[NetEase smart news August 25 news] Recently, Disney researchers are developing some compelling new technologies, including real-time voice animation, shared augmented reality technology and some horrible live performance technology. Researchers at Disney and the Boston University of Massachusetts are now working on neural networks that can assess short stories. Although these artificial intelligences (so far) have not been able to analyze stories like professional literary critics, the software attempts to predict which stories are most popular. "Our neural network has achieved some success in predicting the popularity of the story," Disney research scientist Boyang "Albert" Li said in a statement. "You can't use them yet to pick winners for your local writing competition, but they can be used as a guide for future research."
Researchers used a large database on Quora, a social networking site, to enter artificial intelligence algorithms. Many of Quora’s answers come in the form of stories, so readers’ votes can be used as a measure of popularity and as “a manifestation of narrative quality.†The research team collected nearly 55,000 answers and classified more than 28,000 of them as stories, each with an average of 369 words. Then they developed several different neural networks - one to look at different parts of each story and the other to have a more complete understanding of the meaning of the story. Each AI predicts the relative popularity of a given story. Both neural networks are more suitable for determining the popularity of a story than textual baseline assessments, but the overall network shows an 18% advantage over a chapter-focused network.
Of course, it's not hard to imagine that movie companies will use future versions of this technology to select scripts for their products, but this technology is still in its infancy. We hope that researchers can find a way to judge the quality of the story, not just the popularity. No one wants another Transformers movie.
(Selected from: engadget Translation: Netease see the smart editor robot review: Li Muzhen)
2.0 Rgb Computer Speakers,Rgb Light 2.0 Channel Speaker,Knob Control Function 2.0 Speaker,Rgb Without Bluetooth Speaker
Comcn Electronics Limited , https://www.comencnspeaker.com