Index

A

AbstractSegmenter (class in wordseg.algos.dibs)

B

boundaries() (in module wordseg.folding) BoundaryEvaluation (class in wordseg.evaluate)

BoundaryNoEdgeEvaluation (class in wordseg.evaluate) build_colloc0_grammar() (in module wordseg.algos.ag)

C

check_grammar() (in module wordseg.algos.ag) check_level() (wordseg.separator.Separator method) check_separator() (wordseg.separator.Separator method) check_utterance() (in module wordseg.prepare)

compute_class_labels() (in module wordseg.evaluate) CorpusStatistics (class in wordseg.statistics) CorpusSummary (class in wordseg.algos.dibs) Counter (class in wordseg.algos.dibs)

D

DEFAULT_ARGS (in module wordseg.algos.ag) describe_all() (wordseg.statistics.CorpusStatistics method)

describe_corpus() (wordseg.statistics.CorpusStatistics method) describe_tokens() (wordseg.statistics.CorpusStatistics method) diphones (wordseg.algos.dibs.CorpusSummary attribute)

E

evaluate() (in module wordseg.evaluate)

exact_match() (wordseg.evaluate.TokenEvaluation method)

F

fold() (in module wordseg.folding)

forbidden_chars (wordseg.separator.Separator attribute) fscore() (wordseg.evaluate.TokenEvaluation method)

G

get_boundary_positions() (wordseg.evaluate.BoundaryEvaluation static method) (wordseg.evaluate.BoundaryNoEdgeEvaluation static method)

get_grammar_files() (in module wordseg.algos.ag) gold() (in module wordseg.prepare) GoldSegmenter (class in wordseg.algos.dibs)

I

increment() (wordseg.algos.dibs.Counter method) init_diphones() (wordseg.algos.dibs.AbstractSegmenter method) (wordseg.algos.dibs.GoldSegmenter method) (wordseg.algos.dibs.LexicalSegmenter method) (wordseg.algos.dibs.PhrasalSegmenter method)

internal_diphones (wordseg.algos.dibs.CorpusSummary attribute) is_parent_in_grammar() (in module wordseg.algos.ag) iterate() (wordseg.separator.Separator method)

L

levels() (wordseg.separator.Separator method) LexicalSegmenter (class in wordseg.algos.dibs)

lexicon (wordseg.algos.dibs.CorpusSummary attribute) lexicon_check() (wordseg.evaluate.TypeEvaluation static method)

M

module wordseg.algos.ag wordseg.algos.baseline wordseg.algos.dibs wordseg.algos.dpseg wordseg.algos.puddle wordseg.algos.tp wordseg.evaluate wordseg.folding wordseg.prepare wordseg.separator wordseg.statistics wordseg.syllabification

most_common() (wordseg.algos.ag.ParseCounter method) most_common_tokens() (wordseg.statistics.CorpusStatistics method)

N

normalized_segmentation_entropy() (wordseg.statistics.CorpusStatistics method)

O

open_datafile() (wordseg.syllabification.Syllabifier static method)

P

ParseCounter (class in wordseg.algos.ag) PhrasalSegmenter (class in wordseg.algos.dibs) phrase_final (wordseg.algos.dibs.CorpusSummary attribute) phrase_initial (wordseg.algos.dibs.CorpusSummary attribute)

postprocess() (in module wordseg.algos.ag) precision() (wordseg.evaluate.TokenEvaluation method) prepare() (in module wordseg.prepare) Puddle (class in wordseg.algos.puddle) punctuation_re (in module wordseg.prepare)

R

read_data() (in module wordseg.evaluate)

recall() (wordseg.evaluate.TokenEvaluation method) remove() (wordseg.separator.Separator method)

S

segment() (in module wordseg.algos.ag) (in module wordseg.algos.baseline) (in module wordseg.algos.dibs) (in module wordseg.algos.dpseg) (in module wordseg.algos.puddle) (in module wordseg.algos.tp) (wordseg.algos.dibs.AbstractSegmenter method) (wordseg.algos.puddle.Puddle method) segment_oracle() (in module wordseg.algos.baseline) SegmentationSummary (class in wordseg.evaluate)

Separator (class in wordseg.separator) spanning_diphones (wordseg.algos.dibs.CorpusSummary attribute) split() (wordseg.separator.Separator method) strip() (wordseg.separator.Separator method) summarize() (wordseg.evaluate.SegmentationSummary method) summarize_utterance() (wordseg.evaluate.SegmentationSummary method) summary (wordseg.algos.dibs.CorpusSummary attribute) summary() (in module wordseg.evaluate) Syllabifier (class in wordseg.syllabification) syllabify() (wordseg.syllabification.Syllabifier method)

T

to_dict() (wordseg.evaluate.SegmentationSummary method) TokenEvaluation (class in wordseg.evaluate) tokenize() (wordseg.separator.Separator method)

tokens (wordseg.statistics.CorpusStatistics attribute) train() (wordseg.algos.puddle.Puddle method) TypeEvaluation (class in wordseg.evaluate)

U

unfold() (in module wordseg.folding) UnicodeGenerator (class in wordseg.algos.dpseg) unigram (wordseg.statistics.CorpusStatistics attribute) update() (wordseg.algos.ag.ParseCounter method) (wordseg.evaluate.TokenEvaluation method)

update_lists() (wordseg.evaluate.BoundaryEvaluation method) (wordseg.evaluate.TokenEvaluation method) (wordseg.evaluate.TypeEvaluation method) upper_levels() (wordseg.separator.Separator method)

W

wordseg.algos.ag module wordseg.algos.baseline module wordseg.algos.dibs module wordseg.algos.dpseg module wordseg.algos.puddle module wordseg.algos.tp module

wordseg.evaluate module wordseg.folding module wordseg.prepare module wordseg.separator module wordseg.statistics module wordseg.syllabification module

Y

yield_parses() (in module wordseg.algos.ag)