Natural language understanding and generation

NLP techniques have been used and tested for several years in different environments and for different applications/domains. The performances of the Natural Language Understanding (NLU) toolbox are closely related to the quality of the text but also on the specific knowledge-domain. Social Media content typically use short sentences with simple grammar and tend to include specific jargon and abbreviations. Grammatical rules are not always respected and spelling errors are common. These characteristics are also common to the human generated military intelligence/tactical reports. The first objective of the project is to automatically generate “human-like” reports, in both French and English, based on “structured-data”. The second objective of this project is to create a knowledge extraction toolbox to be used with both social media reports and military intelligence reports (for both French and English).

Faculty Supervisor:

Timothy J. O’Donnell

Student:

Wilfred Tat Fai Yau

Partner:

Thales Canada Inc.

Discipline:

Languages and linguistics

Sector:

Information and communications technologies

University:

McGill University