W4 L2

Question 1

what is lexical semantics

Answer 1

a branch of nlp that deals with word sense

but what is a sense bearing unit

Question 2

does a word always have the same meaning

Answer 2

no! the same spelling of a word can have different meanings

Question 3

homonymy

Answer 3

when two words are spelt the same but have different meaning

i went to the bank
we sat on the bank

Question 4

what is word net

Answer 4

the largest most popular database of lexical relations

Question 5

what is a homophone

Answer 5

same pronouncation with different spelling

to too two

these are hard for speech models

Question 6

homographs

Answer 6

same spelling but different pronounciaiton

drum bass
fish bass

hard for text to speech agents

Question 7

what is polysemy

Answer 7

when words are extended/ the meaning is transfered from words

bank
blood bank

Question 8

what is metonymy

Answer 8

a subtype of polysemy

ie shakespear

author: shakepear wrote hamlet

works of author: i studied shakespear at school

turkey animal vs turkey meat

Question 9

what synonymy

Answer 9

words that have the similar meaning

ie sofa and couch

Question 10

antonymy

Answer 10

words that have opposite meanings

big small

Question 11

what is hypo and nypernym

Answer 11

hypo is a sub term

and hyper is a super term

socretes is a man
all men are mortal
socreties is moral

hypo to hyper

but not hyper to hyp
not all men are socreties

Question 12

what are semeantic fields

Answer 12

allow you to combine various terms that are related to the same domain

ie flight booking, plane, price, meal
-> domain of air travel

Question 13

what is a concept

Answer 13

and abstract idea representign the fundemental characteristics of what it represents

Question 14

what is classical concept theory

Answer 14

aristotle

concepts have a definitional structure, a list of features and all memebrs of this class must have these features

Question 15

what is prototype concept therory

Answer 15

properties of concepts are not definitional

memebers tend to posses them but not strictly required

ie memebrs tend to look similar but they dont need to be super restrictive requriements

Question 16

what is the theory concept theory

Answer 16

catagorization by concept

as new evidence comes, new members join and definitions change

definitions are in relation to each other

Question 17

what is the big bag of words method

Answer 17

machine learning models reqiure numbers so we can use classification to turn words lemmas synsets and concepts into features

this ignores word order so its called bag of words method

Question 18

what do we need to apply to features to classififcation

Answer 18

feature selection, feature weighting, normalization

Question 19

what is feature selection

Answer 19

selecting the most important of the features

Question 20

what is feature weighting and normalisiation

Answer 20

weighing the most important features after feature selection (tfidf)

Question 21

what is the power of bayes formula

Answer 21

bayes formula allowss us to flip the coniditions

P(class|content) =

P(content)

Question 22

what is the P(class | content) in bayes formula

Answer 22

posteriro probabilitiy
this is the postierior probabilitiy we are interested in in bayes formula that we need to use other formulas to get

Question 23

what is P(class) in bayes formula

Answer 23

prior probabilitiy

our belife about the class distrbution before we see more evidence

Question 24

what is P(content |class) in bayes formula

Answer 24

the likelihood

it shows how likely it is to see this exact combinations of features

Question 25

what is the P(Content) in bayes formula

Answer 25

the probability of the data independent of the class and is treated like a normalization factor

Question 26

what is the maximum a posteriori (MAP) decision rule

Answer 26

y = maxP(Y|X) = P(X|Y)P(Y) ------------------ P(X) = P(X|Y)P(Y)

Question 27

why is estimating P(content |spam) easier in practice than estimating P(spam |content)

Answer 27

because of the naive independence assumption we assume that the occurrence of each feature given the class is indepented of the occurance/non occurance of any other feature given the class

Question 28

what can we do when probabilities are independent

Answer 28

we can multiply probabilities ie P(f1|spam)x.... P(fn|spam)

Question 29

how would we estimate the priors in spam vs ham

Answer 29

ex P(spam) = num(spam emails in training set)/ num(all emails in trainingset) P(ham) = num(ham emails in training set)/ num(all emails in trianing set) note all priors in the set should sum up to one spam + ham = 1

Question 30

how to calculate feature probabilities ex what is the chance of 'lottery' given its spam

Answer 30

P("Lottery"|spam) = num(spam emails with 'lottery in training set) ---------------------------------------- num(spam emails in training set) note that all of the feature probabilities for each word should sum up to one for both spam and ham cases

Question 31

what are some ways we can evalutate the success of our algorithm

Answer 31

accuracy, confusion matrix precision, recall, f1

Question 32

what is formula for accuracy

Answer 32

correct/ (correct+incorrect) not ideal for unbalanced classes

Question 33

what is a confusion matrix

Answer 33

A confusion matrix is a table used to evaluate the performance of a classification model by comparing predicted and actual outcomes. It shows True Positives (TP), True Negatives (TN), False Positives (FP), and False Negatives (FN). its fr positive fr negative predicted pos predicted neg

Question 34

why is a confusion matrix better than accuracy score

Answer 34

It is useful because it provides detailed insights into model performance, helps calculate metrics like accuracy, precision, recall, and F1-score, and highlights specific areas where the model may be making errors.

Question 35

what is precision

Answer 35

Precision: Measures how many predicted positives are actually correct. Formula: TP / (TP + FP)

Question 36

what is recall

Answer 36

Recall: Measures how many actual positives were correctly predicted. Formula: TP / (TP + FN)

Question 37

what is f1

Answer 37

F1-Score: Harmonic mean of precision and recall, balancing both. Formula: 2 × (Precision × Recall) / (Precision + Recall)