FastText embeddings in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load FastText model from gensim.

NLP

from gensim.models import FastText
model = FastText.load('[1]')

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

Afasttext.txt

Bfasttext.bin

Cfasttext.model

Dfasttext.vec

Attempts:

3 left

💡 Hint

Common Mistakes

Using the wrong file extension like .bin or .vec which are not gensim model files.

Trying to load a text vector file instead of the model.

The FastText model is saved as a model file, typically with .model extension. Use that filename to load it.

2fill in blank

medium

Complete the code to get the vector for the word 'apple' using FastText model.

NLP

vector = model.wv.[1]('apple')

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

Aget_vector

Bword_vec

Cvector

Dembedding

Attempts:

3 left

💡 Hint

Common Mistakes

Using model.wv.vector which does not exist.

Using model.wv.word_vec which is deprecated.

The correct method to get a word vector in gensim FastText is get_vector().

3fill in blank

hard

Fix the error in the code to train a FastText model on sentences.

NLP

from gensim.models import FastText
sentences = [['hello', 'world'], ['fasttext', 'embedding']]
model = FastText(sentences=[1], vector_size=50, window=3, min_count=1, epochs=10)

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

Asentence

Bcorpus

Cdata

Dsentences

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'sentence' instead of 'sentences' causes a TypeError.

Passing data with wrong parameter name.

The parameter name for training data in FastText is 'sentences'.

4fill in blank

hard

Fill both blanks to create a FastText model and train it on data.

NLP

model = FastText([1], vector_size=100, window=5, min_count=2)
model.[2](sentences, total_examples=len(sentences), epochs=5)

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

Asentences

Btrain

Cfit

Dfit_transform

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'fit' or 'fit_transform' which are not methods of gensim FastText.

Not passing the training data correctly.

You pass the training data as 'sentences' and call the 'train' method to train the model.

5fill in blank

hard

Fill both blanks to create a dictionary of word vectors for words longer than 3 characters.

NLP

word_vectors = {word: model.wv.[1](word) for word in model.wv.index_to_key if len(word) [2] 3 and word.isalpha()}
filtered_vectors = {k: v for k, v in word_vectors.items() if v is not None and v.any()}
print(len(filtered_vectors))

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

Aget_vector

B>

C<

D==

Attempts:

3 left

💡 Hint

Common Mistakes

Using incorrect comparison operators like '<' or '=='.

Using wrong method names to get vectors.

Use get_vector to get vectors, filter words with length > 3.