Syllabus
As the information age has revolutionized the way humans live, we are experiencing information overload where the amount of data we encounter grows beyond the human capacity. Although multimedia became a substantial part of big data, text is still the most primitive yet dominating medium. This interdisciplinary course teaches how to extract necessary information from text (Linguistics), make statistical analysis of the extracted information (Quantitative Theory and Methods ), and write computer programs to automate this process (Computer Science).
- Class hours and location: MW 2:30 - 3:45pm, MSC W201.
- Prerequisites: CS 171 (CS and LING students), QTM 220 (QTM students).
- Jinho Choi: TR 2:30 - 4pm, MSC E414.
- Bonggun Shin and Henry Chen: Fri 4 - 6pm, MSC E308A.
- Speech and Language Processing (2nd Edition), Jurafsky and Martin.
- Introduction to Information Retrieval, Manning, Raghavan, Schütze.
- Homework assignments: 40%.
- Take-home quizzes: 10%.
- Midterm exam: 20%.
- Final exam: 30%.
- Your work is governed by the Emory Honor Code and the Math/CS SPCA. Honor code violations on any submission will be referred to the Emory Honor Council.
- Excuses for exam absence/reschedule and other serious personal events (health, family, personal related, etc.) that affect course performance must be accompanied by a letter from the Office of Undergraduate Education.
- Homework assignments and quizzes are due by the beginning of the class. Late submissions are not allowed for quizzes. Late submissions for homework assignments are accepted with the grading penalty of 15%. Late submissions are no longer accepted once the answer keys are out. Exceptions to this policy will be made only in extraordinary circumstances.
- Homework assignments and quizzes must be submitted individually unless they are assigned as group projects. Group discussions are allowed; however, your work must be original. Apparent copies from any source, including your colleagues and internet sites, will be referred to the Emory Honor Council.
