NLP problems
Tokenize, embed, compare. Text into numbers.
420 problems152 Easy185 Medium83 Hard
50 problems
Tokenization
nlp-001
Bag of Words
nlp-002
TF-IDF
nlp-003
N-grams
nlp-004
Cosine Similarity of Token Vectors
nlp-005
Punctuation-Stripping Tokenizer
nlp-006
Whitespace Tokenizer with Offsets
nlp-007
Character N-grams
nlp-008
Stopword Removal
nlp-009
Naive Suffix Stemmer
nlp-010
Simple Plural Normalization
nlp-011
Lemmatization Map Lookup
nlp-012
Vocabulary with Minimum Frequency
nlp-013
Vocabulary Index Mapping
nlp-014
One-Hot Token Encoding
nlp-015
Type-Token Ratio
nlp-016
Most Common Token
nlp-017
Hapax Count
nlp-018
Sentence Splitter
nlp-019
BPE Merge Step
nlp-020
BPE Encode with Merges
nlp-021
WordPiece Longest-Match Tokenizer
nlp-022
Unigram Log Probability
nlp-023
Bigram Counts
nlp-024
Bigram Probabilities with Laplace Smoothing
nlp-025
Perplexity from Probabilities
nlp-026
Bigram Log-Likelihood of a Sentence
nlp-027
Add-k Smoothing
nlp-028
Backoff Probability
nlp-029
Interpolation Probability
nlp-030
Levenshtein Edit Distance
nlp-031
Damerau Input with Adjacent Transposition
nlp-032
Jaro Similarity
nlp-033
Jaro-Winkler Prefix Boost
nlp-034
Jaccard Token Similarity
nlp-035
Dice Coefficient of Tokens
nlp-036
Term Frequency
nlp-037
Inverse Document Frequency
nlp-038
TF-IDF for a Single Term
nlp-039
BM25 Score for a Single Term
nlp-040
Build an Inverted Index
nlp-041
Positional Index Search
nlp-042
Boolean AND Query
nlp-043
Boolean OR Query
nlp-044
Phrase Query Check
nlp-045
Wildcard Prefix Match
nlp-046
Fuzzy Match within Edit Distance 1
nlp-047
Longest Common Subsequence of Tokens
nlp-048
Softmax over Attention Scores
nlp-049
Scaled Dot-Product Attention
nlp-050
Showing 50 of 420 problems.