Children learn language by observing the things around them and connecting the dots between what they are seeing and hearing. By learning language like this, they are able to establish a language’s word order, such as where subjects and verbs belong in a sentence.In machine learning, languages are learned by training systems on sentences annotated by humans that describe the structure and meaning of words. Gathering that annotation data can be time-consuming and practically impossible for less common languages. Furthermore, not all humans agree on annotations, and annotations might not accurately reflect how people naturally speak.This week, MIT researchers presented a paper describing a new parser that learns the way a child does. The parser observes captioned videos and associates words with recorded objects and actions. When provided a new sentence, the parser can then use what it learned about the language structure to predict a sentence’s meaning without the accompanying video.This approach is “weakly supervised,” meaning that it requires limited training data. According to the researchers, the approach could expand data types and reduce the effort required for training parsers.The researchers also believe that this parser could be used to make interactions between humans and personal robots more natural. “People talk to each other in partial sentences, run-on thoughts, and jumbled language. You want a robot in your home that will adapt to their particular way of speaking… and still figure out what they mean,” said Andrei Barbu, co-author of the paper and a researcher in the Computer Science and Artificial Intelligence Laboratory (CSAIL) and the Center for Brains, Minds, and Machines (CBMM) within MIT’s McGovern Institute.In the future, the researchers plan to look into modeling interactions as opposed to just passive observations, the researchers explained.
Tommy Pickles and his crew are about to make their way to the silver screen in a big way in a Paramount Players-produced live-action/CG hybrid Rugrats movie. THR has revealed that Diary of a Wimpy Kid director David Bowers has been tapped to direct the forthcoming Rugrats feature. While little is known about the project, it’s expected that the babies in this film will be CG creations. Also, the initial cartoon ran for nine seasons from 1991 to 2000 and spawned three movies and a sequel series called All Grown Up!. The property was created by Arlene Klasky, Gábor Csupò, and Paul Germain. In total, the main series ran for 172 episodes while All Grown Up! ended up airing 55 episodes before wrapping up its run in 2008. Rugrats tallied four Daytime Emmy wins and six Kids’ Choice Awards. Paramount’s plan for a live-action Rugrats film was first announced nearly three years ago, when it was also revealed that Paramount and Nickelodeon would team to revive the popular cartoon with a 26-episode order. Bowers’ hiring marks the first official hiring since that initial announcement. Lastly, the live-action Rugrats film is slated to hit theaters on Jan. 29, 2021. Source: CBR