PGPM NLPquiz2_Ngram, TFIDF,CosineSimilarityEtc

For two different sentences when can be the Cosine similarity factor be 1

Which process will give meaningful words

• Stemming

• Lemmatization

• Stop words

• All of the above

______ considers the value of words across the documents

• TF

• IDF

Give example of 'multiple meaning' of a sentence/word

Application of TF-IDF is in......

• Document Classification

• Topic Modelling

• Information Retrieval System

• All of the mentioned

A larger value of TD-IDF indicates

• The higher significance of the word in the sentence

• The higher significance of the word in the corpus

• The lower significance of the word in the sentence

• The lower significance of the word in the corpus

Identify the odd one out from following

• nltk

• scikit

• SpaCy

• BERT

NLTK stands for -------------

• Natural Language Toolkit

• Natural Language Technique

• Natural Language Technology

• Natural Language Tokenization Kit

Words may have multiple meanings. This leads to what type of ambiguity in NLP?

• Syntactic ambiguity

• Anaphoric ambiguity

• Semantic ambiguity

• Lexical ambiguity

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

• Lemmatization

• Euclidean distance

• Cosine Similarity

• N-grams