nltk-org

NLTK Documentation API Reference Example Usage Module Index Wiki FAQ Open Issues NLTK on GitHub Installation Installing NLTK Installing NLTK Data More Release Notes Contributing to NLTK NLTK Team Natural Language Toolkit¶ NLTK is a leading platform for building Python programs to work with human language data. It provides easy-to-use interfaces to over 50 corpora and lexical resources such as WordNet, along with a suite of text processing libraries for classification, tokenization, stemming, tagging, parsing, and semantic reasoning, wrappers for industrial-strength NLP libraries, and an active discussion forum. Thanks to a hands-on guide introducing programming fundamentals alongside topics in computational linguistics, plus comprehensive API documentation, NLTK is suitable for linguists, engineers, students, educators, researchers, and industry users alike. NLTK is available for Windows, macOS, and Linux. Best of all, NLTK is a free, open source, community-driven project. NLTK has been called “a wonderful tool for teaching, and working in, computational linguistics using Python,” and “an amazing library to play with natural language.” Natural Language Processing with Python provides a practical introduction to programming for language processing. Written by the creators of NLTK, it guides the reader through the fundamentals of writing Python programs, working with corpora, categorizing text, analyzing linguistic structure, and more. The online version of the book has been been updated for Python 3 and NLTK 3. (The original Python 2 version is still available at https://www.nltk.org/book_1ed.) Some simple things you can do with NLTK¶ Tokenize and tag some text: >>> import nltk >>> sentence = """At eight o'clock on Thursday morning ... Arthur didn't feel very good.""" >>> tokens = nltk.word_tokenize(sentence) >>> tokens ['At', 'eight', "o'clock", 'on', 'Thursday', 'morning', 'Arthur', 'did', "n't", 'feel', 'very', 'good', '.'] >>> tagged = nltk.pos_tag(tokens) >>> tagged[0:6] [('At', 'IN'), ('eight', 'CD'), ("o'clock", 'JJ'), ('on', 'IN'), ('Thursday', 'NNP'), ('morning', 'NN')] Identify named entities: >>> entities = nltk.chunk.ne_chunk(tagged) >>> entities Tree('S', [('At', 'IN'), ('eight', 'CD'), ("o'clock", 'JJ'), ('on', 'IN'), ('Thursday', 'NNP'), ('morning', 'NN'), Tree('PERSON', [('Arthur', 'NNP')]), ('did', 'VBD'), ("n't", 'RB'), ('feel', 'VB'), ('very', 'RB'), ('good', 'JJ'), ('.', '.')]) Display a parse tree: >>> from nltk.corpus import treebank >>> t = treebank.parsed_sents('wsj_0001.mrg')[0] >>> t.draw() NB. If you publish work that uses NLTK, please cite the NLTK book as follows: Bird, Steven, Edward Loper and Ewan Klein (2009), Natural Language Processing with Python. O’Reilly Media Inc. Next Steps¶ Sign up for release announcements Join in the discussion --- NLTK Documentation API Reference Example Usage Module Index Wiki FAQ Open Issues NLTK on GitHub Installation Installing NLTK Installing NLTK Data More Release Notes Contributing to NLTK NLTK Team nltk package¶ Subpackages¶ nltk.app package Submodules nltk.app.chartparser_app module app() nltk.app.chunkparser_app module app() nltk.app.collocations_app module app() nltk.app.concordance_app module app() nltk.app.nemo_app module app() nltk.app.rdparser_app module app() nltk.app.srparser_app module app() nltk.app.wordfreq_app module nltk.app.wordnet_app module app() Module contents nltk.ccg package Submodules nltk.ccg.api module AbstractCCGCategory CCGVar Direction FunctionalCategory PrimitiveCategory nltk.ccg.chart module BackwardTypeRaiseRule BinaryCombinatorRule CCGChart CCGChartParser CCGEdge CCGLeafEdge ForwardTypeRaiseRule compute_semantics() demo() printCCGDerivation() printCCGTree() nltk.ccg.combinator module BackwardCombinator DirectedBinaryCombinator ForwardCombinator UndirectedBinaryCombinator UndirectedComposition UndirectedFunctionApplication UndirectedSubstitution UndirectedTypeRaise backwardBxConstraint() backwardOnly() backwardSxConstraint() backwardTConstraint() bothBackward() bothForward() crossedDirs() forwardOnly() forwardSConstraint() forwardTConstraint() innermostFunction() nltk.ccg.lexicon module CCGLexicon Token augParseCategory() fromstring() matchBrackets() nextCategory() parseApplication() parsePrimitiveCategory() parseSubscripts() nltk.ccg.logic module compute_composition_semantics() compute_function_semantics() compute_substitution_semantics() compute_type_raised_semantics() Module contents nltk.chat package Submodules nltk.chat.eliza module demo() eliza_chat() nltk.chat.iesha module demo() iesha_chat() nltk.chat.rude module demo() rude_chat() nltk.chat.suntsu module demo() suntsu_chat() nltk.chat.util module Chat nltk.chat.zen module demo() zen_chat() Module contents chatbots() nltk.chunk package Submodules nltk.chunk.api module ChunkParserI nltk.chunk.named_entity module Maxent_NE_Chunker NEChunkParser NEChunkParserTagger build_model() cmp_chunks() load_ace_data() load_ace_file() postag_tree() shape() simplify_pos() nltk.chunk.regexp module ChunkRule ChunkRuleWithContext ChunkString ExpandLeftRule ExpandRightRule MergeRule RegexpChunkParser RegexpChunkRule RegexpParser SplitRule StripRule UnChunkRule demo() demo_eval() tag_pattern2re_pattern() nltk.chunk.util module ChunkScore accuracy() conllstr2tree() conlltags2tree() demo() ieerstr2tree() tagstr2tree() tree2conllstr() tree2conlltags() Module contents RegexpChunkParser RegexpChunkRules Efficiency Emacs Tip Unresolved Issues ne_chunk() ne_chunk_sents() ne_chunker() nltk.classify package Submodules nltk.classify.api module ClassifierI MultiClassifierI nltk.classify.decisiontree module DecisionTreeClassifier demo() f() nltk.classify.maxent module Terminology: ‘feature’ BinaryMaxentFeatureEncoding ConditionalExponentialClassifier FunctionBackedMaxentFeatureEncoding GISEncoding MaxentClassifier MaxentFeatureEncodingI TadmEventMaxentFeatureEncoding TadmMaxentClassifier TypedMaxentFeatureEncoding calculate_deltas() calculate_empirical_fcount() calculate_estimated_fcount() calculate_nfmap() demo() load_maxent_params() maxent_pos_tagger() save_maxent_params() train_maxent_classifier_with_gis() train_maxent_classifier_with_iis() train_maxent_classifier_with_megam() nltk.classify.megam module call_megam() config_megam() parse_megam_weights() write_megam_file() nltk.classify.naivebayes module NaiveBayesClassifier demo() nltk.classify.positivenaivebayes module PositiveNaiveBayesClassifier demo() nltk.classify.rte_classify module RTEFeatureExtractor rte_classifier() rte_features() rte_featurize() nltk.classify.scikitlearn module SklearnClassifier nltk.classify.senna module Senna nltk.classify.svm module SvmClassifier nltk.classify.tadm module call_tadm() config_tadm() encoding_demo() names_demo() parse_tadm_weights() write_tadm_file() nltk.classify.textcat module TextCat demo() nltk.classify.util module CutoffChecker accuracy() apply_features() attested_labels() binary_names_demo_features() check_megam_config() log_likelihood() names_demo() names_demo_features() partial_names_demo() wsd_demo() nltk.classify.weka module ARFF_Formatter WekaClassifier config_weka() Module contents Features Featuresets Training Classifiers nltk.cluster package Submodules nltk.cluster.api module ClusterI nltk.cluster.em module EMClusterer demo() nltk.cluster.gaac module GAAClusterer demo() nltk.cluster.kmeans module KMeansClusterer demo() nltk.cluster.util module Dendrogram VectorSpaceClusterer cosine_distance() euclidean_distance() Module contents nltk.corpus package Subpackages nltk.corpus.reader package Submodules Module contents Submodules nltk.corpus.europarl_raw module nltk.corpus.util module LazyCorpusLoader Module contents Available Corpora Corpus Reader Functions demo() nltk.draw package Submodules nltk.draw.cfg module CFGDemo CFGEditor ProductionList demo() demo2() demo3() nltk.draw.dispersion module dispersion_plot() nltk.draw.table module MultiListbox Table demo() nltk.draw.tree module TreeSegmentWidget TreeView TreeWidget demo() draw_trees() tree_to_treesegment() nltk.draw.util module AbstractContainerWidget BoxWidget BracketWidget CanvasFrame CanvasWidget ColorizedList EntryDialog MutableOptionMenu OvalWidget ParenWidget ScrollWatcherWidget SequenceWidget ShowText SpaceWidget StackWidget SymbolWidget TextWidget demo() Module contents nltk.inference package Submodules nltk.inference.api module BaseModelBuilderCommand BaseProverCommand BaseTheoremToolCommand ModelBuilder ModelBuilderCommand ModelBuilderCommandDecorator ParallelProverBuilder ParallelProverBuilderCommand Prover ProverCommand ProverCommandDecorator TheoremToolCommand TheoremToolCommandDecorator TheoremToolThread nltk.inference.discourse module CfgReadingCommand DiscourseTester DrtGlueReadingCommand ReadingCommand demo() discourse_demo() drt_discourse_demo() load_fol() spacer() nltk.inference.mace module Mace MaceCommand decode_result() demo() spacer() test_build_model() test_make_relation_set() test_model_found() test_transform_output() nltk.inference.nonmonotonic module ClosedDomainProver ClosedWorldProver PredHolder ProverParseError SetHolder UniqueNamesProver closed_domain_demo() closed_world_demo() combination_prover_demo() default_reasoning_demo() demo() get_domain() print_proof() unique_names_demo() nltk.inference.prover9 module Prover9 Prover9Command Prover9CommandParent Prover9Exception Prover9FatalException Prover9LimitExceededException Prover9Parent convert_to_prover9() demo() spacer() test_config() test_convert_to_prover9() test_prove() nltk.inference.resolution module BindingDict BindingException Clause DebugObject ProverParseError ResolutionProver ResolutionProverCommand UnificationException clausify() demo() most_general_unification() resolution_test() testResolutionProver() test_clausify() nltk.inference.tableau module Agenda Categories Debug ProverParseError TableauProver TableauProverCommand demo() tableau_test() testHigherOrderTableauProver() testTableauProver() Module contents nltk.lm package Submodules nltk.lm.api module LanguageModel Smoothing nltk.lm.counter module Language Model Counter NgramCounter nltk.lm.models module AbsoluteDiscountingInterpolated InterpolatedLanguageModel KneserNeyInterpolated Laplace Lidstone MLE StupidBackoff WittenBellInterpolated nltk.lm.preprocessing module flatten() padded_everygram_pipeline() padded_everygrams() nltk.lm.smoothing module AbsoluteDiscounting KneserNey WittenBell nltk.lm.util module log_base2() nltk.lm.vocabulary module Vocabulary Module contents NLTK Language Modeling Module. Preparing Data Training Using a Trained Model AbsoluteDiscountingInterpolated AbsoluteDiscountingInterpolated.__init__() KneserNeyInterpolated KneserNeyInterpolated.__init__() Laplace Laplace.__init__() Lidstone Lidstone.__init__() Lidstone.unmasked_score() MLE MLE.unmasked_score() NgramCounter NgramCounter.N() NgramCounter.__init__() NgramCounter.update() StupidBackoff StupidBackoff.__init__() StupidBackoff.unmasked_score() Vocabulary Vocabulary.__init__() Vocabulary.cutoff Vocabulary.lookup() Vocabulary.update() WittenBellInterpolated WittenBellInterpolated.__init__() nltk.metrics package Submodules nltk.metrics.agreement module AnnotationTask nltk.metrics.aline module Example usage R() V() align() delta() demo() diff() sigma_exp() sigma_skip() sigma_sub() nltk.metrics.association module BigramAssocMeasures ContingencyMeasures NGRAM NgramAssocMeasures QuadgramAssocMeasures TOTAL TrigramAssocMeasures UNIGRAMS fisher_exact() nltk.metrics.confusionmatrix module ConfusionMatrix demo() nltk.metrics.distance module binary_distance() custom_distance() demo() edit_distance() edit_distance_align() fractional_presence() interval_distance() jaccard_distance() jaro_similarity() jaro_winkler_similarity() masi_distance() presence() nltk.metrics.paice module Paice demo() get_words_from_dictionary() nltk.metrics.scores module accuracy() approxrand() demo() f_measure() log_likelihood() precision() recall() nltk.metrics.segmentation module ghd() pk() windowdiff() nltk.metrics.spearman module ranks_from_scores() ranks_from_sequence() spearman_correlation() Module contents nltk.misc package Submodules nltk.misc.babelfish module babelize_shell() nltk.misc.chomsky module generate_chomsky() nltk.misc.minimalset module MinimalSet nltk.misc.sort module bubble() demo() merge() quick() selection() nltk.misc.wordfinder module check() revword() step() word_finder() wordfinder() Module contents nltk.parse package Submodules nltk.parse.api module ParserI nltk.parse.bllip module BllipParser nltk.parse.chart module AbstractChartRule BottomUpChartParser BottomUpLeftCornerChartParser BottomUpPredictCombineRule BottomUpPredictRule CachedTopDownPredictRule Chart ChartParser ChartRuleI EdgeI EmptyPredictRule FilteredBottomUpPredictCombineRule FilteredSingleEdgeFundamentalRule FundamentalRule LeafEdge LeafInitRule LeftCornerChartParser SingleEdgeFundamentalRule SteppingChartParser TopDownChartParser TopDownInitRule TopDownPredictRule TreeEdge demo() demo_grammar() nltk.parse.corenlp module CoreNLPDependencyParser CoreNLPParser CoreNLPServer CoreNLPServerError GenericCoreNLPParser transform() try_port() nltk.parse.dependencygraph module DependencyGraph DependencyGraphError conll_demo() conll_file_demo() cycle_finding_demo() demo() dot2img() malt_demo() nltk.parse.earleychart module CompleteFundamentalRule CompleterRule EarleyChartParser FeatureCompleteFundamentalRule FeatureCompleterRule FeatureEarleyChartParser FeatureIncrementalBottomUpChartParser FeatureIncrementalBottomUpLeftCornerChartParser FeatureIncrementalChart FeatureIncrementalChartParser FeatureIncrementalTopDownChartParser FeaturePredictorRule FeatureScannerRule FilteredCompleteFundamentalRule IncrementalBottomUpChartParser IncrementalBottomUpLeftCornerChartParser IncrementalChart IncrementalChartParser IncrementalLeftCornerChartParser IncrementalTopDownChartParser PredictorRule ScannerRule demo() nltk.parse.evaluate module DependencyEvaluator nltk.parse.featurechart module FeatureBottomUpChartParser FeatureBottomUpLeftCornerChartParser FeatureBottomUpPredictCombineRule FeatureBottomUpPredictRule FeatureChart FeatureChartParser FeatureEmptyPredictRule FeatureFundamentalRule FeatureSingleEdgeFundamentalRule FeatureTopDownChartParser FeatureTopDownInitRule FeatureTopDownPredictRule FeatureTreeEdge InstantiateVarsChart demo() demo_grammar() run_profile() nltk.parse.generate module demo() generate() nltk.parse.malt module MaltParser find_malt_model() find_maltparser() malt_regex_tagger() nltk.parse.nonprojectivedependencyparser module DemoScorer DependencyScorerI NaiveBayesDependencyScorer NonprojectiveDependencyParser ProbabilisticNonprojectiveParser demo() hall_demo() nonprojective_conll_parse_demo() rule_based_demo() nltk.parse.pchart module BottomUpProbabilisticChartParser InsideChartParser LongestChartParser ProbabilisticBottomUpInitRule ProbabilisticBottomUpPredictRule ProbabilisticFundamentalRule ProbabilisticLeafEdge ProbabilisticTreeEdge RandomChartParser SingleEdgeProbabilisticFundamentalRule UnsortedChartParser demo() nltk.parse.projectivedependencyparser module ChartCell DependencySpan ProbabilisticProjectiveDependencyParser ProjectiveDependencyParser arity_parse_demo() demo() projective_prob_parse_demo() projective_rule_parse_demo() nltk.parse.recursivedescent module RecursiveDescentParser SteppingRecursiveDescentParser demo() nltk.parse.shiftreduce module ShiftReduceParser SteppingShiftReduceParser demo() nltk.parse.stanford module GenericStanfordParser StanfordDependencyParser StanfordNeuralDependencyParser StanfordParser nltk.parse.transitionparser module Configuration Transition TransitionParser demo() nltk.parse.util module TestGrammar extract_test_sentences() load_parser() taggedsent_to_conll() taggedsents_to_conll() nltk.parse.viterbi module ViterbiParser demo() Module contents nltk.sem package Submodules nltk.sem.boxer module Usage AbstractBoxerDrs Boxer BoxerCard BoxerDrs BoxerDrsParser BoxerEq BoxerIndexed BoxerNamed BoxerNot BoxerOr BoxerOutputDrsParser BoxerPred BoxerProp BoxerRel BoxerWhq NltkDrtBoxerDrsInterpreter PassthroughBoxerDrsInterpreter UnparseableInputException nltk.sem.chat80 module Overview Reading Chat-80 Files Concepts Persistence Individuals and Lexical Items Concept binary_concept() cities2table() clause2concepts() concepts() label_indivs() main() make_lex() make_valuation() process_bundle() sql_demo() sql_query() unary_concept() val_dump() val_load() nltk.sem.cooper_storage module CooperStore demo() parse_with_bindops() nltk.sem.drt module AnaphoraResolutionException DRS DrsDrawer DrtAbstractVariableExpression DrtApplicationExpression DrtBinaryExpression DrtBooleanExpression DrtConcatenation DrtConstantExpression DrtEqualityExpression DrtEventVariableExpression DrtExpression DrtFunctionVariableExpression DrtIndividualVariableExpression DrtLambdaExpression DrtNegatedExpression DrtOrExpression DrtParser DrtProposition DrtTokens DrtVariableExpression() PossibleAntecedents demo() resolve_anaphora() test_draw() nltk.sem.drt_glue_demo module DrsWidget DrtGlueDemo demo() nltk.sem.evaluate module Assignment Error Model Undefined Valuation arity() demo() foldemo() folmodel() is_rel() propdemo() read_valuation() satdemo() set2rel() trace() nltk.sem.glue module DrtGlue DrtGlueDict DrtGlueFormula Glue GlueDict GlueFormula demo() nltk.sem.hole module Constants Constraint HoleSemantics hole_readings() nltk.sem.lfg module FStructure demo_read_depgraph() nltk.sem.linearlogic module ApplicationExpression AtomicExpression BindingDict ConstantExpression Expression ImpExpression LinearLogicApplicationException LinearLogicParser Tokens UnificationException VariableBindingException VariableExpression demo() nltk.sem.logic module AbstractVariableExpression AllExpression AndExpression AnyType ApplicationExpression BasicType BinaryExpression BooleanExpression ComplexType ConstantExpression EntityType EqualityExpression EventType EventVariableExpression ExistsExpression ExpectedMoreTokensException Expression FunctionVariableExpression IffExpression IllegalTypeException ImpExpression InconsistentTypeHierarchyException IndividualVariableExpression IotaExpression LambdaExpression LogicParser LogicalExpressionException NegatedExpression OrExpression QuantifiedExpression SubstituteBindingsI Tokens TruthValueType Type TypeException TypeResolutionException UnexpectedTokenException Variable VariableBinderExpression VariableExpression() binding_ops() boolean_ops() demo() demoException() demo_errors() equality_preds() is_eventvar() is_funcvar() is_indvar() printtype() read_logic() read_type() skolem_function() typecheck() unique_variable() nltk.sem.relextract module class_abbrev() clause() conllesp() conllned() descape_entity() extract_rels() ieer_headlines() in_demo() list2sym() ne_chunked() roles_demo() rtuple() semi_rel2reldict() tree2semi_rel() nltk.sem.skolemize module skolemize() to_cnf() nltk.sem.util module demo() demo_legacy_grammar() demo_model0() evaluate_sents() interpret_sents() parse_sents() read_sents() root_semrep() Module contents nltk.sentiment package Submodules nltk.sentiment.sentiment_analyzer module SentimentAnalyzer nltk.sentiment.util module demo_liu_hu_lexicon() demo_movie_reviews() demo_sent_subjectivity() demo_subjectivity() demo_tweets() demo_vader_instance() demo_vader_tweets() extract_bigram_feats() extract_unigram_feats() json2csv_preprocess() mark_negation() output_markdown() parse_tweets_set() split_train_test() timer() nltk.sentiment.vader module SentiText SentimentIntensityAnalyzer VaderConstants Module contents nltk.stem package Submodules nltk.stem.api module StemmerI nltk.stem.arlstem module ARLSTem nltk.stem.arlstem2 module ARLSTem2 nltk.stem.cistem module Cistem nltk.stem.isri module ISRIStemmer nltk.stem.lancaster module LancasterStemmer nltk.stem.porter module PorterStemmer demo() nltk.stem.regexp module RegexpStemmer nltk.stem.rslp module RSLPStemmer nltk.stem.snowball module ArabicStemmer DanishStemmer DutchStemmer EnglishStemmer FinnishStemmer FrenchStemmer GermanStemmer HungarianStemmer ItalianStemmer NorwegianStemmer PorterStemmer PortugueseStemmer RomanianStemmer RussianStemmer SnowballStemmer SpanishStemmer SwedishStemmer demo() nltk.stem.util module prefix_replace() suffix_replace() nltk.stem.wordnet module WordNetLemmatizer Module contents nltk.tag package Submodules nltk.tag.api module FeaturesetTaggerI TaggerI nltk.tag.brill module BrillTagger Pos Word brill24() describe_template_sets() fntbl37() nltkdemo18() nltkdemo18plus() nltk.tag.brill_trainer module BrillTaggerTrainer nltk.tag.crf module CRFTagger nltk.tag.hmm module HiddenMarkovModelTagger HiddenMarkovModelTrainer demo() demo_bw() demo_pos() demo_pos_bw() load_pos() logsumexp2() nltk.tag.hunpos module HunposTagger nltk.tag.mapping module map_tag() tagset_mapping() nltk.tag.perceptron module AveragedPerceptron PerceptronTagger nltk.tag.senna module SennaChunkTagger SennaNERTagger SennaTagger nltk.tag.sequential module AffixTagger BigramTagger ClassifierBasedPOSTagger ClassifierBasedTagger ContextTagger DefaultTagger NgramTagger RegexpTagger SequentialBackoffTagger TrigramTagger UnigramTagger nltk.tag.stanford module StanfordNERTagger StanfordPOSTagger StanfordTagger nltk.tag.tnt module TnT basic_sent_chop() demo() demo2() demo3() nltk.tag.util module str2tuple() tuple2str() untag() Module contents pos_tag() pos_tag_sents() nltk.tbl package Submodules nltk.tbl.api module nltk.tbl.demo module corpus_size() demo() demo_error_analysis() demo_generated_templates() demo_high_accuracy_rules() demo_learning_curve() demo_multifeature_template() demo_multiposition_feature() demo_repr_rule_format() demo_serialize_tagger() demo_str_rule_format() demo_template_statistics() demo_verbose_rule_format() postag() nltk.tbl.erroranalysis module error_list() nltk.tbl.feature module Feature nltk.tbl.rule module Rule TagRule nltk.tbl.template module BrillTemplateI Template Module contents nltk.tokenize package Submodules nltk.tokenize.api module StringTokenizer TokenizerI nltk.tokenize.casual module TweetTokenizer casual_tokenize() reduce_lengthening() remove_handles() nltk.tokenize.destructive module MacIntyreContractions NLTKWordTokenizer nltk.tokenize.legality_principle module LegalitySyllableTokenizer nltk.tokenize.mwe module MWETokenizer nltk.tokenize.nist module NISTTokenizer nltk.tokenize.punkt module PunktBaseClass PunktLanguageVars PunktParameters PunktSentenceTokenizer PunktToken PunktTokenizer PunktTrainer demo() format_debug_decision() load_punkt_params() save_punkt_params() nltk.tokenize.regexp module BlanklineTokenizer RegexpTokenizer WhitespaceTokenizer WordPunctTokenizer blankline_tokenize() regexp_tokenize() wordpunct_tokenize() nltk.tokenize.repp module ReppTokenizer nltk.tokenize.sexpr module SExprTokenizer sexpr_tokenize() nltk.tokenize.simple module CharTokenizer LineTokenizer SpaceTokenizer TabTokenizer line_tokenize() nltk.tokenize.sonority_sequencing module SyllableTokenizer nltk.tokenize.stanford module StanfordTokenizer nltk.tokenize.stanford_segmenter module StanfordSegmenter nltk.tokenize.texttiling module TextTilingTokenizer TokenSequence TokenTableField demo() smooth() nltk.tokenize.toktok module ToktokTokenizer nltk.tokenize.treebank module TreebankWordDetokenizer TreebankWordTokenizer nltk.tokenize.util module CJKChars align_tokens() is_cjk() regexp_span_tokenize() spans_to_relative() string_span_tokenize() xml_escape() xml_unescape() Module contents sent_tokenize() word_tokenize() nltk.translate package Submodules nltk.translate.api module AlignedSent Alignment PhraseTable PhraseTableEntry nltk.translate.bleu_score module Fraction SmoothingFunction brevity_penalty() closest_ref_length() corpus_bleu() modified_precision() sentence_bleu() nltk.translate.chrf_score module chrf_precision_recall_fscore_support() corpus_chrf() sentence_chrf() nltk.translate.gale_church module LanguageIndependent align_blocks() align_log_prob() align_texts() erfcc() norm_cdf() norm_logsf() parse_token_stream() split_at() trace() nltk.translate.gdfa module grow_diag_final_and() nltk.translate.gleu_score module corpus_gleu() sentence_gleu() nltk.translate.ibm1 module Notations References IBMModel1 nltk.translate.ibm2 module Notations References IBMModel2 Model2Counts nltk.translate.ibm3 module Notations References IBMModel3 Model3Counts nltk.translate.ibm4 module Terminology Notations References IBMModel4 Model4Counts nltk.translate.ibm5 module Terminology Notations References IBMModel5 Model5Counts Slots nltk.translate.ibm_model module AlignmentInfo Counts IBMModel longest_target_sentence_length() nltk.translate.lepor module alignment() corpus_lepor() harmonic() length_penalty() ngram_positional_penalty() sentence_lepor() nltk.translate.meteor_score module align_words() exact_match() meteor_score() single_meteor_score() stem_match() wordnetsyn_match() nltk.translate.metrics module alignment_error_rate() nltk.translate.nist_score module corpus_nist() nist_length_penalty() sentence_nist() nltk.translate.phrase_based module extract() phrase_extraction() nltk.translate.ribes_score module corpus_ribes() find_increasing_sequences() kendall_tau() position_of_ngram() sentence_ribes() spearman_rho() word_rank_alignment() nltk.translate.stack_decoder module StackDecoder Module contents nltk.tree package Submodules nltk.tree.immutable module ImmutableMultiParentedTree ImmutableParentedTree ImmutableProbabilisticTree ImmutableTree nltk.tree.parented module MultiParentedTree ParentedTree nltk.tree.parsing module bracket_parse() sinica_parse() nltk.tree.prettyprinter module TreePrettyPrinter nltk.tree.probabilistic module ProbabilisticTree nltk.tree.transforms module chomsky_normal_form() collapse_unary() un_chomsky_normal_form() nltk.tree.tree module Tree Module contents ImmutableMultiParentedTree ImmutableParentedTree ImmutableProbabilisticTree ImmutableProbabilisticTree.__init__() ImmutableProbabilisticTree.convert() ImmutableProbabilisticTree.copy() ImmutableTree ImmutableTree.__init__() ImmutableTree.append() ImmutableTree.extend() ImmutableTree.pop() ImmutableTree.remove() ImmutableTree.reverse() ImmutableTree.set_label() ImmutableTree.sort() MultiParentedTree MultiParentedTree.__init__() MultiParentedTree.left_siblings() MultiParentedTree.parent_indices() MultiParentedTree.parents() MultiParentedTree.right_siblings() MultiParentedTree.roots() MultiParentedTree.treepositions() ParentedTree ParentedTree.__init__() ParentedTree.copy() ParentedTree.left_sibling() ParentedTree.parent() ParentedTree.parent_index() ParentedTree.right_sibling() ParentedTree.root() ParentedTree.treeposition() ProbabilisticTree ProbabilisticTree.__init__() ProbabilisticTree.convert() ProbabilisticTree.copy() Tree Tree.__init__() Tree.chomsky_normal_form() Tree.collapse_unary() Tree.convert() Tree.copy() Tree.draw() Tree.flatten() Tree.freeze() Tree.fromlist() Tree.fromstring() Tree.height() Tree.label() Tree.leaf_treeposition() Tree.leaves() Tree.node Tree.pformat() Tree.pformat_latex_qtree() Tree.pos() Tree.pprint() Tree.pretty_print() Tree.productions() Tree.set_label() Tree.subtrees() Tree.treeposition_spanning_leaves() Tree.treepositions() Tree.un_chomsky_normal_form() TreePrettyPrinter TreePrettyPrinter.__init__() TreePrettyPrinter.nodecoords() TreePrettyPrinter.svg() TreePrettyPrinter.text() bracket_parse() chomsky_normal_form() collapse_unary() sinica_parse() un_chomsky_normal_form() nltk.twitter package Submodules nltk.twitter.api module BasicTweetHandler LocalTimezoneOffsetWithUTC TweetHandlerI nltk.twitter.common module extract_fields() get_header_field_list() json2csv() json2csv_entities() nltk.twitter.twitter_demo module nltk.twitter.twitterclient module nltk.twitter.util module Module contents Submodules¶ nltk.book module sents() texts() nltk.cli module nltk.collections module AbstractLazySequence AbstractLazySequence.count() AbstractLazySequence.index() AbstractLazySequence.iterate_from() LazyConcatenation LazyConcatenation.__init__() LazyConcatenation.iterate_from() LazyEnumerate LazyEnumerate.__init__() LazyIteratorList LazyIteratorList.__init__() LazyIteratorList.iterate_from() LazyMap LazyMap.__init__() LazyMap.iterate_from() LazySubsequence LazySubsequence.MIN_SIZE LazySubsequence.__init__() LazySubsequence.__new__() LazySubsequence.iterate_from() LazyZip LazyZip.__init__() LazyZip.iterate_from() OrderedDict OrderedDict.__init__() OrderedDict.clear() OrderedDict.copy() OrderedDict.items() OrderedDict.keys() OrderedDict.popitem() OrderedDict.setdefault() OrderedDict.update() OrderedDict.values() Trie Trie.LEAF Trie.__init__() Trie.insert() nltk.collocations module BigramCollocationFinder BigramCollocationFinder.__init__() BigramCollocationFinder.default_ws BigramCollocationFinder.from_words() BigramCollocationFinder.score_ngram() QuadgramCollocationFinder QuadgramCollocationFinder.__init__() QuadgramCollocationFinder.default_ws QuadgramCollocationFinder.from_words() QuadgramCollocationFinder.score_ngram() TrigramCollocationFinder TrigramCollocationFinder.__init__() TrigramCollocationFinder.bigram_finder() TrigramCollocationFinder.default_ws TrigramCollocationFinder.from_words() TrigramCollocationFinder.score_ngram() nltk.compat module add_py3_data() py3_data() nltk.data module AUTO_FORMATS BufferedGzipFile() FORMATS FileSystemPathPointer FileSystemPathPointer.__init__() FileSystemPathPointer.file_size() FileSystemPathPointer.join() FileSystemPathPointer.open() FileSystemPathPointer.path GzipFileSystemPathPointer GzipFileSystemPathPointer.open() LazyLoader LazyLoader.__init__() OpenOnDemandZipFile OpenOnDemandZipFile.__init__() OpenOnDemandZipFile.read() OpenOnDemandZipFile.write() OpenOnDemandZipFile.writestr() PathPointer PathPointer.file_size() PathPointer.join() PathPointer.open() SeekableUnicodeStreamReader SeekableUnicodeStreamReader.DEBUG SeekableUnicodeStreamReader.__init__() SeekableUnicodeStreamReader.bytebuffer SeekableUnicodeStreamReader.char_seek_forward() SeekableUnicodeStreamReader.close() SeekableUnicodeStreamReader.closed SeekableUnicodeStreamReader.decode SeekableUnicodeStreamReader.discard_line() SeekableUnicodeStreamReader.encoding SeekableUnicodeStreamReader.errors SeekableUnicodeStreamReader.linebuffer SeekableUnicodeStreamReader.mode SeekableUnicodeStreamReader.name SeekableUnicodeStreamReader.next() SeekableUnicodeStreamReader.read() SeekableUnicodeStreamReader.readline() SeekableUnicodeStreamReader.readlines() SeekableUnicodeStreamReader.seek() SeekableUnicodeStreamReader.stream SeekableUnicodeStreamReader.tell() SeekableUnicodeStreamReader.xreadlines() clear_cache() find() load() path retrieve() show_cfg() nltk.decorators module decorator() getinfo() new_wrapper() nltk.downloader module Downloading Packages Download Directory NLTK Download Server Collection Collection.__init__() Collection.children Collection.fromxml() Collection.id Collection.name Collection.packages Downloader Downloader.DEFAULT_URL Downloader.INDEX_TIMEOUT Downloader.INSTALLED Downloader.NOT_INSTALLED Downloader.PARTIAL Downloader.STALE Downloader.__init__() Downloader.clear_status_cache() Downloader.collections() Downloader.corpora() Downloader.default_download_dir() Downloader.download() Downloader.download_dir Downloader.incr_download() Downloader.index() Downloader.info() Downloader.is_installed() Downloader.is_stale() Downloader.list() Downloader.models() Downloader.packages() Downloader.status() Downloader.update() Downloader.url Downloader.xmlinfo() DownloaderGUI DownloaderGUI.COLUMNS DownloaderGUI.COLUMN_WEIGHTS DownloaderGUI.COLUMN_WIDTHS DownloaderGUI.DEFAULT_COLUMN_WIDTH DownloaderGUI.HELP DownloaderGUI.INITIAL_COLUMNS DownloaderGUI.__init__() DownloaderGUI.about() DownloaderGUI.c DownloaderGUI.destroy() DownloaderGUI.help() DownloaderGUI.mainloop() DownloaderMessage DownloaderShell DownloaderShell.__init__() DownloaderShell.run() ErrorMessage ErrorMessage.__init__() FinishCollectionMessage FinishCollectionMessage.__init__() FinishDownloadMessage FinishDownloadMessage.__init__() FinishPackageMessage FinishPackageMessage.__init__() FinishUnzipMessage FinishUnzipMessage.__init__() Package Package.__init__() Package.author Package.checksum Package.contact Package.copyright Package.filename Package.fromxml() Package.id Package.license Package.name Package.size Package.subdir Package.svn_revision Package.unzip Package.unzipped_size Package.url ProgressMessage ProgressMessage.__init__() SelectDownloadDirMessage SelectDownloadDirMessage.__init__() StaleMessage StaleMessage.__init__() StartCollectionMessage StartCollectionMessage.__init__() StartDownloadMessage StartDownloadMessage.__init__() StartPackageMessage StartPackageMessage.__init__() StartUnzipMessage StartUnzipMessage.__init__() UpToDateMessage UpToDateMessage.__init__() build_index() download() download_gui() download_shell() md5_hexdigest() sha256_hexdigest() unzip() update() nltk.featstruct module Lightweight Feature Structures FeatDict FeatDict.__init__() FeatDict.clear() FeatDict.get() FeatDict.has_key() FeatDict.pop() FeatDict.popitem() FeatDict.setdefault() FeatDict.update() FeatList FeatList.__init__() FeatList.append() FeatList.extend() FeatList.insert() FeatList.pop() FeatList.remove() FeatList.reverse() FeatList.sort() FeatStruct FeatStruct.__new__() FeatStruct.copy() FeatStruct.cyclic() FeatStruct.equal_values() FeatStruct.freeze() FeatStruct.frozen() FeatStruct.remove_variables() FeatStruct.rename_variables() FeatStruct.retract_bindings() FeatStruct.substitute_bindings() FeatStruct.subsumes() FeatStruct.unify() FeatStruct.variables() FeatStruct.walk() FeatStructReader FeatStructReader.VALUE_HANDLERS FeatStructReader.__init__() FeatStructReader.fromstring() FeatStructReader.read_app_value() FeatStructReader.read_fstruct_value() FeatStructReader.read_int_value() FeatStructReader.read_logic_value() FeatStructReader.read_partial() FeatStructReader.read_set_value() FeatStructReader.read_str_value() FeatStructReader.read_sym_value() FeatStructReader.read_tuple_value() FeatStructReader.read_value() FeatStructReader.read_var_value() Feature Feature.__init__() Feature.default Feature.display Feature.name Feature.read_value() Feature.unify_base_values() RangeFeature RangeFeature.RANGE_RE RangeFeature.read_value() RangeFeature.unify_base_values() SlashFeature SlashFeature.read_value() conflicts() subsumes() unify() nltk.grammar module CFG CFG.__init__() CFG.binarize() CFG.check_coverage() CFG.chomsky_normal_form() CFG.eliminate_start() CFG.fromstring() CFG.is_binarised() CFG.is_chomsky_normal_form() CFG.is_flexible_chomsky_normal_form() CFG.is_leftcorner() CFG.is_lexical() CFG.is_nonempty() CFG.is_nonlexical() CFG.leftcorner_parents() CFG.leftcorners() CFG.max_len() CFG.min_len() CFG.productions() CFG.remove_mixed_rules() CFG.remove_unitary_rules() CFG.start() DependencyGrammar DependencyGrammar.__init__() DependencyGrammar.contains() DependencyGrammar.fromstring() DependencyProduction Nonterminal Nonterminal.__init__() Nonterminal.symbol() PCFG PCFG.EPSILON PCFG.__init__() PCFG.fromstring() ProbabilisticDependencyGrammar ProbabilisticDependencyGrammar.__init__() ProbabilisticDependencyGrammar.contains() ProbabilisticProduction ProbabilisticProduction.__init__() Production Production.__init__() Production.is_lexical() Production.is_nonlexical() Production.lhs() Production.rhs() induce_pcfg() nonterminals() read_grammar() nltk.help module brown_tagset() claws5_tagset() upenn_tagset() nltk.internals module Counter Counter.__init__() Counter.get() Deprecated Deprecated.__new__() ElementWrapper ElementWrapper.__init__() ElementWrapper.__new__() ElementWrapper.find() ElementWrapper.findall() ElementWrapper.getchildren() ElementWrapper.getiterator() ElementWrapper.makeelement() ElementWrapper.unwrap() ReadError ReadError.__init__() config_java() deprecated() find_binary() find_binary_iter() find_dir() find_file() find_file_iter() find_jar() find_jar_iter() find_jars_within_path() import_from_stdlib() is_writable() java() overridden() raise_unorderable_types() read_int() read_number() read_str() slice_bounds() nltk.jsontags module JSONTaggedDecoder JSONTaggedDecoder.decode() JSONTaggedDecoder.decode_obj() JSONTaggedEncoder JSONTaggedEncoder.default() register_tag() nltk.langnames module inverse_dict() lang2q() langcode() langname() q2name() q2tag() tag2q() nltk.lazyimport module LazyModule LazyModule.__init__() nltk.probability module ConditionalFreqDist ConditionalFreqDist.N() ConditionalFreqDist.__init__() ConditionalFreqDist.conditions() ConditionalFreqDist.copy() ConditionalFreqDist.deepcopy() ConditionalFreqDist.plot() ConditionalFreqDist.tabulate() ConditionalProbDist ConditionalProbDist.__init__() ConditionalProbDistI ConditionalProbDistI.__init__() ConditionalProbDistI.conditions() CrossValidationProbDist CrossValidationProbDist.SUM_TO_ONE CrossValidationProbDist.__init__() CrossValidationProbDist.discount() CrossValidationProbDist.freqdists() CrossValidationProbDist.prob() CrossValidationProbDist.samples() DictionaryConditionalProbDist DictionaryConditionalProbDist.__init__() DictionaryProbDist DictionaryProbDist.__init__() DictionaryProbDist.logprob() DictionaryProbDist.max() DictionaryProbDist.prob() DictionaryProbDist.samples() ELEProbDist ELEProbDist.__init__() FreqDist FreqDist.B() FreqDist.N() FreqDist.Nr() FreqDist.__init__() FreqDist.copy() FreqDist.freq() FreqDist.hapaxes() FreqDist.max() FreqDist.pformat() FreqDist.plot() FreqDist.pprint() FreqDist.r_Nr() FreqDist.setdefault() FreqDist.tabulate() FreqDist.update() HeldoutProbDist HeldoutProbDist.SUM_TO_ONE HeldoutProbDist.__init__() HeldoutProbDist.base_fdist() HeldoutProbDist.discount() HeldoutProbDist.heldout_fdist() HeldoutProbDist.max() HeldoutProbDist.prob() HeldoutProbDist.samples() ImmutableProbabilisticMixIn ImmutableProbabilisticMixIn.set_logprob() ImmutableProbabilisticMixIn.set_prob() KneserNeyProbDist KneserNeyProbDist.__init__() KneserNeyProbDist.discount() KneserNeyProbDist.max() KneserNeyProbDist.prob() KneserNeyProbDist.samples() KneserNeyProbDist.set_discount() LaplaceProbDist LaplaceProbDist.__init__() LidstoneProbDist LidstoneProbDist.SUM_TO_ONE LidstoneProbDist.__init__() LidstoneProbDist.discount() LidstoneProbDist.freqdist() LidstoneProbDist.max() LidstoneProbDist.prob() LidstoneProbDist.samples() MLEProbDist MLEProbDist.__init__() MLEProbDist.freqdist() MLEProbDist.max() MLEProbDist.prob() MLEProbDist.samples() MutableProbDist MutableProbDist.__init__() MutableProbDist.logprob() MutableProbDist.max() MutableProbDist.prob() MutableProbDist.samples() MutableProbDist.update() ProbDistI ProbDistI.SUM_TO_ONE ProbDistI.__init__() ProbDistI.discount() ProbDistI.generate() ProbDistI.logprob() ProbDistI.max() ProbDistI.prob() ProbDistI.samples() ProbabilisticMixIn ProbabilisticMixIn.__init__() ProbabilisticMixIn.logprob() ProbabilisticMixIn.prob() ProbabilisticMixIn.set_logprob() ProbabilisticMixIn.set_prob() SimpleGoodTuringProbDist SimpleGoodTuringProbDist.SUM_TO_ONE SimpleGoodTuringProbDist.__init__() SimpleGoodTuringProbDist.check() SimpleGoodTuringProbDist.discount() SimpleGoodTuringProbDist.find_best_fit() SimpleGoodTuringProbDist.freqdist() SimpleGoodTuringProbDist.max() SimpleGoodTuringProbDist.prob() SimpleGoodTuringProbDist.samples() SimpleGoodTuringProbDist.smoothedNr() UniformProbDist UniformProbDist.__init__() UniformProbDist.max() UniformProbDist.prob() UniformProbDist.samples() WittenBellProbDist WittenBellProbDist.__init__() WittenBellProbDist.discount() WittenBellProbDist.freqdist() WittenBellProbDist.max() WittenBellProbDist.prob() WittenBellProbDist.samples() add_logs() entropy() log_likelihood() sum_logs() nltk.tabdata module MaxentDecoder MaxentDecoder.tupkey2dict() MaxentEncoder MaxentEncoder.tupdict2tab() PunktDecoder PunktDecoder.tab2intdict() TabDecoder TabDecoder.tab2dict() TabDecoder.tab2ivdict() TabDecoder.tab2tup() TabDecoder.tab2tups() TabDecoder.txt2list() TabDecoder.txt2set() TabEncoder TabEncoder.dict2tab() TabEncoder.ivdict2tab() TabEncoder.list2txt() TabEncoder.set2txt() TabEncoder.tup2tab() TabEncoder.tups2tab() rm_nl() nltk.text module ConcordanceIndex ConcordanceIndex.__init__() ConcordanceIndex.find_concordance() ConcordanceIndex.offsets() ConcordanceIndex.print_concordance() ConcordanceIndex.tokens() ContextIndex ContextIndex.__init__() ContextIndex.common_contexts() ContextIndex.similar_words() ContextIndex.tokens() ContextIndex.word_similarity_dict() Text Text.__init__() Text.collocation_list() Text.collocations() Text.common_contexts() Text.concordance() Text.concordance_list() Text.count() Text.dispersion_plot() Text.findall() Text.generate() Text.index() Text.plot() Text.readability() Text.similar() Text.vocab() TextCollection TextCollection.__init__() TextCollection.idf() TextCollection.tf() TextCollection.tf_idf() TokenSearcher TokenSearcher.__init__() TokenSearcher.findall() nltk.tgrep module TGrep search implementation for NLTK trees Usage Caveats: Known Issues: Implementation notes TgrepException ancestors() tgrep_compile() tgrep_nodes() tgrep_positions() tgrep_tokenize() treepositions_no_leaves() unique_ancestors() nltk.toolbox module StandardFormat StandardFormat.__init__() StandardFormat.close() StandardFormat.fields() StandardFormat.open() StandardFormat.open_string() StandardFormat.raw_fields() ToolboxData ToolboxData.parse() ToolboxSettings ToolboxSettings.__init__() ToolboxSettings.parse() add_blank_lines() add_default_fields() demo() remove_blanks() sort_fields() to_settings_string() to_sfm_string() nltk.treeprettyprinter module TreePrettyPrinter nltk.treetransforms module chomsky_normal_form() collapse_unary() un_chomsky_normal_form() nltk.util module Index Index.__init__() acyclic_branches_depth_first() acyclic_breadth_first() acyclic_depth_first() acyclic_dic2tree() bigrams() binary_search_file() breadth_first() choose() clean_html() clean_url() cut_string() edge_closure() edges2dot() elementtree_indent() everygrams() filestring() flatten() guess_encoding() in_idle() invert_dict() invert_graph() ngrams() pad_sequence() pairwise() parallelize_preprocess() pr() print_string() re_show() set_proxy() skipgrams() tokenwrap() transitive_closure() trigrams() unique_list() unweighted_minimum_spanning_dict() unweighted_minimum_spanning_digraph() unweighted_minimum_spanning_tree() nltk.wsd module lesk() Module contents¶ The Natural Language Toolkit (NLTK) is an open source Python library for Natural Language Processing. A free online book is available. (If you use the library for academic research, please cite the book.) Steven Bird, Ewan Klein, and Edward Loper (2009). Natural Language Processing with Python. O’Reilly Media Inc. https://www.nltk.org/book/ isort:skip_file @version: 3.9.2 nltk.demo()[source]¶ --- NLTK Documentation API Reference Example Usage Module Index Wiki FAQ Open Issues NLTK on GitHub Installation Installing NLTK Installing NLTK Data More Release Notes Contributing to NLTK NLTK Team Example usage of NLTK modules¶ Sample usage for bleu Sample usage for bnc Sample usage for ccg Sample usage for ccg_semantics Sample usage for chat80 Sample usage for childes Sample usage for chunk Sample usage for classify Sample usage for collections Sample usage for collocations Sample usage for concordance Sample usage for corpus Sample usage for crubadan Sample usage for data Sample usage for dependency Sample usage for discourse Sample usage for drt Sample usage for featgram Sample usage for featstruct Sample usage for framenet Sample usage for generate Sample usage for gensim Sample usage for gluesemantics Sample usage for gluesemantics_malt Sample usage for grammar Sample usage for grammartestsuites Sample usage for inference Sample usage for internals Sample usage for japanese Sample usage for lm Sample usage for logic Sample usage for meteor Sample usage for metrics Sample usage for misc Sample usage for nonmonotonic Sample usage for paice Sample usage for parse Sample usage for portuguese_en Sample usage for probability Sample usage for propbank Sample usage for relextract Sample usage for resolution Sample usage for semantics Sample usage for sentiment Sample usage for sentiwordnet Sample usage for simple Sample usage for stem Sample usage for tag Sample usage for tokenize Sample usage for toolbox Sample usage for translate Sample usage for tree Sample usage for treeprettyprinter Sample usage for treetransforms Sample usage for util Sample usage for wordnet Sample usage for wordnet_lch Sample usage for wsd --- NLTK Documentation API Reference Example Usage Module Index Wiki FAQ Open Issues NLTK on GitHub Installation Installing NLTK Installing NLTK Data More Release Notes Contributing to NLTK NLTK Team Python Module Index a | b | c | d | f | g | h | i | j | l | m | n | p | s | t | u | w a nltk.app nltk.app.chartparser_app nltk.app.chunkparser_app nltk.app.collocations_app nltk.app.concordance_app nltk.app.nemo_app nltk.app.rdparser_app nltk.app.srparser_app nltk.app.wordnet_app b nltk.book c nltk.ccg nltk.ccg.api nltk.ccg.chart nltk.ccg.combinator nltk.ccg.lexicon nltk.ccg.logic nltk.chat nltk.chat.eliza nltk.chat.iesha nltk.chat.rude nltk.chat.suntsu nltk.chat.util nltk.chat.zen nltk.chunk nltk.chunk.api nltk.chunk.named_entity nltk.chunk.regexp nltk.chunk.util nltk.classify nltk.classify.api nltk.classify.decisiontree nltk.classify.maxent nltk.classify.megam nltk.classify.naivebayes nltk.classify.positivenaivebayes nltk.classify.rte_classify nltk.classify.scikitlearn nltk.classify.senna nltk.classify.svm nltk.classify.tadm nltk.classify.textcat nltk.classify.util nltk.classify.weka nltk.cluster nltk.cluster.api nltk.cluster.em nltk.cluster.gaac nltk.cluster.kmeans nltk.cluster.util nltk.collections nltk.collocations nltk.compat nltk.corpus nltk.corpus.europarl_raw nltk.corpus.reader nltk.corpus.reader.aligned nltk.corpus.reader.api nltk.corpus.reader.bcp47 nltk.corpus.reader.bnc nltk.corpus.reader.bracket_parse nltk.corpus.reader.categorized_sents nltk.corpus.reader.chasen nltk.corpus.reader.childes nltk.corpus.reader.chunked nltk.corpus.reader.cmudict nltk.corpus.reader.comparative_sents nltk.corpus.reader.conll nltk.corpus.reader.crubadan nltk.corpus.reader.dependency nltk.corpus.reader.framenet nltk.corpus.reader.ieer nltk.corpus.reader.indian nltk.corpus.reader.ipipan nltk.corpus.reader.knbc nltk.corpus.reader.lin nltk.corpus.reader.markdown nltk.corpus.reader.mte nltk.corpus.reader.nkjp nltk.corpus.reader.nombank nltk.corpus.reader.nps_chat nltk.corpus.reader.opinion_lexicon nltk.corpus.reader.panlex_lite nltk.corpus.reader.panlex_swadesh nltk.corpus.reader.pl196x nltk.corpus.reader.plaintext nltk.corpus.reader.ppattach nltk.corpus.reader.propbank nltk.corpus.reader.pros_cons nltk.corpus.reader.reviews nltk.corpus.reader.rte nltk.corpus.reader.semcor nltk.corpus.reader.senseval nltk.corpus.reader.sentiwordnet nltk.corpus.reader.sinica_treebank nltk.corpus.reader.string_category nltk.corpus.reader.switchboard nltk.corpus.reader.tagged nltk.corpus.reader.timit nltk.corpus.reader.toolbox nltk.corpus.reader.twitter nltk.corpus.reader.udhr nltk.corpus.reader.util nltk.corpus.reader.verbnet nltk.corpus.reader.wordlist nltk.corpus.reader.wordnet nltk.corpus.reader.xmldocs nltk.corpus.reader.ycoe nltk.corpus.util d nltk.data nltk.decorators nltk.downloader nltk.draw nltk.draw.cfg nltk.draw.dispersion nltk.draw.table nltk.draw.tree nltk.draw.util f nltk.featstruct g nltk.grammar h nltk.help i nltk.inference nltk.inference.api nltk.inference.discourse nltk.inference.mace nltk.inference.nonmonotonic nltk.inference.prover9 nltk.inference.resolution nltk.inference.tableau nltk.internals j nltk.jsontags l nltk.langnames nltk.lazyimport nltk.lm nltk.lm.api nltk.lm.counter nltk.lm.models nltk.lm.preprocessing nltk.lm.smoothing nltk.lm.util nltk.lm.vocabulary m nltk.metrics nltk.metrics.agreement nltk.metrics.aline nltk.metrics.association nltk.metrics.confusionmatrix nltk.metrics.distance nltk.metrics.paice nltk.metrics.scores nltk.metrics.segmentation nltk.metrics.spearman nltk.misc nltk.misc.babelfish nltk.misc.chomsky nltk.misc.minimalset nltk.misc.sort nltk.misc.wordfinder n nltk p nltk.parse nltk.parse.api nltk.parse.bllip nltk.parse.chart nltk.parse.corenlp nltk.parse.dependencygraph nltk.parse.earleychart nltk.parse.evaluate nltk.parse.featurechart nltk.parse.generate nltk.parse.malt nltk.parse.nonprojectivedependencyparser nltk.parse.pchart nltk.parse.projectivedependencyparser nltk.parse.recursivedescent nltk.parse.shiftreduce nltk.parse.stanford nltk.parse.transitionparser nltk.parse.util nltk.parse.viterbi nltk.probability s nltk.sem nltk.sem.boxer nltk.sem.chat80 nltk.sem.cooper_storage nltk.sem.drt nltk.sem.drt_glue_demo nltk.sem.evaluate nltk.sem.glue nltk.sem.hole nltk.sem.lfg nltk.sem.linearlogic nltk.sem.logic nltk.sem.relextract nltk.sem.skolemize nltk.sem.util nltk.sentiment nltk.sentiment.sentiment_analyzer nltk.sentiment.util nltk.sentiment.vader nltk.stem nltk.stem.api nltk.stem.arlstem nltk.stem.arlstem2 nltk.stem.cistem nltk.stem.isri nltk.stem.lancaster nltk.stem.porter nltk.stem.regexp nltk.stem.rslp nltk.stem.snowball nltk.stem.util nltk.stem.wordnet t nltk.tabdata nltk.tag nltk.tag.api nltk.tag.brill nltk.tag.brill_trainer nltk.tag.crf nltk.tag.hmm nltk.tag.hunpos nltk.tag.mapping nltk.tag.perceptron nltk.tag.senna nltk.tag.sequential nltk.tag.stanford nltk.tag.tnt nltk.tag.util nltk.tbl nltk.tbl.api nltk.tbl.demo nltk.tbl.erroranalysis nltk.tbl.feature nltk.tbl.rule nltk.tbl.template nltk.text nltk.tgrep nltk.tokenize nltk.tokenize.api nltk.tokenize.casual nltk.tokenize.destructive nltk.tokenize.legality_principle nltk.tokenize.mwe nltk.tokenize.nist nltk.tokenize.punkt nltk.tokenize.regexp nltk.tokenize.repp nltk.tokenize.sexpr nltk.tokenize.simple nltk.tokenize.sonority_sequencing nltk.tokenize.stanford nltk.tokenize.stanford_segmenter nltk.tokenize.texttiling nltk.tokenize.toktok nltk.tokenize.treebank nltk.tokenize.util nltk.toolbox nltk.translate nltk.translate.api nltk.translate.bleu_score nltk.translate.chrf_score nltk.translate.gale_church nltk.translate.gdfa nltk.translate.gleu_score nltk.translate.ibm1 nltk.translate.ibm2 nltk.translate.ibm3 nltk.translate.ibm4 nltk.translate.ibm5 nltk.translate.ibm_model nltk.translate.lepor nltk.translate.meteor_score nltk.translate.metrics nltk.translate.nist_score nltk.translate.phrase_based nltk.translate.ribes_score nltk.translate.stack_decoder nltk.tree nltk.tree.immutable nltk.tree.parented nltk.tree.parsing nltk.tree.prettyprinter nltk.tree.probabilistic nltk.tree.transforms nltk.tree.tree nltk.treeprettyprinter nltk.treetransforms nltk.twitter nltk.twitter.api nltk.twitter.common u nltk.util w nltk.wsd