Help me to get the maximum points on these questions! These questions are not from my exam today, but rather documentation that I obtained in $2022.$ More detailed question is informed on the picture

Questions:

$1.$ Explain intuitively:

a$.$ What is the tokenization? $(10$ points$)$

b$.$ What is the different between stemming and lemmatization? Give an example!

points$)$

$2.$ Let we have corpus: $5$ low, $6$ newer, $3$ wider, $2$ new.

a$.$ Do subword tokenization using wordpiece tokenization in three iterations. $(15$ points$)$

b$.$ What is the tokenization of word "lower" according to wordpiece? $(5$ points$)$

$3.$ We are given the following corpus, modified from the one in the chapter:

I am Sam

Sam I am

Sam like eggs

I do not like green eggs and Sam

a$.$ Create the bigram counting table and probability table! $(15$ points$)$

b$.$ If we use linear interpolation smoothing between a maximum$-$likelihood bigram

model and a maximum$-$likelihood unigram model with ${}_1=\frac{1}{4}$ and ${}_2=\frac{3}{4},$ what

is Sam $|am?$ Include and in your counts just like any other token. $(5$

points$)$

$4.$ Given the following short movie reviews, each labeled with a genre, either comedy or action:

fun, couple, love, love : comedy

fast, furious, shoot : action

couple, fly, fast, fun, fun : comedy

furious, shoot, shoot, fun : action

fly, fast, shoot, love : action

A new document D: fast, couple, shoot, fly

a$.$ Compute the most likely class for $D.$ Assume a naive Bayes classifier and use add$-1$

smoothing for the likelihoods. $(10$ points$)$

b$.$ Compute the vector representation of document D using tf$-$idf. $(10$ points$)$

$5.$ Explain what the attention mechanism is$!$ give a brief example and visualization! $(20$ points$)$