nltk

Splits raw text into word tokens and sentences using language-specific regex patterns and punkt sentence segmentation models. Handles edge cases like contractions ('didn't' → 'did', 'n't'), abbreviations, and punctuation via trained statistical models rather than simple whitespace splitting. The `nltk.word_tokenize()` function applies Penn Treebank tokenization conventions, preserving linguistic structure needed for downstream NLP tasks.

Assigns grammatical tags (NN, VB, JJ, IN, etc.) to tokenized words using a pre-trained averaged perceptron model trained on Penn Treebank corpus. The `nltk.pos_tag()` function takes a list of tokens and returns tuples of (word, tag) pairs. Internally uses a statistical classifier that learns tag sequences from annotated training data, enabling context-aware tagging (e.g., 'bank' tagged as NN vs VB depending on surrounding words).

Extracts semantic roles (Agent, Patient, Instrument, etc.) and predicate-argument structures from parsed sentences. NLTK provides tools for analyzing semantic relationships beyond syntactic structure, enabling developers to identify 'who did what to whom' in sentences. Uses parse trees and semantic role annotations from corpora to extract structured semantic information.

Trains and applies feature-based classifiers using decision trees and maximum entropy models via the `nltk.classify` module. Developers define custom feature extraction functions, then train classifiers on labeled datasets. Decision trees provide interpretable rules (e.g., 'if word contains "not" then negative'), while maximum entropy models learn probabilistic feature weights. Both classifiers support `.classify()` for prediction and `.show_most_informative_features()` for interpretability.

Identifies and classifies named entities (PERSON, ORGANIZATION, LOCATION, etc.) in POS-tagged text by applying a pre-trained chunker that wraps entities in nested tree structures. The `nltk.chunk.ne_chunk()` function takes POS-tagged sequences and returns an `nltk.Tree` object where entity spans are nested as subtrees labeled with entity types. Uses a maximum entropy classifier trained on the ACE corpus to recognize entity boundaries and types based on word, POS tag, and context features.

Constructs and visualizes hierarchical parse trees representing the grammatical structure of sentences. NLTK provides access to pre-parsed corpora (e.g., Penn Treebank via `nltk.corpus.treebank.parsed_sents()`) and includes parsers for generating new parse trees from raw text. The `Tree` class represents parse trees as nested structures where each node is labeled with a syntactic category (S, NP, VP, etc.) and leaf nodes are words. The `.draw()` method renders trees graphically, enabling visual inspection of sentence structure.

Provides a unified Python interface to 50+ linguistic corpora and lexical resources (e.g., Penn Treebank, WordNet, Brown Corpus) via the `nltk.corpus` module. Corpora are accessed as Python objects with methods like `.words()`, `.sents()`, `.parsed_sents()`, enabling lazy loading of data on-demand rather than loading entire corpora into memory. The abstraction handles file I/O, format parsing (.mrg, .txt, etc.), and caching, allowing developers to access diverse linguistic resources with consistent APIs.

Reduces words to their root forms using rule-based stemming algorithms (Porter Stemmer, Snowball) or lemmatization via WordNet. Stemming applies morphological rules to strip affixes (e.g., 'running' → 'run', 'happiness' → 'happi'), while lemmatization uses lexical databases to find canonical forms (e.g., 'better' → 'good'). NLTK provides multiple stemmer implementations (PorterStemmer, SnowballStemmer for 15+ languages) and WordNet-based lemmatization, enabling developers to choose trade-offs between speed, accuracy, and language coverage.

Trains and applies text classifiers using naive Bayes and other statistical models via the `nltk.classify` module. Developers define custom feature extraction functions that map text to feature dictionaries (e.g., presence of specific words, n-grams, POS tags), then train classifiers on labeled datasets. The module provides `NaiveBayesClassifier.train()` for training and `.classify()` for prediction, with built-in accuracy evaluation and feature importance analysis via `.show_most_informative_features()`.

Computes semantic similarity and relatedness between words using WordNet, a lexical database of English words organized into synsets (synonym sets) and hypernym/hyponym relations. The `nltk.corpus.wordnet` module provides methods like `.path_similarity()`, `.lch_similarity()`, and `.wup_similarity()` that measure distance between synsets based on their position in the WordNet hierarchy. Enables developers to find synonyms, antonyms, and semantically related words without external APIs or pre-trained embeddings.

Generates n-grams (sequences of n consecutive tokens) from text and analyzes their frequency distributions. The `nltk.util.ngrams()` function produces all n-grams of a specified length from a token sequence, while `nltk.FreqDist()` computes frequency distributions of n-grams or other linguistic units. Enables developers to identify common word sequences, collocations, and patterns for language modeling, feature extraction, or linguistic analysis.

Searches for word occurrences in text and displays them in context via concordance views. The `nltk.Text` class wraps a token list and provides `.concordance()` method to find all occurrences of a word and display surrounding context (typically 25 characters on each side). Enables developers and researchers to explore word usage patterns, collocations, and semantic contexts without manual text inspection.