What is the goal of learning word vectors?1 pointFind the hidden or latent features in a text.Given a word, predict which words are in its vicinity.Labelling a text corpus, so a human doesn’t have to do it.Determine the vocabulary in the codebook.

The goal of learning word vectors, also known as word embeddings, is to create a numerical representation of words that captures their meanings, semantic relationships, and the contexts in which they are used. This is achieved through the following steps:

1. Find the hidden or latent features in a text: Word vectors are capable of capturing a number of latent features of a text, such as its sentiment, topic, or other abstract concepts that are not explicitly stated.

2. Given a word, predict which words are in its vicinity: This is the principle behind the Word2Vec model, which is trained to understand the context in which words appear. The model makes predictions about the words that are likely to appear in the vicinity of a given word, and these predictions are used to adjust the word vectors.

3. Labelling a text corpus, so a human doesn’t have to do it: Word vectors can be used to automate the process of labelling a text corpus. For example, they can be used to identify the topics of documents or the sentiment of social media posts.

4. Determine the vocabulary in the codebook: The vocabulary of a text corpus is the set of unique words that it contains. Word vectors can be used to identify this vocabulary, which is a crucial step in many natural language processing tasks.