Parent Interventions: Children Conceived After Short Duration of Marriage At Risk of Schizophrenia  |  Parent Interventions: Babbling Help Babies In Language Development  |  Technology Inceptions: Tissue Chips in Space Program To Help in Disease Research  |  Science Innovations: Aerospace material from polymer  |  Science Innovations: Way to boost drug potency  |  Teacher Insights: Short Rest Intervals Help May Improve Memory and Learning  |  Parent Interventions: Constipation In Children May be Caused by Difference in Sensory Processing  |  Teacher Insights: Sibling bullying more in large families  |  Teacher Insights: Low earnings related to inattention at KG   |  Science Innovations: Bio-alternative to plastics  |  Science Innovations: Horseshoe crabs relatedto spiders   |  Teacher Insights: Young Children Can Understand the Facial Gestures of Adults  |  Parent Interventions: Alarming Rise in Kids Swallowing Foreign Objects   |  Teacher Insights: Neurofeedback Training Can Improve Learning, Control of Body Movements  |  Parent Interventions: Sleep Myths May Lead to Poor Sleep Habits and Health  |  
  • Pallikkutam Magazine
  • Companion Magazine
  • Mentor
  • Smart Board
  • Pallikkutam Publications

November 13, 2018 Tuesday 11:17:54 AM IST
Alexa and Siri may in future learn language as kids do!

Researchers of Massachusetts Institute of Technology have developed a “semantic parser” that learns through observation to more closely mimic a child’s language-acquisition process.

Have you observed how children learn language? They learn by observing their environment, listening to the people around them, and connecting the dots between what they see and hear. This is how children establish their language's word order, such as where subjects and verbs fall in a sentence.

In the world of computing, learning language is the task of syntactic and semantic parsers. Parsers are becoming increasingly important for web searches, natural-language database querying, and voice-recognition systems such as Alexa and Siri.

MIT researchers have developed a parser that learns through observation to more closely mimic a child's language-acquisition process, which could greatly extend the parser's capabilities. To learn the structure of language, the parser observes captioned videos, with no other information, and associates the words with recorded objects and actions.

"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," suggest the researchers.

In the future, the parser could be used to improve natural interaction between humans and personal robots.

Source: http://news.mit.edu/2018/machines-learn-language-human-interaction-1031

Comments