Word vectorization captures which kind of linguistic relationships?Question 11Answera.Semanticb.Syntactic

Word vectorization captures both semantic and syntactic linguistic relationships.

Semantic relationships: Word vectorization, especially methods like Word2Vec, are capable of capturing semantic relationships between words. For example, words that are semantically similar (like 'king' and 'queen' or 'dog' and 'puppy') will have similar vector representations. This is because these models are trained on large amounts of text data, and words that appear in similar contexts tend to have similar meanings.

Syntactic relationships: Word vectorization can also capture syntactic relationships. For example, the relationship between 'walking' and 'walked' is similar to the relationship between 'swimming' and 'swam'. In the vector space, this relationship is represented as a spatial relationship, meaning the 'distance' from 'walking' to 'walked' is similar to the 'distance' from 'swimming' to 'swam'. This shows that the model has learned something about the grammatical rule of forming the past tense in English.