NYUAD CS-UH 2216 / Spring 2019

Natural Language Processing

Description

The field of natural language processing (NLP), also known as computational linguistics, is interested in the modeling and processing of human (i.e., natural) languages. This course covers foundational NLP concepts and ideas, such as regular expressions, n-gram models, hidden Markov models, part-of-speech tagging, context free grammars, syntactic parsing, and semantic representations (including word embeddings). The course will survey a range of NLP applications such as sentiment analysis, information retrieval, summarization and machine translation. Concepts taught in class will be reinforced in practice by hands-on assignments.

Students who successfully complete this course will be able to

  • Understand the fundamental concepts and methods of NLP
  • Understand the special challenges and solutions of a number of NLP applications
  • Build models, and implement algorithms central to NLP and other computer science areas
  • Conduct scientific research in NLP applications
  • Design and run NLP scientific experiments (including forming hypotheses, identifying baselines and toplines, following proper methodology for blind testing, analyzing results, and forming conclusions)
  • Develop NLP applications using some of the most commonly used NLP toolkits

Text Books, Slides and Handouts

SLP: Daniel Jurafsky and James H. Martin. "Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition." (portions from 2nd Edition and 3rd Edition, draft). Specific chapters are included in the course syllabus shared folder to ensure a common version is read by all in this course.

All slides and handouts will be available online on the course syllabus shared folder (see end of this page).

Requirements

Components of the Final Grade

  1. Assignments (50%)
    • The assignments vary in form including on-paper exercises (such as walking through algorithms), hands-on programming, building systems using off-the-shelf tools, and data analysis.
    • Assignment #1 (10%), Assignment #2 (10%), Assignment #3 (15%), Assignment #4 (15%)
  2. Midterm Exam (15%)
  3. Final Exam (20%)
  4. Pop Quizzes (10%)
    • Random short quizzes about course readings and discussed materials
  5. Participation in class (5%)
    • Demonstrate through participation in discussions about assigned readings

Grade Conversion

  • A=95-100; A-=90-94; B+=87-89; B=83-86; B-=80-82; C+=77-79; C=73-76; C-=70-72; D+=67-69; D=63-66; F=below 63

Participation and Attendance Policies

  • Full attendance is required. Absences must be excused. Participation is expected in class discussions of specific NLP problems and solutions in a way that demonstrates preparedness. Every unexcused absence (not pre-cleared with instructor, or not with medical documentation provided to instructor) will automatically result in a 10% reduction in the final grade.

Assignment Submission Policies

  • All assignments are due at 11:59pm on the due date specified in syllabus. Submission will be done through NYU Classes. For late submissions, 10% will be deducted from the homework grade per each late day.

Academic Integrity

As set forth in NYU Abu Dhabi's Academic Integrity Policy, the relationship between students and faculty at NYU Abu Dhabi is defined by a shared commitment to academic excellence and is grounded in an expectation of fairness, honesty, and respect, which are essential to maintaining the integrity of the community. Every student who enrolls and everyone who accepts an appointment as a member of the faculty or staff at NYU Abu Dhabi agrees to abide by the expectation of academic honesty. The full policies and procedures relating to Academic Integrity may be found on the NYUAD Student Portal.

Copying or paraphrasing someone's work, or permitting your own work to be copied or paraphrased, even if only in part, is not allowed, and will result in an automatic grade of 0 for the entire assignment or exam in which the copying or paraphrasing was done. Your grade should reflect your own work. If you believe you are going to have trouble completing an assignment, please talk to the instructor in advance of the due date.

Course Schedule

NLP-S2019-Public-Schedule

Course Syllabus Shared Folder