Index

_

__dict__ (pythainlp.khavee.KhaveeVerifier attribute) (pythainlp.spell.NorvigSpellChecker attribute) __init__() (pythainlp.augment.lm.FastTextAug method) (pythainlp.augment.lm.Thai2transformersAug method) (pythainlp.augment.word2vec.bpemb_wv.BPEmbAug method) (pythainlp.augment.word2vec.LTW2VAug method) (pythainlp.augment.word2vec.Thai2fitAug method) (pythainlp.augment.word2vec.Word2VecAug method) (pythainlp.augment.WordNetAug method) (pythainlp.chat.ChatBotModel method) (pythainlp.classify.GzipModel method) (pythainlp.el.EntityLinker method) (pythainlp.generate.Bigram method) (pythainlp.generate.Trigram method) (pythainlp.generate.Unigram method) (pythainlp.generate.wangchanglm.WangChanGLM method) (pythainlp.khavee.KhaveeVerifier method) (pythainlp.phayathaibert.NamedEntityTagger method) (pythainlp.phayathaibert.PartOfSpeechTagger method) (pythainlp.phayathaibert.ThaiTextAugmenter method) (pythainlp.phayathaibert.ThaiTextProcessor method) (pythainlp.spell.NorvigSpellChecker method) (pythainlp.summarize.keybert.KeyBERT method), [1] (pythainlp.tag.NER method) (pythainlp.tag.NNER method) (pythainlp.tag.thainer.ThaiNameTagger method) (pythainlp.tokenize.attacut.AttacutTokenizer method) (pythainlp.tokenize.han_solo.Featurizer method) (pythainlp.tokenize.longest.LongestMatchTokenizer method) (pythainlp.tokenize.multi_cut.LatticeString method) (pythainlp.tokenize.Tokenizer method) (pythainlp.translate.en_th.EnThTranslator method) (pythainlp.translate.en_th.ThEnTranslator method) (pythainlp.translate.th_fr.ThFrTranslator method) (pythainlp.translate.Translate method) (pythainlp.translate.zh_th.ThZhTranslator method) (pythainlp.translate.zh_th.ZhThTranslator method) (pythainlp.transliterate.wunsen.WunsenTransliterate method) (pythainlp.ulmfit.ThaiTokenizer method) (pythainlp.util.Trie method) (pythainlp.util.Trie.Node method) (pythainlp.wangchanberta.NamedEntityRecognition method) (pythainlp.wangchanberta.ThaiNameTagger method) (pythainlp.word_vector.WordVector method)

__module__ (pythainlp.khavee.KhaveeVerifier attribute) (pythainlp.spell.NorvigSpellChecker attribute)

A

add() (pythainlp.util.Trie method) add_special_cases() (pythainlp.ulmfit.ThaiTokenizer method) aksonhan_to_current() (in module pythainlp.ancient) AttacutTokenizer (class in pythainlp.tokenize.attacut) audio_vector() (in module pythainlp.soundex.sound) augment() (pythainlp.augment.lm.FastTextAug method) (pythainlp.augment.lm.Thai2transformersAug method) (pythainlp.augment.word2vec.bpemb_wv.BPEmbAug method) (pythainlp.augment.word2vec.LTW2VAug method) (pythainlp.augment.word2vec.Thai2fitAug method) (pythainlp.augment.word2vec.Word2VecAug method) (pythainlp.augment.WordNetAug method) (pythainlp.phayathaibert.ThaiTextAugmenter method)

B

benchmark() (in module pythainlp.benchmarks.word_tokenization)

Bigram (class in pythainlp.generate) BPEmbAug (class in pythainlp.augment.word2vec.bpemb_wv)

C

chat() (pythainlp.chat.ChatBotModel method) ChatBotModel (class in pythainlp.chat) check_aek_too() (pythainlp.khavee.KhaveeVerifier method) check_karu_lahu() (pythainlp.khavee.KhaveeVerifier method) check_klon() (pythainlp.khavee.KhaveeVerifier method) check_marttra() (pythainlp.khavee.KhaveeVerifier method) check_sara() (pythainlp.khavee.KhaveeVerifier method)

children (pythainlp.util.Trie.Node attribute) chunk_parse() (in module pythainlp.tag) compute_stats() (in module pythainlp.benchmarks.word_tokenization) coreference_resolution() (in module pythainlp.coref) correct() (in module pythainlp.spell) (pythainlp.spell.NorvigSpellChecker method) correct_sent() (in module pythainlp.spell)

D

DEFAULT_SPELL_CHECKER (in module pythainlp.spell) dependency_parsing() (in module pythainlp.parse)

dictionary() (pythainlp.spell.NorvigSpellChecker method) doesnt_match() (pythainlp.word_vector.WordVector method)

E

embed() (pythainlp.summarize.keybert.KeyBERT method), [1] end (pythainlp.util.Trie.Node attribute) EnThTranslator (class in pythainlp.translate.en_th) EntityLinker (class in pythainlp.el) environment variable PYTHAINLP_DATA_DIR, [1] PYTHAINLP_READ_MODE

extract_features() (in module pythainlp.tokenize.crfcut) extract_keywords() (in module pythainlp.summarize) (pythainlp.summarize.keybert.KeyBERT method), [1]

F

FastTextAug (class in pythainlp.augment.lm) featurize() (pythainlp.tokenize.han_solo.Featurizer method) Featurizer (class in pythainlp.tokenize.han_solo)

find_all_segment() (in module pythainlp.tokenize.multi_cut) find_synonyms() (pythainlp.augment.WordNetAug method) freq() (pythainlp.spell.NorvigSpellChecker method)

G

gen_instruct() (pythainlp.generate.wangchanglm.WangChanGLM method) gen_sentence() (pythainlp.generate.Bigram method) (pythainlp.generate.Trigram method) (pythainlp.generate.Unigram method) generate() (pythainlp.augment.lm.Thai2transformersAug method) (pythainlp.phayathaibert.ThaiTextAugmenter method) get_el() (pythainlp.el.EntityLinker method) get_model() (pythainlp.word_vector.WordVector method)

get_ner() (in module pythainlp.tag.tltk) (pythainlp.phayathaibert.NamedEntityTagger method) (pythainlp.tag.thainer.ThaiNameTagger method) (pythainlp.wangchanberta.NamedEntityRecognition method) (pythainlp.wangchanberta.ThaiNameTagger method) get_sense() (in module pythainlp.wsd) get_tag() (pythainlp.phayathaibert.PartOfSpeechTagger method) GzipModel (class in pythainlp.classify)

H

handle_karun_sound_silence() (pythainlp.khavee.KhaveeVerifier method)

I

instruct_generate() (pythainlp.generate.wangchanglm.WangChanGLM method)

is_exclude() (pythainlp.generate.wangchanglm.WangChanGLM method) is_sumpus() (pythainlp.khavee.KhaveeVerifier method)

K

KeyBERT (class in pythainlp.summarize.keybert), [1]

KhaveeVerifier (class in pythainlp.khavee) known() (pythainlp.spell.NorvigSpellChecker method)

L

LatticeString (class in pythainlp.tokenize.multi_cut) list_to_string() (in module pythainlp.tokenize.thaisumcut) lk82() (in module pythainlp.soundex) load_dict() (in module pythainlp.tokenize.nlpo3) load_engine() (pythainlp.tag.NER method) (pythainlp.tag.NNER method) load_model() (pythainlp.chat.ChatBotModel method) (pythainlp.generate.wangchanglm.WangChanGLM method) (pythainlp.translate.Translate method)

load_w2v() (pythainlp.augment.word2vec.bpemb_wv.BPEmbAug method) (pythainlp.augment.word2vec.LTW2VAug method) (pythainlp.augment.word2vec.Thai2fitAug method) load_wordvector() (pythainlp.word_vector.WordVector method) LongestMatchTokenizer (class in pythainlp.tokenize.longest) LTW2VAug (class in pythainlp.augment.word2vec)

M

metasound() (in module pythainlp.soundex) middle_cut() (in module pythainlp.tokenize.thaisumcut) mmcut() (in module pythainlp.tokenize.multi_cut) modify_sent() (pythainlp.augment.lm.FastTextAug method) (pythainlp.augment.word2vec.Word2VecAug method) module pythainlp.summarize.keybert pythainlp.tokenize.attacut pythainlp.tokenize.crfcut pythainlp.tokenize.deepcut pythainlp.tokenize.etcc pythainlp.tokenize.han_solo pythainlp.tokenize.longest pythainlp.tokenize.multi_cut pythainlp.tokenize.nercut pythainlp.tokenize.newmm pythainlp.tokenize.nlpo3 pythainlp.tokenize.oskut pythainlp.tokenize.pyicu pythainlp.tokenize.sefr_cut pythainlp.tokenize.tcc pythainlp.tokenize.tcc_p pythainlp.tokenize.thaisumcut pythainlp.transliterate.royin.romanize pythainlp.transliterate.thai2rom.romanize

most_similar_cosmul() (pythainlp.word_vector.WordVector method)

N

NamedEntityRecognition (class in pythainlp.wangchanberta) NamedEntityTagger (class in pythainlp.phayathaibert) NER (class in pythainlp.tag)

nighit() (in module pythainlp.morpheme) NNER (class in pythainlp.tag) NorvigSpellChecker (class in pythainlp.spell)

P

pad() (pythainlp.tokenize.han_solo.Featurizer method) PartOfSpeechTagger (class in pythainlp.phayathaibert) pos_tag() (in module pythainlp.tag) pos_tag_sents() (in module pythainlp.tag) prayut_and_somchaip() (in module pythainlp.soundex) predict() (pythainlp.classify.GzipModel method) prefixes() (pythainlp.util.Trie method) preprocess() (pythainlp.phayathaibert.ThaiTextProcessor method) preprocessing() (in module pythainlp.benchmarks.word_tokenization) prob() (pythainlp.generate.Bigram method) (pythainlp.generate.Trigram method) (pythainlp.spell.NorvigSpellChecker method) pythainlp.summarize.keybert module pythainlp.tokenize.attacut module pythainlp.tokenize.crfcut module pythainlp.tokenize.deepcut module pythainlp.tokenize.etcc module pythainlp.tokenize.han_solo module pythainlp.tokenize.longest module

pythainlp.tokenize.multi_cut module pythainlp.tokenize.nercut module pythainlp.tokenize.newmm module pythainlp.tokenize.nlpo3 module pythainlp.tokenize.oskut module pythainlp.tokenize.pyicu module pythainlp.tokenize.sefr_cut module pythainlp.tokenize.tcc module pythainlp.tokenize.tcc_p module pythainlp.tokenize.thaisumcut module pythainlp.transliterate.royin.romanize module pythainlp.transliterate.thai2rom.romanize module PYTHAINLP_DATA_DIR

R

remove() (pythainlp.util.Trie method) remove_space() (pythainlp.phayathaibert.ThaiTextProcessor method) replace_newlines() (pythainlp.phayathaibert.ThaiTextProcessor method) replace_rep_after() (pythainlp.phayathaibert.ThaiTextProcessor method) replace_spaces() (pythainlp.phayathaibert.ThaiTextProcessor method)

replace_url() (pythainlp.phayathaibert.ThaiTextProcessor method) replace_wrep_post() (pythainlp.phayathaibert.ThaiTextProcessor method) reset_chat() (pythainlp.chat.ChatBotModel method) rm_brackets() (pythainlp.phayathaibert.ThaiTextProcessor method) rm_useless_spaces() (pythainlp.phayathaibert.ThaiTextProcessor method)

S

segment() (in module pythainlp.phayathaibert) (in module pythainlp.tokenize.attacut) (in module pythainlp.tokenize.crfcut) (in module pythainlp.tokenize.deepcut) (in module pythainlp.tokenize.etcc) (in module pythainlp.tokenize.han_solo) (in module pythainlp.tokenize.longest) (in module pythainlp.tokenize.multi_cut) (in module pythainlp.tokenize.nercut) (in module pythainlp.tokenize.newmm) (in module pythainlp.tokenize.nlpo3) (in module pythainlp.tokenize.oskut) (in module pythainlp.tokenize.pyicu) (in module pythainlp.tokenize.sefr_cut) (in module pythainlp.tokenize.tcc) (in module pythainlp.tokenize.tcc_p)

sentence_vectorizer() (pythainlp.word_vector.WordVector method) set_tokenize_engine() (pythainlp.tokenize.Tokenizer method) similarity() (pythainlp.word_vector.WordVector method) soundex() (in module pythainlp.soundex) spell() (in module pythainlp.spell) (pythainlp.spell.NorvigSpellChecker method) spell_sent() (in module pythainlp.spell) split_into_sentences() (pythainlp.tokenize.thaisumcut.ThaiSentenceSegmentor method) summarize() (in module pythainlp.summarize)

T

tag() (pythainlp.tag.NER method) (pythainlp.tag.NNER method) tag_provinces() (in module pythainlp.tag) tcc() (in module pythainlp.tokenize.tcc) (in module pythainlp.tokenize.tcc_p) tcc_pos() (in module pythainlp.tokenize.tcc) (in module pythainlp.tokenize.tcc_p) Thai2fitAug (class in pythainlp.augment.word2vec) Thai2transformersAug (class in pythainlp.augment.lm) ThaiNameTagger (class in pythainlp.tag.thainer) (class in pythainlp.wangchanberta) ThaiSentenceSegmentor (class in pythainlp.tokenize.thaisumcut) ThaiTextAugmenter (class in pythainlp.phayathaibert) ThaiTextProcessor (class in pythainlp.phayathaibert) ThaiTokenizer (class in pythainlp.ulmfit) ThEnTranslator (class in pythainlp.translate.en_th) ThFrTranslator (class in pythainlp.translate.th_fr) ThZhTranslator (class in pythainlp.translate.zh_th) tokenize() (pythainlp.augment.lm.FastTextAug method) (pythainlp.tokenize.attacut.AttacutTokenizer method) (pythainlp.tokenize.longest.LongestMatchTokenizer method)

Tokenizer (class in pythainlp.tokenize) tokenizer() (pythainlp.augment.word2vec.bpemb_wv.BPEmbAug method) (pythainlp.augment.word2vec.LTW2VAug method) (pythainlp.augment.word2vec.Thai2fitAug method) (pythainlp.ulmfit.ThaiTokenizer static method) train() (pythainlp.classify.GzipModel method) Translate (class in pythainlp.translate) translate() (pythainlp.translate.en_th.EnThTranslator method) (pythainlp.translate.en_th.ThEnTranslator method) (pythainlp.translate.th_fr.ThFrTranslator method) (pythainlp.translate.Translate method) (pythainlp.translate.zh_th.ThZhTranslator method) (pythainlp.translate.zh_th.ZhThTranslator method) transliterate() (pythainlp.transliterate.wunsen.WunsenTransliterate method) Trie (class in pythainlp.util) Trie.Node (class in pythainlp.util) Trigram (class in pythainlp.generate)

U

udom83() (in module pythainlp.soundex)

Unigram (class in pythainlp.generate)

W

WangChanGLM (class in pythainlp.generate.wangchanglm) word2audio() (in module pythainlp.soundex.sound) Word2VecAug (class in pythainlp.augment.word2vec) word_approximation() (in module pythainlp.soundex.sound)

word_tokenize() (pythainlp.tokenize.Tokenizer method) WordNetAug (class in pythainlp.augment) WordVector (class in pythainlp.word_vector) WunsenTransliterate (class in pythainlp.transliterate.wunsen)

Z

ZhThTranslator (class in pythainlp.translate.zh_th)