Accurate neural models are much less efficient than non-neural models and are useless for processing billions of social media posts or handling user queries in real time with a limited budget. This study revisits the fastest pattern-based NLP methods to make them as accurate as possible, thus yielding a strikingly simple yet surprisingly accurate morphological analyzer for Japanese. The proposed method induces reliable patterns from a morphological dictionary and annotated data. Experimental results on two standard datasets confirm that the method exhibits comparable accuracy to learning-based baselines, while boasting a remarkable throughput of over 1,000,000 sentences per second on a single modern CPU. The source code is available at https://www.tkl.iis.u-tokyo.ac.jp/~ynaga/jagger/

The Rolling Stones' Mick Jagger is famous for his hip-snaking sorcery on stage, but the lead singer may have been shown up by Boston Dynamic robot'Spot' in a new video. To celebrate the 40th anniversary of the British band's'Tattoo You' album, Boston Dynamics' engineers taught Spot to dance and lip-sync like Jagger in the'Start Me Up' music video. The company also trained three other Spot robots to recreate the moves of fellow band members Keith Richards, Ronnie Wood and Charlie Watts. During the video, the lead Spot moves its long neck to mimic the motions Jagger makes with his arms and the robot also opens its mouth to lip-sync along with the Rockstar. The Rolling Stones' Mick Jagger is famous for his hip-snaking sorcery on stage, but the lead singer may have been shown up by Boston Dynamic robot'Spot' in a new video The veteran British band first began performing in 1962 and are the first to score a number one album on the British charts across six different decades.

The last time we saw Spot dance, it was with the entire Boston Dynamics family at the end of last year. That was mostly a showcase of how much Atlas, the company's bipedal robot, had come from the days when it could barely walk. In a new solo display, we get to see it move to "Start Me Up" from The Rolling Stones in honor of the 40th anniversary of their 1981 album Tattoo You. And if you thought Spot dancing was too close to the uncanny valley, wait until you see it lip-sync. It is truly the stuff of nightmare fuel.

Nvidia's research team has just developed a new AI that can use an existing video and just one image to make the person in the image imitate moves from the video. Technically, the method known as video-to-video synthesis takes an input video like a segmentation mask or human poses to turn it into a photorealistic video using an image. The research team said there are two major problems with the current set of AI models trying to achieve the same: First, these models need a trove of target images to turn them into a video. And second, the capability of these models to generalize the output is limited. To overcome these obstacles, researchers trained a new model that learns to generate videos of previously unseen humans or scenes – images that weren't present in the training dataset – using just a few images of them.