Podcasts and Videos

DESCRIPTION: The goals of commonsense reasoning systems include being able to answer commonsense reasoning questions. In order to compare systems, a number of benchmark question sets have arisen. Leaderboards have emerged to act as hubs for hosting benchmarks and supporting infrastructure that accepts submissions of commonsense reasoning systems that then get scored against the benchmarks. These benchmarks vary in structure. Some provide questions and answer choices, while others may provide factual observations and require reasoners to choose the most appropriate hypothesis to explain them. 

Recently, there is an increasing effort to incorporate structured knowledge in these systems, largely based on machine-learning techniques, as a way to improve their overall score against benchmarks. In this talk, we will present and discuss our current efforts in supporting this goal, in the context of the Machine Commonsense Project. It includes a Benchmark Ontology, which provides a common vocabulary to allow diverse benchmarks to be compared, integrated, and to support the analysis of systems and machine-learning language models. This talk will discuss its design decisions and showcases how it is currently supporting the development of a Benchmark tool.

Please join us for a final review of our IDEA Health INCITE COVID Campus Reopening Summer Projects. During this half-hour our students presented their Summer 2020 work on COVIDMINDER, Data INCITE's COVID monitoring application (initiated in early 2020).

NOTE: Recording of these group presentations were split into two half-hour recordings.

Please join us for a final review of our IDEA Health INCITE COVID Campus Reopening Summer Projects. During this half-hour our students presented their Summer 2020 work on the COVID WarRoom and COVID Back-to-School predictive modelling apps.

NOTE: Recording of these group presentations were split into two half-hour recordings.

In this exploratory study, we scrutinize a database of over 1 million tweets collected across the first five months of 2020 to draw conclusions about public attitudes towards the preventative measure of mask usage during the COVID-19 pandemic. In recent months, a body of literature has emerged to suggest the robustness of trends in online activity as proxies for the epidemiological and sociological impact of COVID-19. We employ natural language processing, clustering and sentiment analysis techniques to organize tweets relating to mask-wearing into high-level themes, then relay narratives for individual clusters through automatic text summarization.

We find that topic clustering and visualization based on mask-related Twitter data offers revealing insights into societal perceptions of COVID-19 and techniques for its prevention. We observe that the volume and polarity of mask related tweets has greatly increased. Importantly, the analysis pipeline presented can be leveraged by the health community for the assessment of public response to health interventions in the ongoing global health crisis.

Please join us for a final review of our IDEA Health INCITE COVID Campus Reopening Summer Projects. During this hour our students presented their Summer 2020 work on campus "de-densification" and WiFi monitoring, including building and campus flow, classroom occupancy, and "SafeStudent" applications.

NOTE: Recording of these group presentations were split into two half-hour recordings.

Please join us for a final review of our IDEA Health INCITE COVID Campus Reopening Summer Projects. During this hour our students presented their Summer 2020 work on campus "de-densification" and WiFi monitoring, including building and campus flow, classroom occupancy, and "SafeStudent" applications.

NOTE: Recording of these group presentations were split into two half-hour recordings.