A desirable property of learning systems is to be both effective and interpretable. Towards this goal, recent models have been proposed that first generate an extractive explanation from the input text and then generate a prediction on just the explanation called explain-then-predict models. These models primarily consider the task input as a supervision signal in learning an extractive explanation and do not effectively integrate rationales data as an additional inductive bias to improve task performance. We propose a novel yet simple approach ExPred, that uses multi-task learning in the explanation generation phase effectively trading-off explanation and prediction losses. And then we use another prediction network on just the extracted explanations for optimizing the task performance. We conduct an extensive evaluation of our approach on three diverse language datasets -- fact verification, sentiment classification, and QA -- and find that we substantially outperform existing approaches.

An artist can draw a baby daikon radish wearing a tutu and walking a dog, even if they've never seen one before. But this kind of visual mashup has long been a trickier task for computers. Now, a new artificial-intelligence model can create such images with clarity -- and cuteness. This week nonprofit research company OpenAI released DALL-E, which can generate a slew of impressive-looking, often surrealistic images from written prompts such as "an armchair in the shape of an avocado" or "a painting of a capybara sitting in a field at sunrise." (And yes, the name DALL-E is a portmanteau referencing surrealist artist Salvador Dalí and animated sci-fi film "WALL-E.") A new AI model from OpenAI, DALL-E, can create pictures from the text prompt "an illustration of a baby daikon radish in a tutu walking a dog".

You are speaking to a grid of black squares. One of the black squares gets a text notification. One of the black squares is today replaced by an image of a naked mole rat. None of the black squares will tell you what they found interesting in the reading. The time has come to adopt the newest learning tool, Floobaroom.

OAKLAND, California – More than 225 Google engineers and other workers have formed a union, the group revealed Monday, capping years of growing activism at one of the world's largest companies and presenting a rare beachhead for labor organizers in staunchly anti-union Silicon Valley. The union's creation is highly unusual for the tech industry, which has long resisted efforts to organize its largely white-collar workforce. It follows increasing demands by employees at Google for policy overhauls on pay, harassment and ethics, and is likely to escalate tensions with top leadership. The new union, called the Alphabet Workers Union after Google's parent company, Alphabet, was organized in secret for the better part of a year and elected its leadership last month. The group is affiliated with the Communications Workers of America, a union that represents workers in telecommunications and media in the United States and Canada.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. The Navy is getting into drones in a big way, with new plans to add 21 unmanned surface and underwater vessels over the next five years. The Navy just released its 30-year shipbuilding plan, which reflects a growing emphasis on the use of drones in maritime combat. Between now and 2026, the Navy aims to acquire 12 large unmanned surface vessels, one medium unmanned surface vessel and 8 extra-large unmanned underwater vessels, according to the plan.

This week we are reprinting our top stories of 2020. This article first appeared online in our "Maps" issue in January, 2020. On a chilly evening last fall, I stared into nothingness out of the floor-to-ceiling windows in my office on the outskirts of Harvard's campus. As a purplish-red sun set, I sat brooding over my dataset on rat brains. I thought of the cold windowless rooms in downtown Boston, home to Harvard's high-performance computing center, where computer servers were holding on to a precious 48 terabytes of my data. I have recorded the 13 trillion numbers in this dataset as part of my Ph.D. experiments, asking how the visual parts of the rat brain respond to movement. Printed on paper, the dataset would fill 116 billion pages, double-spaced. When I recently finished writing the story of my data, the magnum opus fit on fewer than two dozen printed pages. Performing the experiments turned out to be the easy part.

Washington – The United States added dozens of Chinese companies, including the country's top chipmaker SMIC and Chinese drone manufacturer SZ DJI Technology Co. Ltd., to a trade blacklist on Friday as U.S. President Donald Trump's administration ratchets up tensions with China in his final weeks in office. Reuters first reported the addition of SMIC and other companies earlier on Friday. The move is seen as the latest in Republican Trump's efforts to burnish his tough-on-China image as part of lengthy fight between Washington and Beijing over trade and numerous economic issues. The U.S. Commerce Department said the action against SMIC stems from Beijing's efforts to harness civilian technologies for military purposes and evidence of activities between SMIC and Chinese military industrial companies of concern. The Commerce Department will "not allow advanced U.S. technology to help build the military of an increasingly belligerent adversary," Secretary Wilbur Ross said in a statement.

Researchers are aiming to "teach" a computer to recognize the sounds of resident killer whales in order to develop a warning system for preventing ships from fatally striking endangered orcas off British Columbia's coast. Steven Bergner, a computing science research associate at Simon Fraser University's Big Data Hub, said he is collecting and managing a database of sounds picked up 24 hours a day by a network of hydrophones in the Salish Sea. Marine biologists will identify the sounds of different species of whales, including humpbacks and transients, and differentiate the acoustics from other noise such as waves and boats, he said. Machine learning or artificial intelligence would help detect the presence of orcas through patterns in the data. "That (information) goes through another system that then decides whether there should be a warning that ultimately reaches the vessel pilots," Bergner said.

As countries look towards re-opening of economic activities amidst the ongoing COVID-19 pandemic, ensuring public health has been challenging. While contact tracing only aims to track past activities of infected users, one path to safe reopening is to develop reliable spatiotemporal risk scores to indicate the propensity of the disease. Existing works which aim to develop risk scores either rely on compartmental model-based reproduction numbers (which assume uniform population mixing) or develop coarse-grain spatial scores based on reproduction number (R0) and macro-level density-based mobility statistics. Instead, in this paper, we develop a Hawkes process-based technique to assign relatively fine-grain spatial and temporal risk scores by leveraging high-resolution mobility data based on cell-phone originated location signals. While COVID-19 risk scores also depend on a number of factors specific to an individual, including demography and existing medical conditions, the primary mode of disease transmission is via physical proximity and contact. Therefore, we focus on developing risk scores based on location density and mobility behaviour. We demonstrate the efficacy of the developed risk scores via simulation based on real-world mobility data. Our results show that fine-grain spatiotemporal risk scores based on high-resolution mobility data can provide useful insights and facilitate safe re-opening.

Cyberpunk--the genre, not just the video game--is back. Altered Carbon and Westworld were hits, there's a new Matrix movie in the works, and Cyberpunk 2077 is poised to be the year's most successful, and most hyped, video game. For Mike Pondsmith, one of the genre's founding fathers, it all makes perfect sense. In the world of cyberpunk, technology has the ability to create miracles, people are struggling for power, the future is uncertain, and corporations have the power of gods. "We have a more cyberpunk world than ever before," Pondsmith says.