Computer Science > EXAM > Practice Midterm Exam for Natural Language Processing New York University - CSC CSCI-UA.04 (All)

Practice Midterm Exam for Natural Language Processing New York University - CSC CSCI-UA.04

Document Content and Description Below

Practice Midterm Exam for Natural Language Processing Name: Net ID Instructions In the actual midterm there will be 7 questions, each will be worth 15 points, for a total of 105 possible points. Please write your name and id number on your test. If any part of your test gets loose from the original, please write your name on that as well. This practice test will have a different number of problems that are intended to be of the same basic type of question as on the actual midterm. THE PRACTICE TEST IS DESIGNED TO TAKE LONGER TO COMPLETE THAN THE ACTUAL TEST WOULD (AROUND 2 HOURS, RATHER THAN 1:15). All answers should be written directly on the test booklet, inside of the indicated tables and boxes. Extra space is provided to allow room for cross-outs and corrections. Please feel free to use the backs of pages and the extra blank pages (at the end of the test) provided as scrap paper. Please do not remove any pages from the test and please do not add any pages to the test. Extra scrap paper is available if you need it. This test is an open book/open notes test: Please feel free to bring your text book, your notes, copies of class lectures and other reading material to the test. A calculator (or cell phone, used as a calculator) is also permitted and it is OK to look at materials on the web in order to read helpful information, being mindful of the time limit. Just don’t use a program that solves a problem for you, e.g., do not find a part of speech tagger and run it if asked to manually annotate mark parts of speech – that WOULD be cheating. Answer all questions on the test. If you show your work and you make a simple arithmetic mistake, but it is clear you knew how to do it, you will get partial credit.• William R. Breakey M.D. • Pamela J. Fischer M.D. • Leighton E. Cluff M.D. • James S. Thompson, M.D. • C.M. Franklin, M.D. • Atul Gawande, M.D. • Dr. Talcott • Dr. J. Gordon Melton • Dr. Etienne-Emile Baulieu • Dr. Karl Thomae • Dr. Alan D. Lourie • Dr. Xiaotong Fei • Doctor Dre • Doctor Dolittle • Doctor William Archibald Spooner • Doctor No Figure 1: Correct Instances of Doctors in Our Corpus Question 1. Write a regular expression for identifying names of doctors in text. Your regular expression should match the examples in figure 1, but should not recognize either non-names (words lacking capital letters) or names that do not include the identifying title information (Dr., Doctor, M.D.). Do your best to include information about spaces, hyphens, commas and periods, as per the examples.

[Show More]

Last updated: 6 months ago

Preview 1 out of 15 pages

Buy Now

Instant download