Word embeddings concept (Word2Vec) in ML Python - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the Word2Vec model from gensim.

ML Python

from gensim.models import [1]

Drag options to blanks, or click blank then click option'

AWord2Vec

Bword2vec

CWordVec

DWordEmbedding

Attempts:

3 left

💡 Hint

Common Mistakes

Using lowercase 'word2vec' which is incorrect.

Using 'WordVec' missing the '2'.

Using 'WordEmbedding' which is not the class name.

The correct class name to import is 'Word2Vec' with capital W and V.

2fill in blank

medium

Complete the code to train a Word2Vec model on sentences.

ML Python

model = Word2Vec(sentences=[1], vector_size=100, window=5, min_count=1, workers=4)

Drag options to blanks, or click blank then click option'

Asentences

Bdata

Ccorpus

Dtext

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'sentences' as a variable when it is not defined.

Using 'text' which is usually raw string, not tokenized sentences.

Using 'data' which is too generic and may not be defined.

The training data variable is commonly called 'corpus' representing the list of sentences.

3fill in blank

hard

Fix the error in accessing the vector for the word 'king'.

ML Python

vector = model.wv[[1]]

Drag options to blanks, or click blank then click option'

A'King'

Bking

C['king']

D'king'

Attempts:

3 left

💡 Hint

Common Mistakes

Using capitalized 'King' which may not be in vocabulary.

Using the variable king without quotes causing NameError.

Using a list ['king'] which is invalid for key access.

The word must be a lowercase string 'king' to match the vocabulary key.

4fill in blank

hard

Fill both blanks to find the most similar words to 'queen'.

ML Python

similar_words = model.wv.[1](positive=[[2]], topn=5)

Drag options to blanks, or click blank then click option'

Amost_similar

B'queen'

C'king'

Dsimilar_words

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'similar_words' as method which is incorrect.

Passing 'king' instead of 'queen' as the positive word.

Not using quotes around the word.

The method to find similar words is 'most_similar' and the input word must be a string 'queen'.

5fill in blank

hard

Fill both blanks to create a dictionary of word vectors for words with length greater than 4.

ML Python

word_vectors = {word: model.wv[[1]] for word in model.wv.index_to_key if len(word) [2] 4}

Drag options to blanks, or click blank then click option'

Aword

B>

C<

Dlen(word)

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'len(word)' as dictionary key which is incorrect.

Using '<' instead of '>' causing wrong filtering.

Using variable names not defined in the comprehension.

We use 'word' as the key to get vectors, and filter words with length greater than 4 using '>'.