Multilingual NLP: Words, Parts of Speech, Morphology

Learn about fundamental concepts in linguistics and natural language processing in this 39-minute lecture from CMU's Multilingual NLP course. Explore the definition of words, parts of speech, and morphology. Dive into structural subfields of linguistics, universal dependencies, and morphological processes across languages like Tagalog, Arabic, and Chinese. Discover morphological typology, the SIGMORPHON shared tasks, and related NLP problems. Gain insights from Yulia Tsvetkov's presentation, part of Graham Neubig's CS11-737 course at Carnegie Mellon University.

Intro
What is a word?
Structural subfields of linguistics
Parts of speech
Part of speech tagsets
The Universal Dependencies
Words are made of morphemes
Morphological processes
Tagalog
Arabic, Chinese
Morphological functions
Morphological typology
The SIGMORPHON shared tasks
Related NLP problems
Readings and class discussion