Semantic networks: word2vec?

Question

I have some doubts on how to represent the relationships between words in texts. Let’s suppose I have two sentences like these:

Angela Merkel is a German politician who has been Chancellor of Germany since 2005.

What I would expect is a connection between name Angela and Merkel (Angela is the name, Merkel the surname) who is German and politician and Chancellor.

I read about the use of word2vec to determine the semantic structure of a sentence. My question is therefore if this model can allow me to determine such semantic structure or if another method would be better.

Answer 1

There are a few models that are trained to analyse a sentence and classify each token (or recognise dependencies between words).

• Part of speech tagging (POS) models assign to each word its function (noun, verb, ...) - have a look at this link

• Dependency parsing (DP) models will recognize which words go together (in this case Angela and Merkel for instance) - check this out

• Named entity recognition (NER) models will for instance say that "Angela Merkel" is a person, "Germany" is a country ... - another link