Is this natural language?

The partner provides software that uses natural language processing techniques to store and analyze documents of different firms. This includes their widely used smart document storage software. The techniques suffer performance when they use text that is not written in well-formed “natural language”, such as tables and labels. The intern will be designing and implementing a model to classify given text as being well-formed or not. The model will then be included in existing software to detect if given text is well-formed or not and the text that is not well-formed will not be considered. This should improve the performance of existing software and future software that analyze text.

Faculty Supervisor:

Milton King

Student:

Partner:

M-Files Canada Inc.

Discipline:

Computer science

Sector:

Professional, scientific and technical services

University:

St. Francis Xavier University

Program: