Graduate Courses
Computational linguistics
-
Introduction to key components of human language technologies, including: parsing, discourse, dialogue, information extraction, sentiment analysis, question answering, analysis of linguistic structure.
Instructors: Core and Georgila (Fall), and Artstein (Spring). -
Computational models of natural language. Formalisms for describing structures of human language, and algorithms for learning language structures from data.
Instructor: Knight. -
Introduce and discuss many of the sub-problems and methods of information extraction, including use of textual patterns, language and formatting features, generative and conditional models, rule-learning and deep learning techniques. Will discuss segmentation of text streams, classification of segments into fields, association of fields into records, and clustering and de-duplication of records.
Instructor: Xiang -
Introduction to machine translation, with a focus on statistical approaches. Word-based, phrase-based, and syntax-based translation; current research questions in machine translation.
Instructors: Chiang and Knight. Last offered Spring 2014. -
Fundamental topics in Information Retrieval, the science of searching for and making sense of information from large collections of text.
Instructor: Leuski.
Last offered Spring 2012. -
Machine learning, pattern recognition, and signal processing tools to analyze, recognize, and predict human communication behaviors during social interactions.
Instructors: Morency and Scherer.
Last offered Fall 2012. -
Computational techniques and active research areas in natural language dialogue systems. Spoken language understanding, modeling dialogue genres, dialogue management and representing context, dialogue response policies, natural language generation, embodied conversational agents, incremental speech processing, and dialogue system evaluation.
Instructors: DeVault and Traum.
Last offered Spring 2013. -
Speech production, acoustics, perception, synthesis, compression, recognition, transmission. Coding for speech, music, and CD-quality. Feature extraction. Echo cancellation. Audio, visual synchronization. Multimedia, Internet use.
Instructor: Narayanan. -
Modern automatic speech recognition systems, with emphasis on statistical methods and modeling techniques. Hidden Markov models (HMMs), acoustic modeling using HMMs, front end processing for robustness, statistical language models, and dialogue modeling.
Instructor: Narayanan.
Related fields
-
CSCI 561: Introduction to Artificial Intelligence
-
CSCI 573: Advanced Artificial Intelligence
-
CSCI 567: Machine Learning
-
EE 517: Statistics for Engineers
-
EE 559: Mathematical Pattern Recognition
-
EE 565: Information Theory
-
LING 531: Phonology
-
LING 547: Morphology
-
LING 530: Generative Syntax
-
LING 537: Advanced Syntax
-
LING 534: Logic and the Theory of Meaning
-
LING 576: Psycholinguistics
-
MATH 505: Applied Probability
-
MATH 511: Data Analysis
-
MATH 541: Introduction to Mathematical Statistics
-
MATH 547: Methods of Statistical Inference
Undergraduate Courses
-
LING 285Lg: Human Language and Technology
Study of human linguistic competence and technologies that simulate it. Grammar, parsing, text generation; semantics, pragmatics, sense disambiguation; phonetics, speech synthesis, speech recognition. Instructor: Iskarous.