1. What is NLU (Natural language understanding) ?
Answer: It’s about understanding of natural language. How humans are communicating in different scenarios.
2. What is Corpus ?
Answer: It’s a collection of text documents.
3. What is N- Gram, Unigram, Bigram and Trigram?
Answer: It’s about word analysis, unigram means single word, bigram means double words and trigram means tripple word.
4. What is Language modeling ?
Answer: A statistical language model is a probability distribution over sequences of words. For instance if a given a sequence say of length m, it assigns a probability to the whole sequence. This model provides context to distinguish between words and phrases that sound similar.
5. What is Latent semantic analysis ?
Answer: Latent semantic analysis is a technique in natural language processing, in particular distributional semantics, of analyzing relationships between a set of documents and the terms.