Custom NLP pipeline for information extraction in a clinical setting

State-of-the-art natural language processing tools are rapidly improving in being able to identify real-world objects in texts (e.g. person, location, organization). However, the vocabularies and document structures used in a medical setting can vary from general language corpus from which the NLP models were trained; resulting in poor performance.This project will fine-tune existing NLP models to perform highly on medical text documents in order to recognise and extract pertinent information about a patient (e.g. diseases, medical findings) in a structured format.

Yóntstha Ka’nikonhrí:yo (Using a Good Mind)

This research project seeks to examine the Haudenosaunee cultural principles of Kayaneren’kó:wa (The Great Law), Skén:nen (Peace and Balance), Ka’satsténshera (Power and Unity), and Ka’nikonhrí:yo (Good Mind / Righteousness). Through research of historical documents, investigation of the current literature, and consultation with Haudenosaunee knowledge keepers, this project seeks to discover innovative ways that these cultural concepts can be applied in the twenty-first century and beyond.

An automated system to identify and extract key structural components in academic written texts or genres

To streamline knowledge acquisition, indexing, dissemination, and synthesis—especially important to the future of libraries—a fundamental understanding of knowledge storage and communication is required. In a textual body of knowledge, relevant qualities include layout and structure; headings, chapters, sections, and paragraphs; figures, tables, lists, captions, and illustrations; authorship information and references; and, most importantly, the relationship between these semantic components.

Separating Syntax and Semantics for Semantic Parsing

Study of language disorders, theoretical linguistics, and neuroscience suggests language competence involves two interacting systems, typically dubbed syntax and semantics. However few state-of-the-art deep-learning approaches for natural language processing explicitly model two different systems of representation. While achieving impressive performance on linguistic tasks, they commonly fail to generalize systematically. For example, unlike humans, learning a new verb like jump in isolation is insufficient for models to combine it with known words (like jump twice or jump and run).

Exploring neuroimaging methods to assess the effects of music therapy

The objective of this project is to research new technologies and methods to help in the assessment and functional imaging of neuroplasticity related to music therapy. The approach utilizes key novel technologies being researched in partnership with Dr. Ryan D’Arcy.

Evaluation of Cultural Change Interventions in the Workplace

Habanero Consulting group is partnering with Postdoctoral Researcher Ryan Taylor and Professor Bryan Gick from the University of British Columbia, and Fernando Nieto Morales from the Colegio de Mexico. They will apply the most current research from the social sciences to strengthen Habanero?s cultural transformation techniques and create a tool to more quickly and accurately diagnose impediments to organizational improvement.

Play for Reality: Conveying Sustainability Challenges Through Game Mechanics

Several Ontario regions have agreed to reduce their carbon emissions by 80% by 2050. However, many of these cities don’t actually have a plan for how they’ll reach this noble but challenging goal. In response, the Waterloo Global Science Initiative (WGSI) (in partnership with several Waterloo Region collaborators) has created a prototype board game called Energize: its goal is to draw attention to the challenges and the solutions of how a city can reduce carbon emissions.

Flow Weaver Virtual Reality Research Project

This project is intended to further the videogame industry's understanding of user presence and immersive game design, where the player feels that they exist in a virtual space and can control a virtual environment with their physical body. Rather than trying to achieve immersion in a virtual world by escaping from the body, this project engages the player's body on the other side of the screen through motions and mechanics enacted through virtual body ownership.

Cultivating Ethos in the Tech Sector

The rapid development of technology and its ubiquitous integration with modern society has clarified for business and technology leaders the need for ethical conversations about the role technology can and should play in our lives. By interviewing primary stakeholders in the technology sector and putting their ideas in conversation with literature about the role of ethics in tech, this project will foster a critical dialogue between businesses, governments and users to overcome the ethical challenges posed by technological innovation.

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.