- This course introduces the key concepts underlying statistical natural language processing. Students will learn a variety of techniques for the computational modeling of natural language, including: n-gram models, smoothing, Hidden Markov models, Bayesian Inference, Expectation Maximization, Viterbi, Inside-Outside Algorithm for Probabilistic Context-Free Grammars, and higher-order language models. Software: GitHub, Git Bash, Python: NLTK, SpaCy, numpy, scikit-learn.
- This course provides a hands-on project-based approach to particular problems and issues in computational linguistics. Students are expected to be able to gain enough familiarity to install, run and perform project work on these packages on their own machines. Projects to be tackled in this course are themed around the topic of language understanding: Treebanks (phrase-structure/dependency-based): e.g. Penn Treebank, lookup software. Part-of-speech taggers. The use and modification of statistical parsers trained on Treebanks Advanced linguistic theories Ontologies and Semantic Networks: WordNet etc. Question-Answering (QA)
- Natural language processing (NLP) is the study of how we can teach computers to use language by extracting knowledge from text, and then use that knowledge in some meaningful way. In this introductory course, we will examine the fundamental components on which natural language processing systems are built, including frequency distributions, part of speech tagging, syntactic parsing, semantics and analyzing meaning, search, introductory information and relation extraction, and structured knowledge resources. We also examine pragmatic concerns in processing raw text from real-world sources.
- This is a introductory course in computational linguistics at an advanced level. Students implement finite state automata, transducers, parsers and translation programs based on grammar rules in a series of computer laboratory exercises. Software: Software: Perl, Python, Bash, SWI-Prolog, Ubuntu(Linux), Virtual Machine. In the case of numerical calculations, we make use of Microsoft Excel for worked examples and homework questions. We program using Python (3.x) and also learn to use computational tools such as NLTK for language analysis.
- Topics include speech synthesis, automatic speech recognition, acoustics, waveforms, spectrograms, and other speech technologies. This course gives students background for a career in the speech technology industry. Software: python, jupyter notebooks, Praat.
- Modern linguistic theory requires a working familiarity with several “formal”disciplines, e.g. set theory, logic, lambda calculus, formal language theory, probability theory, etc. The point of this course is to provide that familiarity, with particular attention to how those disciplines can be and are used in our field.
- Study of the user interface in information systems, of human computer interaction, and of website design and evaluation. Group project included building a sample web page using Bootstrap, git, GitHub. Evaulation included tools such as an IDE and the browser console.
- Using Python on linguistics-related topics, we cover datatypes and variables, control structures, object-oriented programming, GUIs, functions, input-output, modules, nltk, web scraping, text manipulation, functional programming.
- I audited this course. This course introduces students to the concepts and techniques of data mining for knowledge discovery. It includes methods developed in the fields of statistics, large-scale data analytics, machine learning, pattern recognition, database technology and artificial intelligence for automatic or semi-automatic analysis of large quantities of data to extract previously unknown interesting patterns. Topics include understanding varieties of data, data preprocessing, classification, association and correlation rule analysis, cluster analysis, outlier detection, and data mining trends and research frontiers. We use software packages for data mining, explaining the underlying algorithms and their use and limitations. The course include laboratory exercises, with data mining case studies using data from many different resources such as social networks, linguistics, geo-spatial applications, marketing and/or psychology.
- I audited this course. Neural networks are a branch of machine learning that combines a large number of simple computational units to allow computers to learn from and generalize over complex patterns in data. Students in this course will learn how to train and optimize feed forward, convolutional, and recurrent neural networks for tasks such as text classification, image recognition, and game playing.
- Provides an introduction to cognitive science by exploring foundational issues as well as topics of contemporary research in cognitive science.
- In this interdisciplinary graduate seminar, we explore knowledge representation from both computational and cognitive perspectives. High-level topics we will explore will include the nature of conceptual representations, how concepts are represented and used in brains and computers (symbol grounding), semantic networks and knowledge graphs, structured representations, ontological engineering, semantic frames, concepts in infants, the situated nature of concepts/embodied cognition, explanatory knowledge, common-sense knowledge, and other related topics.
Blintzkrieg/Courses
Courses taken at the University of Arizona toward the M.S. in Human Language Technology; completion expected Spring 2020
Prolog