Question Bank
NLP interview questions
Text classification and document retrieval call for different choices. Use these questions to review text representations, language-model training and evaluation. Distinguish properties of the model from the data and the way it is used.
Showing 20 of 76 questions
What is TF-IDF and how is it used in natural language processing?
Explain how the Word2Vec method works and what is the difference between CBOW and Skip-gram.
What is the main idea behind the BERT model and how does it differ from previous models?
Explain what self-attention is and how it differs from cross-attention.
Compare temperature sampling and top-k sampling. In what scenarios would each be preferable?
What is beam search, and how does it differ from greedy approach?
Explain how BERT's pre-training works, including MLM and NSP.
When and why should fine-tuning be used for transformer models?
What is the role of RLHF (Reinforcement Learning from Human Feedback) in training language models?
Explain the difference between CBOW and Skip-gram in the context of word2vec.
When and why is it preferable to use GloVe over word2vec?
How does the self-attention mechanism work in transformers?
Explain how BERT works and how the next sentence prediction (NSP) is implemented.
Compare and contrast the tokenization methods BPE and WordPiece.
Why are contextual embeddings used in ELMo and how do they differ from static embeddings?
What are the main principles of how the T5 model works and what makes it unique?
Explain what BERT is and what it is used for in natural language processing tasks.
Prepare for your next interview with Vibe Interview.
Download Vibe Interview