Topics: This course will provide an introduction to computational linguistics, from morphology (word formation) and syntax (sentence structure) to semantics (meaning), and natural language processing applications such as parsing, machine translation, generation and dialog systems.
Objectives: At the end of this course, students should have a good understanding of the research questions and methods used in different areas of natural language processing. Students should also be able to use this knowledge to implement simple natural language processing algorithms and applications. Students who take this course for 4 hours credit should also be able to understand and evaluate original research papers in natural language processing that build on and go beyond the textbook material covered in class.
Textbook: Jurafsky and Martin (2008), Speech and Language Processing, 2nd edition. This is a required text. All assigned readings are from this book, unless indicated otherwise. Make sure to get the second edition, since it is significantly different from the first one!
Target audience and Prerequisites: Advanced undergraduates and graduates with a background in formal language and automata theory (CS273 or equivalent). Programming experience is necessary for the assignments. Prior exposure to linguistics is not required.
Grading and homework: There will be around 5 graded homework assignments, one midterm exam and one final exam. The exams will cover material covered in the required reading and the lectures. The homework assignments will contain some additional programming exercises. You will need a CSIL account to do the homework, as the required software and data will be installed on the CSIL machines. If you are taking this course for 3 hours credit, 1/3 of your grade will come from your homework assignments, 1/3 will come from the midterm, and 1/3 will come from the final exam. If you are taking this course for 4 hours credit, the homework assignments, midterm and final exam will each account for 1/4 of your grade, and the remaining 1/4 will consist of an in-depth literature survey on a topic of your choice or a small research project.