Scribd
Upload
4K views12 pages

Text Document Classification Quiz: Q1. Classification Techniques Have Been Applied To

This document contains a 20 question quiz on text document classification techniques. The questions cover topics like classification algorithms including k-nearest neighbors, naive Bayes, support vector machines and Rocchio classification. Vector space models and cosine similarity are discussed. Multi-class classification techniques like one-versus-all and all-versus-all are addressed. The role of kernels and slack variables in support vector machines for nonlinear classification is summarized.

Uploaded by

Shabs
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
4K views12 pages

Text Document Classification Quiz: Q1. Classification Techniques Have Been Applied To

This document contains a 20 question quiz on text document classification techniques. The questions cover topics like classification algorithms including k-nearest neighbors, naive Bayes, support vector machines and Rocchio classification. Vector space models and cosine similarity are discussed. Multi-class classification techniques like one-versus-all and all-versus-all are addressed. The role of kernels and slack variables in support vector machines for nonlinear classification is summarized.

Uploaded by

Shabs
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 12

Text Document Classification Quiz

Q1. Classification techniques have been applied to

(A) Spam filtering,

(B) Language identification,

(C) Automatically determining the degree of readability of a text, either


to find suitable materials for different age groups or reader types

(D)only (A) and (B)

Q2. Automatic document classification techniques include:

(A) K-nearest neighbour algorithms

(B) Support vector machines (SVM)

(C) Latent semantic indexing

(D) Naive Bayes classifier

Q3. Select the correct statements related to "Vector Space


Classification"
(A) Vector Space Representation for classification: represents each
document as a vector with sentences as columns and document as
rows

(B) In vector space classification, training set corresponds to classes in


the vector space.

(C) In vector space classification, training set corresponds to a labeled


set of points (or, equivalently, vectors) in the vector space.

(D) Vector Space Representation for classification: represents each


document as a vector with one real-valued component, usually a tf-idf
weight, for each term

Q4. Select the correct statements related to Rocchio Text Classification

(A) Uses sentence vector representation of documents

(B) Assign test documents to the category with the closest prototype
vector based on cosine similarity

(C) Use standard tf-idf weighted vectors to represent text documents

(D) Relevance feedback (2-class classification Relevant vs. non relevant


documents) methods can be adapted for text categorization
Q5. Use cosine similarity to rank the documents D1 and D2 w.r.t. given
query Q
D1 = 2T1+3T2+5T3
D2 = 3T1+7T2+1T3
Q = 0T1+0T2+2T3

(A) Rank-1=D2, Rank2= D1; Cosine_Sim(D1,q)=0.41,


Cosine_Sim(D2,q)=0.53,

(B) Rank-1=D1, Rank2= D2; Cosine_Sim(D1,q)=0.66,


Cosine_Sim(D2,q)=0.26,

(C) Rank-1=D1, Rank2= D2; Cosine_Sim(D1,q)=0.71,


Cosine_Sim(D2,q)=0.13,

(D) Rank-1=D1, Rank2= D2; Cosine_Sim(D1,q)=0.81,


Cosine_Sim(D2,q)=0.13,

Q6. According to Rocchio Text Categorization algorithm, select the


correct statements
a1| = |a2|

b1| = |b2|

c1| = |c2|

(D) only (A) and (B)

Q7. Select the correct statements related to Rocchio classification

(A) Rocchio forms a simple representation for each class: the


centroid/prototype

(B) Classification is based on similarity to / distance from the


prototype/centroid

(C) It does not guarantee that classifications are consistent with the
given training data

(D)Only (A) and (B)

Q8. Select the correct statements related to kNN classifier

(A) In kNN classifier, NEAREST NEIGHBOR determines the decision


boundary locally

(B) Also called: (1) Case-based learning, (2) Memory-based learning and
(3) Lazy learning

(C) 1NN is not very robust

(D)only (A) and (B)

Q9. Select the correct statements related to kNN classifier (Similarity


Metrics and Complexity)

(A) For text, cosine similarity of tf.idf weighted vectors is typically most
effective.

(B) Euclidean distance is the simplest for continuous m-dimensional


instance space

(C) Hamming distance (number of feature values that differ) is the


simplest for m-dimensional binary instance space.

(D) None of these

Q10. Select the correct statements related to kNN classifier and NB


Classifier

(A) kNN has high variance and low bias.

(B) NB has low variance and high bias

(C) NB is faster than kNN.

(D) For both classifiers training dataset is necessary

Q11. Select the correct statements related to kNN classifier and NB


Classifier "Types of Classifiers"

(A) It is not possible to convert the multiclass classification problem into


a set of binary classification problems

(B) The case when the labels are just +1 or -1 called two class
classification problems

(C) When ‘I’ is related to more than two classes then it is called multi-
class classification problem
(D) It is possible to convert the multiclass classification problem into a
set of binary classification problems

Q12. Select all multi class classification techniques from given


techniques

(A) One-versus-all (OVA)

(B) All-versus-all (AVA)

(C) Error-Correcting Output-Coding (ECOC)

(D) None of these

Q13. Identify the correct technique for the given figure:


Figure: A Multi-class classifier with binary classifier

(A) One-versus-all (OVA)

(B) All-versus-all (AVA)

(C) Error-Correcting Output-Coding (ECOC)

(D) None of these

Q14. Select the correct examples of binary classifiers


(A) Decision trees,

(B) Neural networks,

(C) K-Nearest Neighbor,

(D) Support Vector Machines

Q15. Select the correct examples of Multi-Class classifiers (which


directly achieve multi-class classification, i.e., without support of binary
classifiers)

(A) Decision trees,

(B) Naive Bayes classifiers,

(C) K-Nearest Neighbor,

(D) Support Vector Machines

Q16. Select the correct statements related to "Support vector machine"

(A) SVM can be used as binary classifier

(B) SVM can be used as Multi-class Classifier


(C) SVM does not support learning to rank

(D) SVM supports learning to rank

Q17. Select the correct statements related to "Support vector machine"


with "Linear and Nonlinear classification"

(A) SVM can be used for linear classification

(B) SVM can efficiently perform non-linear classification

(C) SVM can not perform non-linear classification

(D) SVM uses kernel trick for non-linear classification

Q18. The main use of "kernel trick" is/are:

(A) Used to perform binary classification

(B) Used to perform Multi-class classification

(C) Used to perform linear classification

(D) Implicitly mapping the inputs into high-dimensional feature spaces


Q19. Identify the correct statements regarding soft margine of SVM

(A) It is a modified maximum margin idea that allows for mislabeled


examples.

(B) If there exists no hyperplane that can split the "yes" and "no"
examples, the Soft Margin method will choose a hyperplane that splits
the examples as cleanly as possible

(C) It uses the concept of slack variables

(D) None of the above

Q20. Select the correct statements related to Nonlinear classification

(A) SVM uses kernel trick for non-linear classification

(B) SVM uses the concept of slack variables for Nonlinear classification

(C) It means classification for the case of non-linear class boundary.

(D) Nonlinear classifiers uses kernel trick to achieve maximum-margin


hyperplanes.
KEYS: 1-A, B, C; 2-A, B, C, D; 3-C, D ; 4-B, D; 5-D; 6-A, B, C; 7-A, B, C; 8-A,
B, C; 9-A, B, C; 10-A, B; 11-B, C, D; 12-A, B, C; 13-A; 14-A, B, C, D; 15-C,
D; 16-A, B, D; 17-A, B, D; 18-D; 19-A, B, C; 20-A, C, D;

You might also like