Infusing Machine Learning with Domain Knowledge

About this project Extracting useful information from natural language text remains a challenging task despite the considerable advances in machine learning technology for natural language processing in recent years. For example, the accuracy of state-of-the-art machine learning approaches for event extraction remains well below what humans can achieve in this task. Modern machine learning models produce results that are based predominantly on correlations of text passages and lack the understanding that humans who possess prior knowledge would attain. The […]

Click here to view original web page at www.unisa.edu.au

Leave a Comment

Your email address will not be published. Required fields are marked *