Learning Probabilistic and Lexicalized Grammars for Natural Language Processing
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only! Grab it Explore the intricacies of grammar representation and automatic construction for natural language processing in this one-hour talk by Rebecca Hwa from the University of Maryland. Delve into the Probabilistic Lexicalized Tree Insertion Grammars (PLTIGs) formalism and its linguistically motivated properties beneficial for processing natural languages. Learn about an algorithm for automatically inducing PLTIGs from human-annotated text corpora and discover empirical studies comparing PLTIGs with other formalisms across various tasks. Investigate methods to enhance grammar induction efficiency, focusing on reducing dependency on human-annotated training data through sample selection techniques. Gain insights into cutting-edge research in natural language processing, machine learning, and human-computer interaction from this postdoctoral research fellow at the Center for Language & Speech Processing at Johns Hopkins University.