Spearman correlation) showed NLR to outperform LR for the non-outliers, but often underperform LR for the outliers. An approach based on Occam's Razor (OR) was proposed, where linear extrapolation was used instead of nonlinear extrapolation for the outliers. The linear extrapolation to the outlier domain was based on the NLR model within the non-outlier domain. This NLR$_{\mathrm{OR}}$ approach reduced occurrences of very poor extrapolation by NLR, and it tended to outperform NLR and LR for the outliers. In conclusion, input test data should be screened for outliers. For outliers, the unreliable NLR predictions can be replaced by NLR$_{\mathrm{OR}}$ or LR predictions, or by issuing a "no reliable prediction" warning.


ANA starts testing autonomous bus operation at Haneda Airport

The Japan Times

ANA Holdings Inc., the operator of All Nippon Airways Co., said Wednesday it has started testing a semi-autonomous bus that will transport passengers and staff working at Tokyo's Haneda Airport. The company will conduct the test with the electric bus capable of carrying 57 passengers on a 1.9-kilometer route through the end of this month, aiming to start trial operation later in the year. The vehicle, with level-3 automation, allows drivers to turn their attention away from driving and engage in different tasks. "As the Tokyo Olympics are approaching, we hope more passengers from around the world will see our latest technology," ANA Senior Executive Vice President Shinzo Shimizu said in a ceremony at the airport. In 2018, the number of passengers who arrived at and departed from the airport increased 2.1 percent to 85 million, according to Japan Airport Terminal Co. which manages the Haneda Airport facilities.


Airlines avoid Iran and Iraq airspace

The Japan Times

PARIS – Several international airlines said Wednesday they would avoid Iranian and Iraqi airspace after Tehran fired ballistic missiles at bases housing U.S. troops in Iraq. Lufthansa and its Austrian Airlines unit nonetheless decided to maintain flights to the Iranian capital, Tehran, this week, a statement said. Iran launched more than 20 missiles at bases housing U.S. troops in the early hours, officials in Washington and Tehran said. Iran's supreme leader called the attacks a "slap in the face" after a U.S. drone strike killed Iranian military commander Qassem Soleimani near Baghdad international airport last week. In Germany, Lufthansa said it had halted overflights of Iran and Iraq until further notice.


The Amazing Ways Dubai Airport Uses Artificial Intelligence

#artificialintelligence

As one of the world's busiest airports, (ranked No. 3 in 2018 according to Airports Council International's world traffic report), Dubai International Airport is also a leader in using artificial intelligence (AI). In fact, the United Arab Emirates (UAE) leads the Arab world with its adoption of artificial intelligence in other sectors and areas of life and has a government that prioritizes artificial intelligence including an AI strategy and Ministry of Artificial Intelligence with a mandate to invest in technologies and AI tools. The Emirates Ministry of the Interior said that by 2020, immigration officers would no longer be needed in the UAE. They will be replaced by artificial intelligence. The plan is to have people just walk through an AI-powered security system to be scanned without taking off shoes or belts or emptying pockets.


The Rise of Smart Airports: A Skift Deep Dive

#artificialintelligence

In late September, Beijing unveiled to the world Daxing, a glimmering $11 billion airport showcasing technologies such as robots and facial recognition scanners that many other airports worldwide are either adopting or are now considering. Daxing fits the description of what experts hail as a "smart airport." Just as a smart home is where internet-connected devices control functions like security and thermostats, smart airports use cloud-based technologies to simplify and improve services. Of course, many of the nearly 4,000 scheduled service airports across the world are still embarrassingly antiquated. The good news for aviation is that more facilities are investing, finally, to better serve airlines, suppliers, and travelers. This year, airports worldwide will spend $11.8 billion -- 68 percent more than the level three years ago -- on information technology, according to an estimate published this month by SITA (Société Internationale de Telecommunications Aeronautiques, an airline-owned tech provider). A few trends are driving the rise of smart airports. Flight volumes are increasing, so airports need better ways to process flyers. Airports need better ways to make money, too, by encouraging passengers to spend more in their shops and restaurants. Data is growing in importance. Everything happening at an airport, from where passengers are flowing to which items are selling in stores, generates data. Airports can analyze this data to spot opportunities for eking out fatter profits. They can sell the data to third-parties as well.


Self-driving wheelchairs tested at Haneda Airport

The Japan Times

Trials have begun at Haneda Airport in Tokyo on next-generation self-driving electric wheelchairs to help elderly and other people get to boarding gates more easily. Japan Airlines aims to start using self-driving wheelchairs as early as the business year that starts next April. Currently, JAL offers manual wheelchairs at airports across the country. The self-driving wheelchairs JAL aims to introduce are designed to allow users to move without any escort. They automatically return to their home positions after use, making it unnecessary for workers to go and collect them.


MultiBrief: Will convenience outweigh privacy when it comes to using facial recognition in public?

#artificialintelligence

Facial recognition technology is convenient. Many of us use it numerous times a day to unlock our smartphones. Although people often access their phones with Face ID or fingerprints, many still worry about their privacy when their biometric data are used in the public space. There is a fine line between consensual identity verification and non-consensual surveillance. Delta Airlines opened the nation's first biometric terminal at Atlanta's Hartsfield Jackson International Airport (ATL) in November 2018.