Machine Learning (ML) algorithms have opened up new possibilitiesfor the acquisition and processing of documents in InformationRetrieval (IR) systems. Indeed, it is now possible to automate severallabor-intensive tasks related to documents such as categorization andentity extraction. Consequently, the application of machine learning techniquesfor various large-scale IR tasks has gathered significant researchinterest in both the ML and IR communities. This tutorial provides areference summary of our research in applying machine learning techniquesto diverse tasks in Digital Libraries (DL). Digital library portalsare specialized IR systems that work on collections of documentsrelated to particular domains. We focus on open-access, scientific digitallibraries such as CiteSeerx, which involve several crawling, ranking,content analysis, and metadata extraction tasks. We elaborate on thechallenges involved in these tasks and highlight how machine learningmethods can successfully address these challenges.