fa_core_news_sm / meta.json
Phazel's picture
Update spaCy pipeline
5ab8fef verified
Raw
History Blame Contribute Delete
26.4 kB
{
"lang":"fa",
"name":"core_news_sm",
"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":0,
"vectors":0,
"keys":0,
"name":null
},
"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":0.9595584377,
"pos_acc":0.9623659299,
"morph_acc":0.9629100984,
"lemma_acc":0.9790824766,
"dep_uas":0.8969107789,
"dep_las":0.8515184307,
"sents_p":0.9904175222,
"sents_r":0.9945017182,
"sents_f":0.9924554184,
"dep_las_per_type":{
"det":{
"p":0.9291497976,
"r":0.960251046,
"f":0.9444444444
},
"obj":{
"p":0.8541202673,
"r":0.8125,
"f":0.8327904452
},
"case":{
"p":0.9477546228,
"r":0.9511045655,
"f":0.9494266392
},
"compound:lvc":{
"p":0.9391395593,
"r":0.9722976643,
"f":0.9554310115
},
"aux":{
"p":0.9850968703,
"r":0.9865671642,
"f":0.9858314691
},
"root":{
"p":0.9288158795,
"r":0.9326460481,
"f":0.9307270233
},
"cc":{
"p":0.9371884347,
"r":0.94,
"f":0.9385921118
},
"obl":{
"p":0.7494553377,
"r":0.734519573,
"f":0.7419122933
},
"mark":{
"p":0.8871527778,
"r":0.8980667838,
"f":0.8925764192
},
"acl":{
"p":0.6396917148,
"r":0.6535433071,
"f":0.6465433301
},
"obl:arg":{
"p":0.7053824363,
"r":0.7352362205,
"f":0.72
},
"nmod":{
"p":0.8027504912,
"r":0.784562212,
"f":0.793552146
},
"conj":{
"p":0.7835144928,
"r":0.7906764168,
"f":0.7870791629
},
"nsubj":{
"p":0.8258706468,
"r":0.8383838384,
"f":0.8320802005
},
"amod":{
"p":0.821866164,
"r":0.8304761905,
"f":0.8261487447
},
"xcomp":{
"p":0.8487084871,
"r":0.71875,
"f":0.7783417936
},
"nsubj:pass":{
"p":0.8823529412,
"r":0.75,
"f":0.8108108108
},
"flat:name":{
"p":0.6888297872,
"r":0.7295774648,
"f":0.7086183311
},
"ccomp":{
"p":0.6949685535,
"r":0.7269736842,
"f":0.7106109325
},
"advmod":{
"p":0.8146453089,
"r":0.8337236534,
"f":0.8240740741
},
"dep":{
"p":0.780952381,
"r":0.8541666667,
"f":0.815920398
},
"nummod":{
"p":0.9326241135,
"r":0.9740740741,
"f":0.9528985507
},
"cop":{
"p":0.7578947368,
"r":0.7236180905,
"f":0.7403598972
},
"csubj":{
"p":0.6,
"r":0.5,
"f":0.5454545455
},
"advcl":{
"p":0.6621621622,
"r":0.5505617978,
"f":0.6012269939
},
"appos":{
"p":0.34375,
"r":0.2340425532,
"f":0.2784810127
},
"goeswith":{
"p":0.0,
"r":0.0,
"f":0.0
},
"fixed":{
"p":0.75,
"r":1.0,
"f":0.8571428571
},
"flat:num":{
"p":0.9473684211,
"r":1.0,
"f":0.972972973
},
"vocative":{
"p":0.75,
"r":0.6,
"f":0.6666666667
},
"parataxis":{
"p":0.5,
"r":0.6666666667,
"f":0.5714285714
},
"compound":{
"p":1.0,
"r":1.0,
"f":1.0
}
},
"token_acc":0.9995823588,
"token_p":0.9886401604,
"token_r":0.9935781742,
"token_f":0.9911030166,
"speed":8834.2446500744,
"ents_p":0.7766570605,
"ents_r":0.6687344913,
"ents_f":0.7186666667,
"ents_per_type":{
"PER":{
"p":0.7372881356,
"r":0.5858585859,
"f":0.6529080675
},
"LOC":{
"p":0.8815789474,
"r":0.7362637363,
"f":0.8023952096
},
"MON":{
"p":0.7777777778,
"r":0.7,
"f":0.7368421053
},
"ORG":{
"p":0.695035461,
"r":0.6805555556,
"f":0.6877192982
},
"DAT":{
"p":0.75,
"r":0.7391304348,
"f":0.7445255474
},
"TIM":{
"p":0.6666666667,
"r":0.6666666667,
"f":0.6666666667
},
"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"
}
],
"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.",
"requirements":[
"spacy>=3.8.14,<3.9.0"
]
}