ECE467_2010SPRING_EXAM1__[0]

ECE467_2010SPRING_EXAM1__[0] - Natural Language Processing...

Info iconThis preview shows pages 1–4. Sign up to view the full content.

View Full Document Right Arrow Icon
Natural Language Processing Spring 2010 Take-Home Final Exam Name: _______________________________________________________________________ E-mail address: ________________________________________________________________ You have 24 hours to complete this test. You can return it to me physically by directly handing it to me, or you can submit it electronically (if you need to, you may scan hand-written pages and e-mail them to me). This is an open-book, open-notes test. You may look on-line for material. The only rule is that you may not communicate to anyone else to get help with the questions. You also may not post any questions on forums (that counts as communicating with other people).
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Question #1: Regular Expressions, Finite State Transducers, and Morphology In class, we discussed the following transducer, also shown in Figure 3.17 of the textbook: (a) Briefly explain (in one or two sentences) the purpose of this transducer. (b) When translating from lexical form to surface form, what happens before this transducer is applied? In other words, what is the input to this transducer, and how is that input produced? (c) Related to the specific example discussed in the book and class, when the transducer is used to pluralize the noun "fox", what is the input to the transducer? Also, exactly which states are visited (in order), and what is the output generated at each state transition? (d) When the transducer is used to pluralize the noun "house", what is the input to the transducer? Also, exactly which states are visited (in order), and what is the output generated at each state transition?
Background image of page 2
Question #2: N-Grams (a) Assume that an N-Gram model has been trained based on the text in our textbook. Hypothetically, let's say that after training, you choose a random sentence from the textbook
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Image of page 4
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

Page1 / 10

ECE467_2010SPRING_EXAM1__[0] - Natural Language Processing...

This preview shows document pages 1 - 4. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online