CS 6320002 : Natural Language Processing - Machine Translation - Probabilistic Context Free Grammars - Computer Science Assignment Help

Assignment Task :

Deliverables: Answers can be typed directly into Gradescope. LaTeX can be hand typed or generated using Mathpix Snip. See the assignment guide for more details. 

What does it mean to “show your work?” Write out the math step-by-step; we should be able to clearly follow your reasoning from one step to another. (You can combine “obvious” steps like simplifying fractions or doing basic arithmetic.) The point of showing your work is twofold: to get partial credit if your answer is incorrect, and to show us that you worked the problem yourself and understand it. We will deduct points if steps are missing. 

1 Constituent Parsing 

The problems in this section are based on the material covered in Week 6

2 Dependency Parsing 

The problems in this section are based on the material covered in Week 7. 

Consider the sentence “I think I like cats.” 

A. Parse this sentence by hand and list the dependency relations. You can use arrows, as we do in lecture, or simply list pairs of (head, dependent). 

B. Parse this sentence using shift-reduce parsing, the arc-standard transition system, and no arc labels. You can assume you have a perfet oracle that tells you the correct action to take at each time step. Show the stack, buffer, action, and relation set at each time step (you can use a table, as we do in lecture, or simply show a series of lists). 

C. Parse this sentence again, this time using the arc-eager transition system. Show your work as before. 

3 Machine Translation   

The problems in this section are based on the material covered in Week 8. Suppose we have a training corpus of three sentences: 

1. the dog

2. little dog

3. black dog 

le chien petit chien chien noir 

Now suppose we have a word-level statistical machine translation model with the param eters q(j|i, l, m) and t(fi|ej ) initialized uniformly using this corpus. 

A. Perform one iteration of expectation maximization to update the parameters using the training corpus. State the values of the q’s and t’s at the end of this iteration, plus the intermediate values you calculated for p(ai = j|fi, ej ). You can simply state the values; no need to show the arithmetic. 

B. Perform a second iteration of expectation maximization to update the parameters again. As before, state the values of the q’s and t’s at the end of this iteration, plus the intermediate values you calculated for p(ai = j|fi, ej ).

This  Computer Science Assignment has been solved by our  Computer Science Experts at My Uni Paper. Our Assignment Writing Experts are efficient to provide a fresh solution to this question. We are serving more than 10000+ Students in Australia, UK & US by helping them to score HD in their academics. Our Experts are well trained to follow all marking rubrics & referencing style.

Be it a used or new solution, the quality of the work submitted by our assignment experts remains unhampered. You may continue to expect the same or even better quality with the used and new assignment solution files respectively. There’s one thing to be noticed that you could choose one between the two and acquire an HD either way. You could choose a new assignment solution file to get yourself an exclusive, plagiarism (with free Turnitin file), expert quality assignment or order an old solution file that was considered worthy of the highest distinction.