With the rise of ChatGPT, for their Advanced Corpus Linguistics course, a group of MDS Computational Linguistics students wanted to develop a model that can distinguish between human text and A.I. generated text.
Female Participation in Jane Austen Novels | Student Data Science Project
For their Advanced Corpus Linguistics project, a group of MDS Computational Linguistics students wanted to apply the Bechdel Test to the works of Jane Austen.
Looking for a way to improve the conjugation tool for nouns and verbs within various Indigenous languages, such as Ojibwe, CultureFoundry turned to a group of UBC Master of Data Science (MDS) Computational Linguistics students, who created an Ojibwe conjugator and API (Application Programming Interface) to tackle this task. This tool will allow language learners to smoothly and efficiently navigate the many possible forms each word can take, giving them greater authority and confidence in building their language skills.
Analyzing Psychological Distress and Mental Well-Being in Canadian Post-Secondary Students Throughout COVID-19 | Student Capstone Project
The Canadian Campus of Wellbeing Survey (CCWS) wanted to explore the effects of the pandemic on Canadian post-secondary students, in particular on vulnerable learning groups (e.g., learners with disabilities, and racialized learners). The CCWS teamed up with a group of UBC Master of Data Science (MDS) Vancouver students to explore the impact of the pandemic on students’ mental well-being.
Sitewise Analytics, a Software-as-a-Service company, specializing in developing site forecast models, sales impact assessments, and actionable market strategy plans for leading restaurant, retail, real estate, and healthcare chains, partnered with Master of Data Science (MDS) Vancouver students to understand which specific factors drive success (and failure) for certain restaurant brands.
As part of their Advanced Corpus Linguistics project, four MDS Computational Linguistics students wanted to investigate the specific emotion in Goodreads book reviews.
For their Advanced Corpus Linguistics project, a group of MDS Computational Linguistics students decided to track all the spells mentioned in the Harry Potter book series.
A group of MDS Computational Linguistics alumni contributed to an article that centered around automatic speech recognition for non-native English with transfer learning.
In the past, Statistics Canada developed network accessibility measures based on the distance of driving and walking to compute proximity scores for various types of amenities. However, the importance of public transit as a primary mode of travel has not been included and accessibility measures based on time using transit have never been incorporated into proximity scores.
A team of UBC MDS Vancouver students worked with Biba, a smart playground company, to build several learning models in order to estimate the number of monthly sessions at particular playgrounds within a given month. Data was collected from 2506 playgrounds across the US to help understand how playgrounds are being used in order for park managers to make meaningful decisions regarding the management of existing playgrounds and the planning of new playgrounds.
In partnership with Urban Logiq, an organization that helps governments worldwide make faster, cheaper and more accurate decisions with their data, a group of MDS Vancouver students collected data from GPS-enabled vehicles in a specific city of interest and created two sets of visualization tools, which they used to help answer two questions: How far does someone need to travel to reach an amenity? And are certain nearby amenities being bypassed in favour of others?
Working with E-Comm 9-1-1—a multi-municipality emergency communications agency serving British Columbia—UBC Master of Data Science students looked at how the agency’s existing data could be used to create call-taking and dispatch schedules that would correspond with shifting call volumes based on time of day, day of week, and holidays or special events throughout the year.
In partnership with QxMD—a Vancouver-based digital learning technology company—students from UBC’s Master of Data Science program created a tool to identify trending health topics within news articles and match these with relevant medical journal articles. Thus helping medical professionals better serve patients with questions related to specific news articles they’ve read.
Students of UBC’s Master of Data Science program in Vancouver worked with Fresh Prep to design a dashboard tool that not only helped the meal kit delivery company predict its future orders but also provided the insights needed to help Fresh Prep better serve its existing customers and improve their order rate.
Students from UBC’s Master of Data Science program worked with banking software company, Finn Ai, to pinpoint areas for improvement in the way their conversational assistants understand and respond to customer needs.
Working with Coast Mountain Bus Company, students from UBC’s Master of Data Science program designed a forecasting tool using bus route data to create more accurate schedules for TransLink’s largest operating company.
Data scientists are having a positive impact in the medical field – in ways never dreamed possible. Using a new automated RNA analysis platform that conducts biomarker blood tests, data scientists can monitor and treat heart transplant patients with a simple blood test instead of invasive biopsies.
Data analysis of over 160,000 employees from 31 companies revealed a key piece of information that could be used to help companies and policy makers close the gender wage gap.
In response to natural disasters, data scientists are applying machine learning algorithms to Twitter feeds in real time to help relief teams efficiently map disasters.
A group of MDS Computational Linguistics alumni contributed to an article that centered around automatic speech recognition for non-native English with transfer learning.
During his time at Bethesda, Maryland-based National Institutes of Health, Nicholas Sanders, MDS Computational Linguistics Alumnus, Class of 2021, worked on a model deployed on an internal NIH website for staff to input a given grant application and receive PAC/PO recommendations.
Working with Seattle-based AI start-up, Seasalt.ai, students from UBC’s Master of Data Science in Computational Linguistics program created a universal NER (Named Entity Recognition) system that applied transfer learning from high-resource language datasets to low-resource languages. This allowed crucial information to be extracted from previously underrepresented languages, like Indonesian, Javanese, Malay, Vietnamese, Tagalog, Croatian, and Czech, for use across a variety of Natural Language Processing tasks.
As a result of a question posed by UBC Linguistics and French, Hispanic, and Italian Studies faculty, a group of UBC MDS Computational Linguistics students embarked on the first phase of a project that could improve graded readers for any language. The capstone project focused on A1, A2, and B level documents for the Spanish language, but it laid the foundation for the creation of a universal reader.
Ilana Zimmerman, MDS Computational Linguistics Alumna (Class of 2020) was tasked to create a search engine based on two transformer models in her role as a Natural Language Processing Engineer with ALEX - Alternative Experts. ALEX is an ISO 9001:2015-certified solutions provider to Government, Defense, and Commercial contracts, based in Washington, DC.
Students from UBC’s MDS in Computational Linguistics partnered with Minerva Intelligence, an AI company that provides knowledge in earth science domains like mining and natural hazards, to extract information from MINFILE, a British Columbia Government mineral occurrences database. The team developed a way to extract details from these reports in order to help Minerva’s knowledge base and make their AI system more robust.
In partnership with UBC’s Peter A. Allard School of Law, a group of UBC MDS Computational Linguistics students examined all negligence cases in BC between 2000 and 2020 in order to determine how damages and contributory negligence have been changing over time. Using cases pulled from LexisNexus, students used two specific methods to develop a system that extracted relevant information from large amounts of text data.
