Testing an algorithm to determine semantic distance between words

Submitter and Co-author information

Rory A. Sutcliffe, University of WindsorFollow

Standing

Undergraduate

Type of Proposal

Visual Presentation (Poster, Installation, Demonstration)

Faculty

Faculty of Science

Faculty Sponsor

Chitra Rangan

Proposal

A computer algorithm that can calculate the semantic distance between words is being used extensively in Psychology. In one application, it is used to determine the difference in word meanings as perceived by a person with brain injury or disease versus a "normal" person, for non-invasive diagnosis of impairment. This algorithm was developed using a relatively small sample of human language, i.e., about half a million words. We have developed prototype algorithms that reproduce the earlier results for these small bodies of work. In this project, we are testing this algorithm for a large body of work (corpus) that contains billions of words. This test will enable us to see if the computer algorithms scale for large fractions of human language.

Location

University of Windsor

Grand Challenges

Healthy Great Lakes

Share

COinS
 

Testing an algorithm to determine semantic distance between words

University of Windsor

A computer algorithm that can calculate the semantic distance between words is being used extensively in Psychology. In one application, it is used to determine the difference in word meanings as perceived by a person with brain injury or disease versus a "normal" person, for non-invasive diagnosis of impairment. This algorithm was developed using a relatively small sample of human language, i.e., about half a million words. We have developed prototype algorithms that reproduce the earlier results for these small bodies of work. In this project, we are testing this algorithm for a large body of work (corpus) that contains billions of words. This test will enable us to see if the computer algorithms scale for large fractions of human language.