Natural Language Processing Cheat Sheet 2026

The 30 highest-yield Natural Language Processing facts, distilled from real exam questions. Print it, save it as a PDF, or study it here — free, no sign-up.

1. What does text mining stemming mean? → Reducing a word to its root
2. What is a bag-of-words (BoW) representation? → A text representation that counts word occurrences while ignoring word order
3. What is coreference resolution? → Determining when two or more expressions in a text refer to the same real-world entity
4. Which parsing strategy processes input left-to-right and builds the parse bottom-up using a stack and input buffer? → Shift-reduce parsing
5. What is the role of part-of-speech (POS) tagging in the NLP pipeline? → It assigns grammatical categories (noun, verb, adjective, etc.) to each token
6. What is extractive question answering? → Selecting a span of text from a given passage as the answer to a question
7. What is the primary innovation of the Transformer architecture over RNNs? → It uses self-attention to process all tokens in parallel rather than sequentially
8. What is the main limitation of n-gram language models? → They suffer from data sparsity because higher-order n-grams rarely appear in training data
9. Morphological segmentation: What is it? → Separate words into individual morphemes and identify the class of the morphemes
10. What does constituency parsing produce? → A hierarchical tree of phrases grouped by grammatical roles
11. An application of Google Translate is ___. → Information retrieval
12. What is text categorization (document classification)? → Assigning predefined category labels to documents based on their content
13. The Penn Treebank (PTB) uses which annotation scheme? → Phrase-structure (constituency) trees with bracket notation
14. Why does NLP employ named entity recognition? → Classify entities into predefined labels
15. Finding "bridging relationships" involving referring phrases is part of the broader coreference resolution problem. → TRUE
16. What is the purpose of lowercasing text during NLP preprocessing? → To reduce vocabulary size by treating 'Apple' and 'apple' as the same token
17. The primary difficulty with NLP is ________. → Handling Ambiguity of Sentences
18. What is a word embedding in NLP? → A dense, low-dimensional vector representation of a word that captures semantic meaning
19. What is Byte-Pair Encoding (BPE) used for in NLP? → Subword tokenization to handle rare and out-of-vocabulary words
20. What is tokenization in NLP? → Splitting text into individual units such as words or subwords
21. What is sentiment analysis in NLP? → The task of determining the emotional tone or opinion expressed in a piece of text
22. Which tagging scheme is commonly used for NER to mark entity boundaries? → BIO (Beginning, Inside, Outside) tagging
23. What is constituency parsing? → Analyzing a sentence into nested hierarchical phrases using a context-free grammar
24. Which technique assigns a probability to each word in a vocabulary given the preceding context? → Language modeling
25. What does TF-IDF stand for in NLP? → Term Frequency–Inverse Document Frequency
26. Which of the following lists the main NLP tasks? → All of the mentioned
27. In dependency parsing, what does a directed arc from word A to word B represent? → A is the head and B is the dependent
28. Machine learning, particularly statistical machine learning, is the foundation of contemporary NLP algorithms. → TRUE
29. What does Natural Language Processing (NLP) entail? → All of the mentioned
30. Which algorithm can parse ALL context-free grammars (not just CNF) and runs in O(n³) time? → Earley's algorithm