Skip to content

Latest commit

 

History

History
43 lines (31 loc) · 2.6 KB

Policies.md

File metadata and controls

43 lines (31 loc) · 2.6 KB

Getting help

TA's office hours will be 11-12 on Friday in the computational linguistics lab (the space next to TSRB 228A). You can TSRB by showing your GTID at the desk. The office is to the left of the stairs on the second floor.

Professor Eisenstein’s office hours will be 10-11 on Tuesday in TSRB 228A.

Prerequisites

This course assumes

  • Good coding ability, corresponding to at least a third or fourth-year undergraduate CS major. Assignments will be in Python.
  • Background in basic probability, linear algebra, and calculus.
  • Understanding of automata and formal language theory: finite-state and context-free languages, NP-completeness, etc.
  • Experience with dynamic programming algorithms.
  • Familiarity with machine learning is helpful but not assumed. Of particular relevance are linear classifiers: perceptron, naive Bayes, and logistic regression.

People sometimes want to take the course without having all of these prerequisites. Frequent cases are:

  • Junior CS students with strong programming skills but limited theoretical and mathematical background,
  • Non-CS students with strong mathematical background but limited programming experience.

Students in the first group suffer in the exam and don't understand the lectures, and students in the second group suffer in the problem sets. My advice is to get the background material first, and then take this course.

Policies

Multiple studies have shown that using a laptop in class -- even for taking notes -- reduces students' educational attainment. See here for a popular press article summarizing this research. You are adults and must make your own decision, but my advice is to try pen and paper instead.

There are three types of assignments: homeworks, problem sets, and the final project.

  • Homework assignments are due in class, in paper format. Printers are unreliable, so leave a little time to get it printed out. They will not be accepted late; however, you get one "freebie" homework that you can skip.
  • Problem sets are due at the start of class on T-Square. They will be accepted up to three days late. For every 24 hour period after the due date, the grade will be reduced by 20%. It's usually best to just turn in the project on time with what you have.
  • The final project will have several intermediate due dates, as indicated on the schedule.

If you cannot make it to office hours, please email me to make an appointment. It's unlikely I'll be able to chat if you just stop by my office. The same is true for the TA.