{ "lang":"fa", "name":"core_news_lg", "version":"3.8.0", "description":"Persian pipeline optimized for CPU. Components: tok2vec, tagger, morphologizer, trainable_lemmatizer, parser, ner. Entity labels: PER, LOC, ORG, DAT, MON, TIM, PCT.", "author":"Kiyarash Fazeli", "email":"kiyarash@nlogn.ir", "url":"https://github.com/Fazel94/spacy-persian", "license":"CC BY-SA 4.0", "spacy_version":">=3.8.14,<3.9.0", "spacy_git_version":"0069cf9", "vectors":{ "width":300, "vectors":200000, "keys":-1, "name":"floret" }, "labels":{ "tok2vec":[ ], "tagger":[ "ADJ_AJCM", "ADJ_AJCM_AUX", "ADJ_AJCM_AUX_PUNC", "ADJ_AJP", "ADJ_AJP_AUX", "ADJ_AJP_AUX_PUNC", "ADJ_AJP_AUX_PUNC_PUNC", "ADJ_AJP_PR_JOPER", "ADJ_AJP_PR_JOPER_AUX_PUNC", "ADJ_AJP_PR_JOPER_PUNC", "ADJ_AJSUP", "ADR_POSADR", "ADR_PRADR", "ADV_SADV", "AUX", "AUX_PASS", "AUX_SUBR", "CONJ", "IDEN", "N_ANM", "N_ANM_ADR_POSADR", "N_ANM_ADR_POSADR_PUNC", "N_ANM_AUX", "N_ANM_AUX_PUNC", "N_ANM_AUX_PUNC_PUNC", "N_ANM_PR_JOPER", "N_ANM_PR_JOPER_PUNC", "N_ANM_V_ACT", "N_IANM", "N_IANM_AUX", "N_IANM_AUX_PUNC", "N_IANM_PR_JOPER", "N_IANM_PR_JOPER_PUNC", "N_IANM_PR_SEPER", "PART", "POSNUM", "POSTP", "PREM_AMBAJ", "PREM_AMBAJ_N_IANM", "PREM_DEMAJ", "PREM_DEMAJ_N_IANM", "PREM_EXAJ", "PREM_QUAJ", "PRENUM", "PREP", "PREP_N_IANM", "PREP_PREM_AMBAJ", "PREP_PREM_DEMAJ", "PREP_PR_DEMON", "PREP_PR_JOPER", "PREP_PR_JOPER_PUNC", "PREP_PR_SEPER", "PR_CREFX", "PR_CREFX_AUX_PUNC", "PR_CREFX_PR_JOPER", "PR_DEMON", "PR_DEMON_AUX", "PR_DEMON_AUX_PUNC", "PR_DEMON_CONJ", "PR_DEMON_SUBR", "PR_INTG", "PR_INTG_AUX", "PR_INTG_AUX_PUNC", "PR_JOPER", "PR_JOPER_PART", "PR_JOPER_POSTP", "PR_RECPR", "PR_SEPER", "PR_SEPER_AUX", "PR_SEPER_AUX_PUNC", "PR_SEPER_AUX_PUNC_PUNC", "PR_SEPER_POSTP", "PR_SEPER_POSTP_PUNC", "PR_SEPER_PR_JOPER", "PR_UCREFX", "PR_UCREFX_PR_JOPER", "PR_UCREFX_PR_JOPER_PUNC", "PSUS", "PSUS_ADR_POSADR_PUNC", "PSUS_PR_JOPER", "PSUS_PR_JOPER_PUNC", "PUNC", "SUBR", "SUBR_SUBR", "V_ACT", "V_ACT_PR_JOPER", "V_ACT_PR_JOPER_PUNC", "V_MODL", "V_MODL_PR_SEPER", "V_PASS" ], "morphologizer":[ "POS=ADP", "Number=Sing|POS=NOUN", "POS=DET|PronType=Dem", "POS=ADJ", "POS=CCONJ", "POS=PUNCT", "Number=Plur|POS=NOUN", "Number=Sing|POS=VERB|Person=3|Tense=Past|Voice=Act", "Number=Sing|POS=PROPN", "POS=PROPN", "Number=Plur|POS=VERB|Person=3|Tense=Past|Voice=Act", "Number=Sing|POS=PRON", "POS=INTJ", "POS=PRON", "Mood=Imp|Number=Sing|POS=VERB|Person=2|Tense=Pres|VerbForm=Fin|Voice=Act", "POS=NUM", "POS=ADV", "Number=Plur|POS=VERB|Person=3|Tense=Pres|Voice=Act", "Number=Sing|POS=NOUN|Person=3|PronType=Prs", "POS=SCONJ", "Number=Sing|POS=PROPN|Person=3", "Number=Sing|POS=PRON|Person=3|PronType=Prs", "Number=Sing|POS=VERB|Person=3|Tense=Pres|Voice=Act", "Number=Sing|POS=VERB|Person=3|Tense=Past|VerbForm=Part|Voice=Pass", "Number=Sing|POS=VERB|Person=3|VerbForm=Part|Voice=Pass", "Number=Sing|POS=AUX|Person=3", "Number=Sing|POS=VERB|Person=3|Tense=Past|Voice=Pass", "Number=Sing|POS=VERB|Person=3|Tense=Pres", "Number=Plur|POS=VERB|Person=3|VerbForm=Part|Voice=Act", "Number=Sing|POS=VERB|Person=3|Tense=Past", "Number=Sing|POS=AUX|Person=3|Tense=Pres", "Number=Plur|POS=PRON|Person=3|PronType=Prs", "Mood=Sub|Number=Plur|POS=AUX|Person=3|Tense=Pres|VerbForm=Fin", "Number=Plur|POS=VERB|Person=3|Voice=Act", "Number=Sing|POS=VERB|Person=3|VerbForm=Part|Voice=Act", "Number=Sing|POS=VERB|Person=3|Tense=Past|VerbForm=Part|Voice=Act", "Number=Sing|POS=NUM", "Number=Plur|POS=PROPN", "Number=Sing|POS=VERB|Person=3|Voice=Act", "Number=Plur,Sing|POS=NOUN|Person=1|PronType=Prs", "Number=Sing|POS=VERB|Person=1|Tense=Past|Voice=Act", "Number=Plur|POS=VERB|Person=1|Voice=Act", "Number=Sing|POS=PRON|Person=1|PronType=Prs", "Number=Sing|POS=NOUN|Person=1|PronType=Prs", "Number=Sing|POS=AUX|Person=3|Polarity=Neg", "Number=Sing|POS=PRON|Person=2|PronType=Prs", "Number=Sing|POS=VERB|Person=2|Voice=Act", "Number=Sing|POS=VERB|Person=3", "Mood=Imp|Number=Plur|POS=VERB|Person=2|Tense=Pres|VerbForm=Fin|Voice=Act", "POS=DET", "Number=Sing|POS=NOUN|Typo=Yes", "POS=X", "Number=Sing|POS=AUX|Person=3|Tense=Past", "POS=ADP|PronType=Dem", "Number=Plur|POS=VERB|Person=3", "POS=AUX", "Number=Plur|POS=AUX|Person=3", "Mood=Ind|Number=Sing|POS=AUX|Person=3|Tense=Fut|VerbForm=Fin", "Number=Plur|POS=VERB|Person=1|Tense=Pres|Voice=Act", "Number=Plur|POS=VERB|Person=3|VerbForm=Part|Voice=Pass", "Number=Plur|POS=VERB|Person=1|Polarity=Neg|VerbForm=Part|Voice=Act", "Number=Sing|POS=VERB|Person=1", "Number=Sing|POS=VERB|Person=1|Tense=Pres|Voice=Act", "Number=Sing|POS=VERB|Person=1|Voice=Act", "Mood=Ind|Number=Plur|POS=AUX|Person=3|Tense=Fut|VerbForm=Fin", "POS=PART", "Mood=Sub|Number=Sing|POS=VERB|Person=3|Tense=Pres|VerbForm=Fin", "Number=Plur|POS=PRON|Person=1|PronType=Prs", "Number=Plur|POS=PRON", "Number=Plur|POS=VERB|Person=3|Polarity=Neg|VerbForm=Part|Voice=Act", "Number=Sing|POS=VERB|Person=3|Polarity=Neg|Tense=Pres|Voice=Act", "Number=Plur|POS=VERB|Person=1|Polarity=Neg|Voice=Act", "Mood=Imp|Number=Plur|POS=VERB|Person=2|Polarity=Neg|Tense=Pres|VerbForm=Fin|Voice=Act", "Number=Sing|POS=VERB|Person=1|VerbForm=Part|Voice=Act", "Number=Plur|POS=VERB|Person=3|Polarity=Neg|Tense=Pres|Voice=Act", "Number=Sing|POS=VERB|Person=3|Polarity=Neg|Tense=Past|VerbForm=Part|Voice=Act", "POS=VERB|Tense=Pres|Voice=Act", "Number=Plur|POS=VERB|Person=1|Tense=Past|Voice=Act", "Number=Sing|POS=VERB|Person=1|Polarity=Neg|VerbForm=Part|Voice=Act", "Number=Plur|POS=VERB|Person=3|Polarity=Neg|Voice=Act", "Number=Plur|POS=VERB|Person=2|Polarity=Neg|Tense=Past|Voice=Act", "Number=Plur|POS=VERB|Person=2|Tense=Past|Voice=Act", "Number=Plur,Sing|POS=NOUN|Person=3|PronType=Prs", "Number=Plur|POS=VERB|Person=1|Polarity=Neg|Tense=Pres|Voice=Act", "Mood=Sub|Number=Plur|POS=AUX|Person=1|Tense=Pres|VerbForm=Fin", "Number=Plur|POS=AUX|Person=3|Tense=Past", "Mood=Ind|Number=Plur|POS=AUX|Person=1|Polarity=Neg|Tense=Fut|VerbForm=Fin", "Number=Plur|POS=VERB|Person=1|VerbForm=Part|Voice=Act", "Number=Sing|POS=VERB|Person=3|Polarity=Neg", "Number=Sing|POS=AUX|Person=1|Tense=Past", "Number=Sing|POS=VERB|Person=3|Polarity=Neg|Tense=Past|Voice=Act", "POS=DET|PronType=Int", "Number=Sing|POS=VERB|Person=3|Polarity=Neg|VerbForm=Part|Voice=Act", "Number=Plur|POS=VERB|Person=3|Polarity=Neg|Tense=Past|Voice=Act", "Mood=Ind|Number=Sing|POS=AUX|Person=1|Tense=Fut|VerbForm=Fin", "Number=Sing|POS=VERB|Person=1|Polarity=Neg|Tense=Pres|Voice=Act", "Number=Plur|POS=VERB|Person=1", "Mood=Sub|Number=Sing|POS=AUX|Person=3|Tense=Pres|VerbForm=Fin", "POS=VERB|Polarity=Neg", "Number=Sing|POS=VERB|Person=3|Polarity=Neg|Voice=Act", "Mood=Ind|Number=Sing|POS=AUX|Person=3|Polarity=Neg|Tense=Fut|VerbForm=Fin", "Mood=Sub|Number=Plur|POS=AUX|Person=2|Tense=Pres|VerbForm=Fin", "POS=VERB|Polarity=Neg|Tense=Pres|Voice=Act", "POS=NOUN", "Mood=Imp|Number=Sing|POS=VERB|Person=1|Polarity=Neg|Tense=Pres|VerbForm=Fin|Voice=Act", "POS=AUX|Polarity=Neg", "Number=Sing|POS=VERB|Person=2|Tense=Pres|Voice=Act", "Number=Plur|POS=AUX|Person=3|Polarity=Neg", "POS=VERB|Tense=Pres", "Number=Sing|POS=VERB|Person=3|Polarity=Neg|Tense=Past|Voice=Pass", "Number=Plur|POS=VERB|Person=3|Polarity=Neg", "Number=Sing|POS=VERB|Person=2|Tense=Past|Voice=Act", "Number=Plur|POS=VERB|Person=2|Voice=Act", "Number=Plur,Sing|POS=AUX|Person=3|PronType=Prs", "Number=Plur|POS=AUX|Person=2|Polarity=Neg", "Number=Sing|POS=ADJ|Person=3|PronType=Prs", "Number=Plur|POS=ADJ|Person=3|PronType=Prs", "Number=Plur|POS=PRON|Person=2|PronType=Prs", "Number=Plur|POS=VERB|Person=1|Polarity=Neg|Tense=Past|Voice=Act", "Number=Sing|POS=VERB|Person=3|Polarity=Neg|Tense=Past", "Number=Sing|POS=AUX|Person=3|Polarity=Neg|Tense=Pres", "Number=Sing|POS=VERB|Person=1|Polarity=Neg|Tense=Past|Voice=Act", "Number=Plur|POS=AUX|Person=1", "Number=Sing|POS=VERB|Person=2", "Number=Sing|POS=NOUN|Person=3", "Number=Plur|POS=VERB|Person=2|VerbForm=Part|Voice=Act", "Mood=Imp|Number=Plur|POS=VERB|Person=3|Tense=Pres|VerbForm=Fin|Voice=Act", "Number=Plur|POS=VERB|Person=2|Tense=Pres|Voice=Act", "Mood=Ind|Number=Plur|POS=AUX|Person=3|Polarity=Neg|Tense=Fut|VerbForm=Fin", "Mood=Ind|Number=Plur|POS=AUX|Person=1|Tense=Fut|VerbForm=Fin", "Number=Plur,Sing|POS=VERB|Person=3", "Number=Plur|POS=ADJ|Person=2|PronType=Prs", "Number=Sing|POS=AUX|Person=3|Voice=Act", "Number=Sing|POS=ADJ|Person=1|PronType=Prs", "POS=VERB", "Number=Sing|POS=NOUN|Person=2|PronType=Prs", "Number=Sing|POS=VERB|Person=1|Polarity=Neg", "Number=Plur|POS=NOUN|Person=3|PronType=Prs", "Number=Sing|POS=AUX|Person=1|Voice=Act", "Number=Sing|POS=VERB|Person=2|Polarity=Neg|Tense=Pres|Voice=Act", "Number=Plur|POS=AUX|Person=2", "Number=Sing|POS=AUX|Person=2", "Number=Sing|POS=VERB|Person=1|Polarity=Neg|Voice=Act", "Number=Sing|POS=VERB|Person=2|Polarity=Neg|VerbForm=Part|Voice=Act", "Mood=Imp|Number=Sing|POS=VERB|Person=2|Polarity=Neg|Tense=Pres|VerbForm=Fin|Voice=Act", "Number=Plur|POS=NOUN|Person=1|PronType=Prs", "Number=Plur|POS=AUX|Person=1|Tense=Past", "Number=Plur|POS=ADJ|Person=1|PronType=Prs", "Number=Sing|POS=ADP", "Number=Sing|POS=PROPN|Person=1|PronType=Prs", "Number=Plur|POS=VERB|Person=2|Polarity=Neg|Voice=Act", "Number=Plur,Sing|POS=AUX|Person=3", "Number=Sing|POS=PUNCT|Person=3", "Number=Sing|POS=ADJ|Person=3", "Number=Plur,Sing|POS=NOUN|Person=2|PronType=Prs", "Number=Sing|POS=PRON|Person=3", "Number=Sing|POS=AUX|Person=2,3|PronType=Prs", "Number=Sing|POS=ADJ|Person=2|PronType=Prs", "Mood=Sub|Number=Sing|POS=AUX|Person=1|Tense=Pres|VerbForm=Fin", "Number=Plur|POS=NOUN|Person=2|PronType=Prs", "Number=Sing|POS=NOUN|PronType=Dem", "Mood=Ind|Number=Sing|POS=AUX|Person=1|Polarity=Neg|Tense=Fut|VerbForm=Fin", "Mood=Ind|Number=Plur|POS=AUX|Person=2|Tense=Fut|VerbForm=Fin", "Number=Plur,Sing|POS=NOUN|Person=3", "Number=Plur|POS=VERB|Person=2", "Mood=Ind|Number=Plur|POS=AUX|Person=2|Polarity=Neg|Tense=Fut|VerbForm=Fin", "Number=Plur|POS=AUX|Person=2|Voice=Act", "Mood=Ind|Number=Sing|POS=AUX|Person=2|Tense=Fut|VerbForm=Fin", "Number=Plur|POS=AUX|Person=3|Voice=Act", "Number=Plur|POS=VERB|Person=2|Polarity=Neg|Tense=Pres|Voice=Act", "Number=Sing|POS=INTJ|Person=1|PronType=Prs", "Number=Plur|POS=AUX|Person=1|Voice=Act", "Number=Plur|POS=VERB|Person=3|Tense=Past", "Number=Plur,Sing|POS=VERB|Person=3|PronType=Prs|Tense=Past|Voice=Act", "Number=Sing|POS=AUX|Person=1", "Number=Sing|POS=PUNCT|Person=1|PronType=Prs", "Number=Sing|POS=VERB|Person=2|Polarity=Neg|Voice=Act", "Number=Sing|POS=AUX|Person=1|Polarity=Neg", "Number=Sing|POS=PUNCT|Person=3|PronType=Prs", "Number=Sing|POS=PRON|Person=1,3|PronType=Prs", "Number=Sing|POS=VERB|Person=2|PronType=Prs", "Number=Sing|POS=VERB|Person=2|VerbForm=Part|Voice=Act", "POS=DET|PronType=Exc", "Number=Sing|POS=VERB|Person=1,3|PronType=Prs|Tense=Past|Voice=Act", "Number=Sing|POS=VERB|Person=3|Tense=Pres|Voice=Pass", "Number=Plur,Sing|POS=PRON|Person=2,3|PronType=Prs", "Number=Sing|POS=VERB|Person=3|Voice=Pass", "Number=Plur|POS=VERB|Person=2|Polarity=Neg|VerbForm=Part|Voice=Act", "Number=Plur|POS=VERB|Person=3|Tense=Pres", "Number=Sing|POS=VERB|Person=3|Polarity=Neg|VerbForm=Part|Voice=Pass", "Number=Sing|POS=AUX|Person=2|Polarity=Neg", "Number=Plur,Sing|POS=PUNCT|Person=1,3|PronType=Prs", "Number=Plur,Sing|POS=PRON|Person=1,3|PronType=Prs", "Number=Sing|POS=VERB|Person=1,2|PronType=Prs|Tense=Pres|Voice=Act", "Number=Sing|POS=PROPN|Person=2|PronType=Prs", "Mood=Sub|Number=Plur|POS=VERB|Person=3|Tense=Pres|VerbForm=Fin", "Mood=Sub|Number=Sing|POS=AUX|Person=2|Tense=Pres|VerbForm=Fin", "Number=Sing|POS=PUNCT|Person=2|PronType=Prs", "Number=Plur,Sing|POS=VERB|Person=1,2|PronType=Prs|Tense=Pres|Voice=Act", "Number=Plur|POS=VERB|Person=3|Polarity=Neg|VerbForm=Part|Voice=Pass", "Number=Plur|POS=PUNCT|Person=3", "Number=Plur,Sing|POS=PROPN|Person=2|PronType=Prs", "Number=Plur,Sing|POS=VERB|Person=1", "Number=Plur,Sing|POS=PUNCT|Person=1|PronType=Prs", "Number=Plur,Sing|POS=PRON|Person=3|PronType=Prs", "Number=Sing|POS=AUX|Person=2|Tense=Past", "Number=Plur,Sing|POS=PROPN|Person=1|PronType=Prs", "Number=Plur|POS=PRON|Person=1,2|PronType=Prs", "Number=Sing|POS=AUX|Person=3|PronType=Prs", "Number=Sing|POS=VERB|Person=3|Polarity=Neg|Tense=Pres", "Number=Sing|POS=VERB|Person=1,2|Polarity=Neg|PronType=Prs|Tense=Pres|Voice=Act", "Number=Plur|POS=ADJ|Person=3", "Number=Plur|POS=VERB|Person=3|Voice=Pass", "Number=Plur|POS=VERB|Person=1|Tense=Pres|Voice=Pass", "Number=Sing|POS=AUX|Person=2|Voice=Act", "Number=Plur|POS=VERB|Person=1|Tense=Pres", "Number=Plur,Sing|POS=VERB|Person=2", "Number=Sing|POS=VERB|Person=1|PronType=Prs", "Number=Plur,Sing|POS=VERB|Person=1|PronType=Prs", "Mood=Imp|Number=Plur|POS=VERB|Person=1|Tense=Pres|VerbForm=Fin|Voice=Act", "Number=Sing|POS=VERB|Person=1,3|PronType=Prs", "Number=Plur|POS=AUX|Person=2|Tense=Past", "Number=Plur,Sing|POS=VERB|Person=3|PronType=Prs", "Number=Sing|POS=VERB|Person=2|Polarity=Neg", "Number=Sing|POS=VERB|Person=2|Voice=Pass", "Number=Plur|POS=VERB|Person=1|Polarity=Neg|Tense=Past", "Number=Plur|POS=VERB|Person=2|Tense=Past|Voice=Pass", "Number=Sing|POS=VERB|Person=3|Polarity=Neg|Voice=Pass", "Number=Sing|POS=VERB|Person=3|PronType=Prs", "Mood=Imp|Number=Sing|POS=VERB|Person=3|Polarity=Neg|Tense=Pres|VerbForm=Fin|Voice=Act", "Mood=Imp|Number=Plur|POS=VERB|Person=1|Polarity=Neg|Tense=Pres|VerbForm=Fin|Voice=Act", "Number=Plur|POS=AUX|Person=1|Polarity=Neg", "Number=Sing|POS=VERB|Voice=Act", "Mood=Imp|Number=Sing|POS=VERB|Person=3|Tense=Past|VerbForm=Fin|Voice=Act", "Number=Plur|POS=VERB|Person=3|Polarity=Neg|Tense=Pres|Voice=Pass", "Number=Sing|POS=VERB|Person=1|Tense=Past", "Number=Plur,Sing|POS=PRON|Person=2|PronType=Prs", "Number=Sing|POS=VERB|Polarity=Neg|Tense=Pres|Voice=Act", "Mood=Imp|Number=Sing|POS=VERB|Person=3|Tense=Pres|VerbForm=Fin|Voice=Act", "Number=Sing|POS=VERB|Person=2|Polarity=Neg|Tense=Past|Voice=Act", "Number=Plur|POS=VERB|Person=2|Tense=Pres", "Number=Sing|POS=ADP|Person=1|PronType=Prs", "POS=VERB|Tense=Past|Voice=Act", "Number=Sing|POS=PUNCT", "Number=Sing|POS=PRON|Person=2,3|PronType=Prs", "Number=Plur|POS=NUM", "Number=Sing|POS=PROPN|Person=3|PronType=Prs", "Number=Plur,Sing|POS=VERB|Person=2,3|PronType=Prs", "Number=Plur|POS=AUX|Person=1|PronType=Prs", "Number=Plur|POS=VERB|Person=3|Tense=Pres|Voice=Pass", "Number=Plur,Sing|POS=AUX|Person=1,3|PronType=Prs", "Number=Plur,Sing|POS=PUNCT|Person=3|PronType=Prs", "Number=Sing|POS=ADP|Person=3|PronType=Prs", "Number=Plur,Sing|POS=VERB|Person=1,3|PronType=Prs|Tense=Pres|Voice=Act", "Number=Sing|POS=AUX", "Number=Sing|POS=AUX|Polarity=Neg", "Number=Sing|POS=PRON|Person=2", "Number=Plur,Sing|POS=AUX|Person=2,3|PronType=Prs", "Number=Sing|POS=VERB|Person=3|PronType=Prs|Voice=Act", "Number=Plur,Sing|POS=VERB|Person=3|PronType=Prs|Voice=Act", "Number=Plur|POS=ADJ|Person=2", "Number=Sing|POS=NOUN|Person=1", "POS=VERB|Tense=Past", "Number=Plur|POS=PUNCT|Person=1|PronType=Prs", "Mood=Imp|Number=Plur|POS=VERB|Person=3|Polarity=Neg|Tense=Pres|VerbForm=Fin|Voice=Act", "Number=Plur,Sing|POS=PUNCT|Person=2|PronType=Prs", "Number=Sing|POS=VERB|Person=2|Tense=Pres", "Number=Plur|POS=AUX|Person=3|Tense=Pres", "Mood=Ind|Number=Sing|POS=AUX|Person=2|Polarity=Neg|Tense=Fut|VerbForm=Fin", "Number=Plur|POS=VERB|Person=1|Polarity=Neg", "Number=Sing|POS=AUX|Person=2|Tense=Pres", "POS=VERB|Voice=Pass", "Mood=Imp|Number=Sing|POS=VERB|Person=3|Polarity=Neg|Tense=Past|VerbForm=Fin|Voice=Act", "Mood=Sub|Number=Sing|POS=VERB|Person=3|Tense=Pres|VerbForm=Fin|Voice=Act", "POS=VERB|Polarity=Neg|Tense=Pres", "Number=Sing|POS=SCONJ", "Number=Sing|POS=AUX|Person=3|Polarity=Neg|Tense=Past", "Number=Sing|POS=VERB|Person=1|VerbForm=Part|Voice=Pass", "Number=Plur|POS=VERB|Person=2,3|PronType=Prs", "Number=Sing|POS=ADJ|Person=1", "Number=Plur|POS=PRON|Person=2,3|PronType=Prs", "Number=Sing|POS=VERB|Tense=Past|Voice=Act", "Number=Plur|POS=PROPN|Person=1|PronType=Prs", "Mood=Sub|Number=Plur|POS=VERB|Person=1|Tense=Pres|VerbForm=Fin", "Number=Plur|POS=VERB|Person=1,2|PronType=Prs", "Number=Plur|POS=VERB|Person=2,3|PronType=Prs|Voice=Act", "Mood=Sub|Number=Sing|POS=VERB|Person=3|Polarity=Neg|Tense=Pres|VerbForm=Fin", "Number=Plur,Sing|POS=VERB|Person=1,2|PronType=Prs", "Number=Plur,Sing|POS=PRON|Person=3", "Number=Plur|POS=VERB|Person=3|Polarity=Neg|Tense=Pres", "Number=Sing|POS=PRON|Person=1,2|PronType=Prs", "Number=Sing|POS=VERB|Person=3|Polarity=Neg|Tense=Past|VerbForm=Part|Voice=Pass", "Number=Plur|POS=PROPN|Person=2|PronType=Prs", "Number=Sing|POS=VERB|Person=1,2|PronType=Prs", "Number=Plur,Sing|POS=VERB|Person=3|PronType=Prs|Tense=Pres|Voice=Act", "Number=Plur|POS=VERB|Person=1|Voice=Pass", "Number=Plur|POS=VERB|Person=2|Voice=Pass", "Mood=Sub|Number=Plur|POS=VERB|Person=2|Tense=Pres|VerbForm=Fin", "Number=Plur|POS=VERB|Person=1|Tense=Past" ], "parser":[ "ROOT", "acl", "advcl", "advmod", "amod", "appos", "aux", "case", "cc", "ccomp", "compound", "compound:lvc", "conj", "cop", "csubj", "dep", "det", "fixed", "flat:name", "flat:num", "mark", "nmod", "nsubj", "nsubj:pass", "nummod", "obj", "obl", "obl:arg", "parataxis", "punct", "vocative", "xcomp" ], "ner":[ "DAT", "LOC", "MON", "ORG", "PCT", "PER", "TIM" ] }, "pipeline":[ "tok2vec", "tagger", "morphologizer", "trainable_lemmatizer", "parser", "ner" ], "components":[ "tok2vec", "tagger", "morphologizer", "trainable_lemmatizer", "parser", "ner" ], "disabled":[ ], "performance":{ "tag_acc":0.965475266, "pos_acc":0.9667534212, "morph_acc":0.966964698, "lemma_acc":0.9807994305, "dep_uas":0.9095516749, "dep_las":0.8659527922, "sents_p":0.9910775566, "sents_r":0.9924398625, "sents_f":0.9917582418, "dep_las_per_type":{ "det":{ "p":0.926, "r":0.9686192469, "f":0.9468302658 }, "obj":{ "p":0.8348813209, "r":0.8569915254, "f":0.8457919498 }, "case":{ "p":0.9531889994, "r":0.959646539, "f":0.9564068692 }, "compound:lvc":{ "p":0.9421136484, "r":0.9636067355, "f":0.9527389903 }, "aux":{ "p":0.9806835067, "r":0.9850746269, "f":0.9828741623 }, "root":{ "p":0.9402882636, "r":0.941580756, "f":0.9409340659 }, "cc":{ "p":0.9325396825, "r":0.94, "f":0.9362549801 }, "obl":{ "p":0.764084507, "r":0.7722419929, "f":0.7681415929 }, "mark":{ "p":0.8982758621, "r":0.9156414763, "f":0.906875544 }, "acl":{ "p":0.723628692, "r":0.6751968504, "f":0.6985743381 }, "obl:arg":{ "p":0.7061032864, "r":0.7401574803, "f":0.722729457 }, "nmod":{ "p":0.8383921247, "r":0.7849462366, "f":0.8107893693 }, "conj":{ "p":0.8201304753, "r":0.8043875686, "f":0.8121827411 }, "nsubj":{ "p":0.8779783394, "r":0.8773448773, "f":0.877661494 }, "amod":{ "p":0.8615682478, "r":0.8476190476, "f":0.8545367259 }, "xcomp":{ "p":0.7714285714, "r":0.759375, "f":0.7653543307 }, "nsubj:pass":{ "p":0.875, "r":0.7, "f":0.7777777778 }, "flat:name":{ "p":0.7306733167, "r":0.8253521127, "f":0.7751322751 }, "ccomp":{ "p":0.6617647059, "r":0.7401315789, "f":0.698757764 }, "advmod":{ "p":0.8325242718, "r":0.8032786885, "f":0.8176400477 }, "dep":{ "p":0.738317757, "r":0.8229166667, "f":0.7783251232 }, "nummod":{ "p":0.9190140845, "r":0.9666666667, "f":0.9422382671 }, "cop":{ "p":0.815920398, "r":0.824120603, "f":0.82 }, "csubj":{ "p":0.68, "r":0.5666666667, "f":0.6181818182 }, "advcl":{ "p":0.6529411765, "r":0.6235955056, "f":0.6379310345 }, "appos":{ "p":0.5714285714, "r":0.3404255319, "f":0.4266666667 }, "goeswith":{ "p":0.0, "r":0.0, "f":0.0 }, "fixed":{ "p":0.75, "r":1.0, "f":0.8571428571 }, "flat:num":{ "p":0.9, "r":1.0, "f":0.9473684211 }, "vocative":{ "p":0.8333333333, "r":1.0, "f":0.9090909091 }, "parataxis":{ "p":0.2857142857, "r":0.6666666667, "f":0.4 }, "compound":{ "p":0.0, "r":0.0, "f":0.0 } }, "token_acc":0.9995823588, "token_p":0.9886401604, "token_r":0.9935781742, "token_f":0.9911030166, "speed":6654.6335750233, "ents_p":0.8150782361, "ents_r":0.7109181141, "ents_f":0.75944334, "ents_per_type":{ "PER":{ "p":0.8125, "r":0.6565656566, "f":0.7262569832 }, "MON":{ "p":1.0, "r":0.8, "f":0.8888888889 }, "LOC":{ "p":0.8921161826, "r":0.7875457875, "f":0.8365758755 }, "ORG":{ "p":0.7424242424, "r":0.6805555556, "f":0.7101449275 }, "DAT":{ "p":0.68, "r":0.7391304348, "f":0.7083333333 }, "TIM":{ "p":1.0, "r":0.4444444444, "f":0.6153846154 }, "PCT":{ "p":0.6666666667, "r":0.5, "f":0.5714285714 } } }, "sources":[ { "name":"UD_Persian-PerDT (PerUDT v1.0)", "url":"https://github.com/UniversalDependencies/UD_Persian-PerDT", "author":"Mohammad Sadegh Rasooli, Pegah Safari, Amirsaeid Moloodi, Alireza Nourian", "license":"CC BY-SA 4.0" }, { "name":"UD_Persian-PerDT NER layer (not-to-release/Dadegan with NER tag/)", "url":"https://github.com/UniversalDependencies/UD_Persian-PerDT", "author":"PerDT authors, tagged with Beheshti-NER (Taher, Hoseini, Shamsfard 2020)", "license":"CC BY-SA 4.0" }, { "name":"spaCy lang/fa language data (stop words originally from HAZM)", "url":"https://github.com/explosion/spaCy/tree/master/spacy/lang/fa", "author":"Explosion and spaCy contributors", "license":"MIT" }, { "name":"fa_floret static vectors (lg tier: 200k rows x 300d floret table trained on the full Persian Wikipedia dump, 5 epochs, via spacy-vectors-builder)", "url":"https://huggingface.co/Phazel/fa-floret-wiki-vectors", "author":"Kiyarash Fazeli", "license":"CC BY-SA 4.0" } ], "notes":"Trained on UD_Persian-PerDT, licensed CC BY-SA 4.0; this pipeline is therefore distributed under CC BY-SA 4.0 with attribution to the treebank authors. The ner component is trained on the NER layer shipped in UD_Persian-PerDT's not-to-release/ directory, so it shares the treebank's genre, tokenization and licence. Those labels are SILVER: the treebank README states they were produced by the BERT-based Beheshti-NER tagger (Taher et al., 2020) with manual corrections to extend recall. They were transferred onto this pipeline's tokenization by difflib alignment at a 99.86% transfer rate (scripts/transfer_perdt_ner.py); spans that could not be aligned exactly were dropped rather than guessed. Labels PER, LOC, ORG and DAT have 1,300 or more training examples each; MON (205), TIM (135) and PCT (121) are thin and their scores in `performance.ents_per_type` should be read before relying on them. Multiword tokens (pronominal clitics, enclitic copulas) were merged with `spacy convert --merge-subtokens`, so a small number of XPOS tags are composite (e.g. N_IANM_PR_JOPER) and ~1.5% of lemmas contain a space. doc.noun_chunks under-fires on this pipeline: spacy/lang/fa/syntax_iterators.py matches ClearNLP labels that do not exist in Universal Dependencies, see docs/upstream/fa-noun-chunks.md. This is the `lg` tier: identical architecture to `sm`/`md` but a larger static floret vector table (200,000 rows x 300 dimensions, minn=maxn=5, hash_count=2) trained on the full Persian Wikipedia dump for 5 epochs via spacy-vectors-builder. Same zero-OOV rationale as `md` (see docs/MODELS.md): floret hashes subwords into a fixed table, so `token.has_vector` is always True despite Persian's ZWNJ (U+200C) inconsistency.", "requirements":[ "spacy>=3.8.14,<3.9.0" ] }