Pre-trained embedding usage in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a pre-trained embedding model using gensim.

NLP

from gensim.models import KeyedVectors
embedding_model = KeyedVectors.load_word2vec_format('[1]', binary=True)

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

Aglove.6B.100d.txt

BGoogleNews-vectors-negative300.bin

Cfasttext.vec

Drandom_vectors.txt

Attempts:

3 left

💡 Hint

Common Mistakes

Using a text file instead of a binary file for Word2Vec loading.

Confusing GloVe or FastText files with Word2Vec binary format.

The GoogleNews-vectors-negative300.bin file is a common pre-trained Word2Vec binary format model used with gensim.

2fill in blank

medium

Complete the code to get the vector for the word 'apple' from the embedding model.

NLP

vector = embedding_model['[1]']

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

Aapple

Bfruit

Cbanana

Dorange

Attempts:

3 left

💡 Hint

Common Mistakes

Using a different word than 'apple'.

Not using quotes around the word.

To get the vector for the word 'apple', you access the embedding model with the key 'apple'.

3fill in blank

hard

Fix the error in the code to check if the word 'computer' is in the embedding model vocabulary.

NLP

if '[1]' in embedding_model.key_to_index:
    print('Found')
else:
    print('Not found')

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

Avocab

Bembedding_model

Ckey_to_index

Dcomputer

Attempts:

3 left

💡 Hint

Common Mistakes

Checking the wrong variable or attribute.

Not using quotes around the word.

To check if 'computer' is in the vocabulary, you check if the string 'computer' is in embedding_model.key_to_index.

4fill in blank

hard

Fill both blanks to create a dictionary of word vectors for words longer than 5 characters.

NLP

word_vectors = {word: embedding_model[word] for word in embedding_model.key_to_index if [1] [2] 5}

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

Alen(word)

B>

C<

Dword

Attempts:

3 left

💡 Hint

Common Mistakes

Using the wrong comparison operator.

Using the word variable instead of its length.

We use len(word) to get the length of the word and check if it is greater than 5.

5fill in blank

hard

Fill all three blanks to create a list of cosine similarities between 'king' and other words starting with 'q'.

NLP

from gensim.matutils import [1]
similarities = [[2](embedding_model['king'], embedding_model[word]) for word in embedding_model.key_to_index if word.startswith('[3]')]

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

Acossim

Cq

Dcosine

Attempts:

3 left

💡 Hint

Common Mistakes

Using the wrong function name for cosine similarity.

Not filtering words starting with 'q'.

The function cossim computes cosine similarity. We use it to compare 'king' with words starting with 'q'.