Explore word segmentation and morphology in this advanced Natural Language Processing lecture from Carnegie Mellon University. Delve into the complexities of defining a "word," learn about tokenization techniques, and understand morphological analysis across various languages. Discover unsupervised subword segmentation methods and examine language typology, including isolated and agglutinative languages. Investigate historical linguistics, patterns of languages, and the application of finite state automata in morphological analysis. Gain insights into spelling rules, type-token curves, and the intricacies of morphology in English and other European languages.
CMU Advanced NLP: Word Segmentation and Morphology