NLP - Language modelling and POS tagging

What is the purpose of a language model in NLP?

• • Generating human-like text

• • Translating text between languages

• • Identifying named entities

• • Extracting features from text

Which one of the following tasks is not about NLP?

• 1. Forecasting the stock market leveraging business news articles

• 1. Classifying which emails should go in the spam folder

• 1. Translating natural language into SQL queries

• 1. Detecting fires from satellite images

What’s the goal of a language model?

• 1. Classifying the language of a text

• 1. Learning the distribution of the words in a language

• 1. Detecting whether a text is grammatically correct or not

• 1. Containing all the rules needed to generate correct texts in a language

What’s the name of the depicted NLP task?

• 1. Relation Extraction

• Named-Entity Recognition

• 1. Keyword and Key phrases Extraction

What is the purpose of named entity recognition (NER) in NLP?

• • 
    Identifying grammatical structure

• • Recognizing entities such as names, locations, and organizations in text

• • Classifying text sentiment

• • Tokenizing text

In the context of NLP, what does the acronym "POS" stand for?

• 
  Parts-of-Speech

• Positive Output 

• Plain Old Search  

• Preprocessed Object Store

In NLP, what does the term "named entity" refer to?

• Specific words and phrases   

    

• Generic nouns 

• Pronouns and conjunctions

• Verbs and adjectives

Which NLP technique involves assigning a label or category to each word in a text like "noun", "verb" or "adjective"?

• 
  Named Entity Recognition

• Sentiment Analysis

• Part-of-Speech Tagging

• Text Classification

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 : 30250 purple: 12321 purple snow : 0

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

• 12321

• 30250

• 0.4073

• 0

Answer explanation

Using Maximum Likelihood Estimate,

P(snow|purple) = count(purple snow) / count(purple) = 0/12321 = 0

N-grams are defined as the combination of N keywords together. How many bi-grams can be generated from the given sentence: Gandhiji is the father of our nation

• 7  

• 6  

• 8   

• 9

Answer explanation

Bigrams are sequence of two words that are appearing adjacent in a sentence.

In the given sentence, we have 6 bigrams, ‘Gandhiji is’, ‘is the’, ‘the father’, ‘father of’, ‘of our’, and ‘our nation’.