FastText embeddings in NLP - Cheat Sheet & Quick Revision

Recall & Review

beginner

What are FastText embeddings?

FastText embeddings are word representations that include information about subwords (small parts of words). This helps capture meanings of rare or new words by looking at their parts.

intermediate

How does FastText differ from traditional word embeddings like Word2Vec?

Unlike Word2Vec, which treats each word as a single unit, FastText breaks words into smaller pieces called n-grams. This helps it understand words it has never seen before by combining these pieces.

beginner

Why are subword embeddings useful in FastText?

Subword embeddings help FastText handle rare words, misspellings, and new words by learning from smaller parts of words. This makes the model more flexible and accurate.

intermediate

What is the role of n-grams in FastText embeddings?

N-grams are sequences of characters inside words. FastText learns embeddings for these n-grams and combines them to form the word's embedding, capturing internal word structure.

advanced

How can FastText embeddings improve performance on languages with rich morphology?

Because FastText uses subword information, it can better understand word variations and endings common in languages with rich morphology, improving representation and downstream task results.

What is the main advantage of FastText embeddings over Word2Vec?

A They ignore word order

B They require less training data

C They only work with fixed vocabulary

D They use subword information to handle rare words

FastText embeddings use subword (n-gram) information, allowing them to represent rare or unseen words better than Word2Vec.

In FastText, what are n-grams?

A Complete sentences

B Sequences of characters inside words

C Individual words

D Paragraphs

N-grams in FastText are sequences of characters within words, used to build subword embeddings.

Why does FastText perform well on misspelled words?

A Because it uses a dictionary lookup

B Because it ignores spelling

C Because it uses subword parts to build embeddings

D Because it trains on misspelled words only

FastText uses subword embeddings, so even if a word is misspelled, its parts can still be recognized and represented.

Which of these is NOT a feature of FastText embeddings?

A Ignoring word context completely

B Handling out-of-vocabulary words

C Using character n-grams

D Capturing subword information

FastText embeddings do consider word context during training; they do not ignore it.

FastText embeddings are especially useful for which type of languages?

A Languages with rich morphology

B Languages with no grammar

C Languages with only short words

D Languages without alphabets

FastText's use of subword information helps it handle languages with many word forms and endings, known as rich morphology.

Explain how FastText embeddings use subword information to represent words.

Think about how smaller parts of words help understand the whole word.

Describe why FastText embeddings can improve performance on languages with many word forms.

Consider how word parts change in different forms.

Practice

1. What is the main advantage of FastText embeddings compared to traditional word embeddings?

easy

A. It considers subword information to handle rare or misspelled words.

B. It only works with whole words and ignores word parts.

C. It requires more memory because it stores entire sentences.

D. It uses images instead of text for embeddings.

Solution

1. Step 1: Understand FastText's approach to word representation

   FastText breaks words into smaller parts called n-grams, which helps it learn better representations for rare or misspelled words.

2. Step 2: Compare with traditional embeddings

   Traditional embeddings like Word2Vec treat words as whole units and cannot handle unseen or misspelled words well.

3. Final Answer:

   It considers subword information to handle rare or misspelled words. -> Option A

4. Quick Check:

   FastText uses subwords = A [OK]

Hint: Remember: FastText uses word parts, not just whole words [OK]

Common Mistakes:

• Thinking FastText ignores subwords
• Confusing FastText with image embeddings
• Assuming FastText stores full sentences

2. Which of the following is the correct way to load pretrained FastText embeddings using the Gensim library in Python?

easy

A. model = gensim.models.FastText.load_fasttext_format('cc.en.300.bin')

B. model = gensim.load('fasttext_model.bin')

C. model = gensim.models.Word2Vec.load('cc.en.300.bin')

D. model = gensim.models.KeyedVectors.load_word2vec_format('cc.en.300.bin', binary=True)

Solution

1. Step 1: Identify the correct Gensim function for FastText pretrained vectors

   Gensim uses KeyedVectors.load_word2vec_format with binary=True to load FastText pretrained vectors in .bin format.

2. Step 2: Check other options for correctness

   model = gensim.models.FastText.load_fasttext_format('cc.en.300.bin') uses a non-existent method. model = gensim.models.Word2Vec.load('cc.en.300.bin') loads Word2Vec models, not FastText. model = gensim.load('fasttext_model.bin') is invalid syntax.

3. Final Answer:

   model = gensim.models.KeyedVectors.load_word2vec_format('cc.en.300.bin', binary=True) -> Option D

4. Quick Check:

   Use KeyedVectors.load_word2vec_format for FastText .bin [OK]

Hint: Use KeyedVectors.load_word2vec_format with binary=True for FastText [OK]

Common Mistakes:

• Using Word2Vec.load for FastText files
• Calling non-existent load_fasttext_format method
• Forgetting binary=True for .bin files

3. Given the following Python code using Gensim FastText model:

from gensim.models import FastText
sentences = [['cat', 'sat', 'on', 'mat'], ['dog', 'barked']]
model = FastText(sentences, vector_size=10, window=3, min_count=1, epochs=5)
print(model.wv['cat'])

What will be the output type of model.wv['cat']?

medium

A. A numpy array representing the vector embedding of 'cat'

B. An integer representing the frequency of 'cat'

C. A list of words similar to 'cat'

D. A string with the word 'cat'

Solution

1. Step 1: Understand what model.wv['word'] returns in Gensim FastText

   model.wv['cat'] returns the vector embedding as a numpy array representing the word 'cat'.

2. Step 2: Check other options for output type

   A list of words similar to 'cat' is for similar words, not the vector. An integer representing the frequency of 'cat' is frequency, which is not returned here. A string with the word 'cat' is just the word string, not the vector.

3. Final Answer:

   A numpy array representing the vector embedding of 'cat' -> Option A

4. Quick Check:

   model.wv['word'] returns vector array [OK]

Hint: model.wv['word'] gives vector array, not word list [OK]

Common Mistakes:

• Expecting a list of similar words instead of vector
• Thinking it returns frequency count
• Confusing word string with vector

4. You trained a FastText model but get a KeyError when trying to get the vector for a word like 'unseenword'. What is the most likely cause and fix?

medium

A. The word is not in the training data; increase epochs to fix.

B. You used Word2Vec instead of FastText; switch to FastText to handle unseen words.

C. FastText cannot handle unseen words; use a different embedding method.

D. The model was not saved properly; reload the model correctly.

Solution

1. Step 1: Understand FastText's ability with unseen words

   FastText can generate vectors for unseen words by using subword information, unlike Word2Vec.

2. Step 2: Identify cause of KeyError

   If you get KeyError for unseen words, likely you trained or loaded a Word2Vec model, not FastText.

3. Final Answer:

   You used Word2Vec instead of FastText; switch to FastText to handle unseen words. -> Option B

4. Quick Check:

   Use FastText (not Word2Vec) for unseen words [OK]

Hint: KeyError on unseen words means Word2Vec used, not FastText [OK]

Common Mistakes:

• Assuming FastText can't handle unseen words
• Trying to fix by increasing epochs only
• Ignoring model type mismatch

5. You want to improve a text classification model's ability to understand misspelled words using FastText embeddings. Which approach is best?

hard

A. Use one-hot encoding instead of embeddings to avoid misspellings.

B. Use pretrained Word2Vec embeddings and ignore misspelled words during training.

C. Train FastText on your dataset with subword information enabled and use its vectors as input features.

D. Replace all misspelled words with a special token before training with any embeddings.

Solution

1. Step 1: Identify how FastText handles misspelled words

   FastText uses subword (character n-gram) information, so it can create embeddings for misspelled or rare words.

2. Step 2: Choose the best approach to leverage this feature

   Training FastText on your dataset with subword info enabled and using its vectors as features helps the model understand misspellings better.

3. Final Answer:

   Train FastText on your dataset with subword information enabled and use its vectors as input features. -> Option C

4. Quick Check:

   Train FastText with subwords for misspellings [OK]

Hint: Train FastText with subwords to handle misspellings [OK]

Common Mistakes:

• Using Word2Vec ignoring misspellings
• Replacing misspellings with tokens loses info
• Using one-hot encoding loses semantic info