wayground logo

Free Printable Worksheets

Font size

S
M
L
XL
Worksheets

NLP301c quiz6

Total questions: 20

Worksheet time: 11mins

Name
Class
Date
1.

A transducer maps between FST one set of _________and another.

a)

Words

b)

Letters

c)

Symbols

d)

Sentences

2.

Benefits of sentiment analysis includes:

a)

Sentiment analysis helps businesses process huge amounts of data in an efficient and cost-effective way.

b)

Sentiment analysis models can help you immediately identify these kinds of situations and gauge brand sentiment, so you can take action right away.

c)

Tagging text by sentiment is highly subjective, influenced by personal experiences, thoughts, and beliefs. By using a centralized sentiment analysis system, companies can apply the samecriteria to all of their data, helping them improve accuracy and gain better insights.

d)

All of the above

3.

the sense of the word depends on the words of that particular word.

a)

Relating

b)

Same

c)

Neighboring

d)

Dependent

4.

Given a stream of text, Named Entity Recognition determines which pronoun maps to which noun.

a)

True

b)

False

5.

_________ is a vocabulary, a list of words, a dictionary.

a)

Corpus

b)

WordNet

c)

Lexicon

d)

None of the above

6.

You have created a document term matrix of the data, treating every tweet as one document. Which of the following is correct, in regards to document term matrix?

a)

Removal of stopwords from the data will affect the dimensionality of data

b)

Normalization of words in the data will reduce the dimensionality of data

c)

Converting all the words in lowercase will not affect the dimensionality of the data

7.

Machine Learning & Statistical Inference are the popular methods for implementing___.

a)

Lexical Analysis

b)

Tokens and Quantifiers

c)

NLP

d)

None of the above

8.

Natural Language generation is the main task of Natural language processing.

a)

True

b)

False

9.

Assume a corpus with 350 tokens in it. We have 20 word types in that corpus (V = 20). The frequency (unigram count) of word types "short" and "fork" are 25 and 15 respectively. Which of the following is the probability of "short" (PMLE("short"))?

a)

25/350

b)

26/370

c)

26/350

d)

25/370

10.

Social Media platforms are the most intuitive form of text data. You are given a corpus of complete social media data of tweets. How can you create a model that suggests the hashtags?

a)

Perform Topic Models to obtain most significant words of the corpus

b)

Train a Bag of Ngrams model to capture top n-grams - words and their combinations

c)

Train a word2vector model to learn repeating contexts in the sentences

d)

All of these

11.

It focuses about the proper ordering of words which can affect its meaning.

a)

Syntax Analysis

b)

Semantic Analysis

c)

Lexical Analysis

d)

Pragmatic Analysis

12.

___________ is the task of identifying and categorizing key information (entities) in text.

a)

Text Summarization

b)

Extractive Summarization

c)

Abstractive Summarization

d)

Named entity recognition

13.

Derivational morphology changes both the meaning and the content of a listeme, while inflectional morphology doesn't change the meaning, but changes the function.

a)

Meaning, Content, Listeme, function

b)

Meaning, Listeme, content, function

c)

Content, meaning, function, Listeme

d)

Function, content, meaning, Listeme

14.

Which of the following techniques can be used to compute the distance between two word vectors in NLP?

a)

Lemmatization

b)

Euclidean distance

c)

Cosine Similarity

d)

N-grams

15.

______ is the interpretation and classification of emotions (positive, negative and neutral) within text data using text analysis techniques.

a)

Lexical analysis

b)

Syntactical analysis

c)

Hybrid analysis

d)

Sentiment Analysis

16.

Which is not regex command from following?

a)

Strsplit ()

b)

Strjoin()

c)

Grep()

d)

Gsub()

17.

When semantic ambiguity occurs?

a)

when the meaning of the words themselves can be misinterpreted.

b)

Words having many meanings.

c)

Both a & b

d)

None of the above

18.

Trains two independent LSTM language model left to right and right to left and shallowly concatenates them

a)

GPT

b)

BERT

c)

ULMFit

d)

ELMo

19.

Let us assume that CorpA is a corpus of English with approximately 560 million tokens. Following are the counts of unigrams and bigrams from the corpus;

snow | purple | snow

30250 | 12321 |0

Find the probability of P(snow|purple) using maximum likelihood estimation without smoothing.

a)

12321

b)

30250

c)

0.4073

d)

0

20.

POS is the process of marking up a word in a text as corresponding to a particular part of speech, based on both its _________and its_________

a)

Sets & meaning

b)

Definition & contexts

c)

Analysis & reporting

d)

Sets & definitions