Connor MacLean

Use of NLP techniques to define an "Innovation Index" dedicated to evaluating startups in the energy sector.

Data and Corpora Generation:

-Participate in the realization of a 3D design automation project (CAD) based on user queries (text)
-Generation of large synthetic corpora of queries in CAD software
-Generation of large corpora using web-scraping (JavaScript, Selenium, BeautifulSoup, Scrapy)
-Creation of testing interfaces to recuperate realistic user requests

Machine/Deep Learning:

-Training

Conversion of PDF documents to XML following the TEI P5 standard

Creation of scripts in Python to mark page and paragraph boundaries

Use of Linux modules for Optical Character Recognition (OCR)

Training Machine Learning (ML) models in spaCy and Flair to automatically attribute grammatical category (POS-Tagging)

Managing multiple projects concurrently with often short deadlines

Distributing new projects to the translation team

Formatting previous project files in order to update the translation database

Delivering projects and communicating with French-speaking and English-speaking clients

Used product knowledge to organize meetings between clients and sales representatives in Quebec, Alberta, Manitoba, Saskatchewan, and British Columbia

Organized and executed email campaigns related to specific products

Planned and organized client-focused events

Administrative paperwork

Summarizing French and English articles in English as well as correcting English grammar written by non-native speakers

Organizing and compiling bibliographical entries related to the research

Double major in Linguistics and French with a focus on translation-based courses