Skip to main content

Course Descriptions

Required Courses

LING 550: Introduction to Linguistic Phonetics

Credits: 5

This course provides an introduction to the articulatory and acoustic correlates of phonological features. Issues covered include the mapping of dynamic events to static representations, phonetic evidence for phonological description, universal constraints on phonological structure and implications of psychological speech-sound categorization for phonological theory.

Prerequisites: LING 200: Introduction to Linguistic Thought or LING 400: Survey of Linguistic Method & Theory


LING 566: Introduction to Syntax for Computational Linguistics

Credits: 3

This course provides an introduction to syntactic analysis and concepts, including part of speech types, constituent structure, the syntax-semantics interface, and phenomena such as complementation, raising, control, and passive and long-distance dependencies. Emphasis will be placed on formal, precise encoding of linguistic hypotheses and designing grammars so they can be scaled up for practical applications. Students will progressively build a consistent grammar for a fragment of English and will work with problem sets that introduce data and phenomena from other languages.

Prerequisites: LING 200: Introduction to Linguistic Thought or LING 400: Survey of Linguistic Method & Theory


LING 570: Shallow Processing Techniques for Natural Language Processing

Credits: 4

This course covers techniques and algorithms for associating relatively surface-level structures and information with natural language corpora. Topics covered include tokenization/word segmentation, part-of-speech tagging, morphological analysis, named-entity recognition, chunk parsing and word-sense disambiguation. Students will also be introduced to linguistic resources that can be leveraged for these tasks, such as the Penn Treebank and WordNet.

Prerequisites:


LING 571: Deep Processing Techniques for Natural Language Processing

Credits: 4

This course covers algorithms for associating deep or elaborated linguistic structures with naturally occurring linguistic data, looking at syntax, semantics and discourse. It also explores algorithms that produce natural language strings from input semantic representations.

Prerequisites:


LING 572: Advanced Statistical Methods in Natural Language Processing

Credits: 4

This course covers several important machine learning algorithms for natural language processing, including decision tree, kNN, Naive Bayes, transformation-based learning, support vector machine, maximum entropy and conditional random field. Students implement many of the algorithms and apply these algorithms to selected NLP tasks.

Prerequisites: LING 570


LING 573: Natural Language Processing Systems & Applications

Credits: 4

This course looks at building coherent NLP systems designed to tackle practical applications. Students work in groups to build a working end-to-end system for some practical application. The specific application addressed varies by year, but examples include: machine (aided) translation, speech interfaces, information retrieval/extraction, natural language query systems, dialogue systems, augmentative and alternative communication, computer-assisted language learning, language documentation/linguistic hypothesis testing, spelling and grammar checking, optical character recognition, handwriting recognition and software localization.

Prerequisites: LING 570, LING 571, LING 572


Elective Courses

The elective course LING 575: Topics in Computational Linguistics is offered four or five times a year, with new topics offered annually. This course is taught by UW Department of Linguistics faculty as well as guest instructors from other departments and experts from the industry.

Below is a list of topics that have been covered in LING 575 in recent years. Students may also take LING 567: Knowledge Engineering for Deep Natural Language Processing or select courses in related fields, such as EE 516: Computer Speech Processing, as electives.

Note: The prerequisites for LING 575 vary by course topic, but typically are LING 570 or LING 571.

LING 575: Computational Methods in Language Documentation

Instructor: Emily Bender

Credits: 3

This course covers computational approaches to facilitating endangered language documentation, with a particular focus on the methods developed in the AGGREGATION Project. Student projects center on extending the inference of AGGREGATION to be able to extract additional types of information out of interlinear glossed text, producing more complete answers to the Grammar Matrix customization system questionnaire.


LING 575: Declarative Information Extraction

Instructor: Fei Xia

Credits: 3

Information extraction (IE) is an essential component for many applications that leverage unstructured text, including social media analytics, biomedical NLP, financial risk analysis, semantic search, regulatory compliance and legal discovery. This course focuses on a new IE paradigm called declarative information extraction. Declarative IE has recently emerged as a powerful approach to building high-performance IE systems. In this course, students explore in detail one particular IE system, SystemT, including its theoretical foundations, rule language (AQL) and algorithms.


LING 575: Spoken Dialogue Systems

Instructor: Gina-Anne Levow

Credits: 3

This course covers the theories and practices of spoken dialogue systems. Students use publicly available tools and toolkits to investigate techniques and issues related to these systems. The focus is on conversational systems that are more flexible than the typical flight status phone system. Students work with the components of a typical spoken dialogue system pipeline, including speech recognizer grammars, semantic interpretation for inputs, dialogue managers and conversational design, and speech output.


LING 575: Introduction to Speech Technology

Instructor: Michael Tjalve

Credits: 3

This course offers an introductory exploration of the key concepts and components of speech technology, a viable interface for millions of users every day. Topics covered include the mechanics of current speech technologies, application design, speech technology research and a comparison of human-to-human speech communication with speech technology. Students get hands-on experience designing and building some of the underlying components of speech technology, including their own speech recognizer. Students also discuss how speech applications impact today's world.


LING 575: Crowdsourcing for Speech Technology & Natural Language Processing

Instructor: Daniela Braga

Credits: 3

This course covers the theory and practice of crowdsourcing, an increasingly popular method for data collection, labeling and evaluation. Students focus on exploring crowdsourcing's applications for speech technology and natural language processing systems. They review the latest papers in the field and design and deploy a task or workflow in a crowdsourcing platform.


LING 575: Linguistic Expressions of Sentiment, Subjectivity & Stance

Instructor: Gina-Anne Levow

Credits: 3

This course explores the main issues and approaches for automatic recognition of sentiment in both written and spoken language, which is used for tasks such as automatically analyzing film and product reviews, detecting bias in news articles and determining the tenor of meetings or customer service calls. Student projects include an implementation of methods for automatic recognition and an analysis of linguistic phenomena associated with sentiment, subjectivity and stance.


LING 575: Creating Natural Language Processing Resources for Resource-Poor Languages

Instructor: Fei Xia

Credits: 3

This course covers recent studies in the area of creating natural language tools for resource-poor languages using resources that already exist for resource-rich languages. Students choose a task, experiment with various techniques, conduct a literature survey, design and evaluate a system, write a final report and present their work.


LING 575: Minimal Recursion Semantics in Applications

Instructor: Emily Bender

Credits: 3

This course explores how Minimal Recursion Semantics representations can be used to inform semantically sensitive natural language processing tasks, such as anaphora resolution, event detection and relation extraction. The seminar begins with an overview of MRS and moves on to explore candidate tasks and how to create machine learning features from MRS to augment existing solutions to those tasks. This seminar includes term projects where students select an existing annotated data set for a semantically sensitive task and an existing baseline solution and then work to improve on that solution by adding MRS-based features.


LING 575: Semantic Representations

Instructor: Emily Bender

Credits: 3

The goal of this course is to give students a better understanding of the relationship between the information encoded in Minimal Recursion Semantics, as produced by the English Resource Grammar, and the information needs of downstream applications that take semantic representations as input. The course begins with an overview of MRS and then moves to alternative meaning representations. Term projects involve developing mappings between MRS and other representations, based on data sets that have target representations included in their annotations with the aim of revealing information that's in the MRS but not in the target representation and vice versa.


LING 575: Domain Adaptation

Instructor: Fei Xia

Credits: 3

This course explores recent studies in domain adaptation, and students experiment with various domain adaptation techniques. For NLP tasks, the course focuses on part-of-speech tagging and parsing for English and Chinese, as the data and baseline systems for those tasks are available. The students choose a task, conduct literature review, design a system, evaluate the system, present their work and write a final report.