Implications and Explanations in User-Generated Data
published: May 3, 2021, recorded: April 2021, views: 7
Report a problem or upload filesIf you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
User-generated data (such as reviews and community Q&A) are a rich source of user insights and experiences that can be very helpful in many different daily life situations, such as when deciding what product to buy, or what hotel to stay. Given its relevance, there has been growing interest in designing systems that can automatically extract knowledge from such types of data. In many cases, in order to extract knowledge from user-generated data it is necessary to make commonsense inferences that will help to better understand the context and the narrative being presented. In this talk I’ll start by going over different approaches that take advantage of commonsense knowledge to solve different downstream tasks related to natural language understanding and artificial intelligence. Then, I’ll focus on the specific characteristics of “user-generated” data and discuss two possible ways that we can frame commonsense: through implications and through explanations.
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !