Training Word2Vec with Gensim in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the Word2Vec model from gensim.

NLP

from gensim.models import [1]

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

AWordToVec

BWord2Vec

CWordVec

Dword2vec

Attempts:

3 left

💡 Hint

Common Mistakes

Using lowercase 'word2vec' which is not the class name.

Misspelling the class name like 'WordVec' or 'WordToVec'.

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

2fill in blank

medium

Complete the code to initialize a Word2Vec model with vector size 100.

NLP

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

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

A300

B50

C200

D100

Attempts:

3 left

💡 Hint

Common Mistakes

Using vector size too small or too large without reason.

Confusing vector_size with window size.

The vector size parameter controls the size of word vectors. Here, 100 is a common choice.

3fill in blank

hard

Fix the error in the code to train the Word2Vec model on sentences.

NLP

model.[1](sentences)

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

Atrain

Bfit

Clearn

Dfit_transform

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'fit' which is common in scikit-learn but not in gensim.

Using 'fit_transform' which is not a Word2Vec method.

The correct method to train a Word2Vec model is train.

4fill in blank

hard

Fill both blanks to create a dictionary of word vectors for words with frequency above 2.

NLP

word_vectors = {word: model.wv.[1](word) for word in model.wv.index_to_key if model.wv.get_vecattr(word, '[2]') > 2}

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

Aget_vector

Bcount

Cfrequency

Dvector

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'vector' instead of 'get_vector' to get word vectors.

Using 'frequency' instead of 'count' for word frequency attribute.

get_vector retrieves the vector for a word, and count is the attribute for word frequency.

5fill in blank

hard

Fill all three blanks to save the trained model and then load it back.

NLP

model.[1]('word2vec.model')
loaded_model = Word2Vec.[2]('word2vec.model')
vector = loaded_model.wv.[3]('example')

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

Asave

Bload

Cget_vector

Dtrain

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'train' instead of 'save' or 'load'.

Using 'vector' instead of 'get_vector' to get word vectors.

Use save to save the model, load to load it, and get_vector to get a word's vector.