New algorithm found for learning languages

September 6, 2005

Cornell University and Tel Aviv University researchers say they've developed a method for enabling a computer program to learn languages.

The researchers said the algorithm they've formulated allows a computer to scan text in many languages, including English and Chinese, and autonomously and without previous information infer the underlying rules of grammar.

The rules can then be used to generate new and meaningful sentences, they said. The method also works for such data as sheet music or protein sequences.

"The algorithm -- the computational method -- for language learning and processing that we have developed can take a body of text, abstract from it a collection of recurring patterns or rules and then generate new material," explained Shimon Edelman, a computer scientist and professor of psychology at Cornell.

"This is the first time an unsupervised algorithm is shown capable of learning complex syntax, generating grammatical new sentences and proving useful in other fields that call for structure discovery from raw data, such as bioinformatics," he said.

The study appears in the Proceedings of the National Academy of Sciences.

Copyright 2005 by United Press International

Explore further: New method peeks inside the 'black box' of artificial intelligence

Related Stories

Machines that learn language more like kids do

October 31, 2018

Children learn language by observing their environment, listening to the people around them, and connecting the dots between what they see and hear. Among other things, this helps children establish their language's word ...

A new molecular programming language: CRN++

October 5, 2018

Synthetic biology is a relatively new area of research that could significantly impact a number of fields, including biology, nanofabrication and medicine. A primary challenge in this emerging field is that of embedding computation ...

Scientists improve deep learning method for neural networks

August 17, 2018

Researchers from the Institute of Cyber Intelligence Systems at the National Research Nuclear University MEPhI (Russia) have recently developed a new learning model for the restricted Boltzmann machine (a neural network), ...

Recommended for you

Carbon goes with the flow

November 13, 2018

Many people see the carbon cycle as vertical—CO2 moving up and down between soil, plants and the atmosphere.

Visualizing 'unfurling' microtubule growth

November 13, 2018

Living cells depend absolutely on tubulin, a protein that forms hollow tube-like polymers, called microtubules, that form scaffolding for moving materials inside the cell. Tubulin-based microtubule scaffolding allows cells ...

DNA structure impacts rate and accuracy of DNA synthesis

November 13, 2018

The speed and error rate of DNA synthesis is influenced by the three-dimensional structure of the DNA. Using "third-generation" genome-wide DNA sequencing data, a team of researchers from Penn State and the Czech Academy ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.