NLP Word Embeddings 2

Question 1

Which property of word2vec embeddings allows the analogy 'king - man + woman ≈ queen' to work?

Accepted Answer

Linear relationship encoding of semantic roles

Answer

Word2vec encodes semantic relationships as linear offsets in the embedding space, enabling arithmetic analogies.

Question 2

What is the primary difference between the Skip-gram and CBOW architectures in word2vec?

Accepted Answer

Skip-gram predicts context from a target word; CBOW predicts a target from context words

Answer

Skip-gram takes a center word and predicts surrounding context words, while CBOW averages context words to predict the center word.

Question 3

What does 'negative sampling' accomplish in word2vec training?

Accepted Answer

Approximates the softmax by training on a small set of noise words alongside the target

Answer

Negative sampling makes training tractable by updating weights only for the target word and a small random sample of non-target words.

Question 4

In GloVe (Global Vectors), what is the main training objective?

Accepted Answer

Factorize the global word co-occurrence matrix into low-rank embeddings

Answer

GloVe directly factorizes the log of the global co-occurrence count matrix to produce word vectors.

Question 5

Which evaluation method tests word embeddings by checking whether cosine similarity rankings match human-rated similarity scores?

Accepted Answer

Intrinsic evaluation via word similarity benchmarks

Answer

Intrinsic evaluation compares embedding-derived similarity rankings against human-annotated datasets like WordSim-353.

NLP Practice Test