zh_core_web_md / meta.json
Adriane Boyd
Update spaCy pipeline
caef619
raw history blame
No virus
10.1 kB
{
"lang":"zh",
"name":"core_web_md",
"version":"3.4.0",
"description":"Chinese pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter, ner, attribute_ruler.",
"author":"Explosion",
"email":"contact@explosion.ai",
"url":"https://explosion.ai",
"license":"MIT",
"spacy_version":">=3.4.0,<3.5.0",
"spacy_git_version":"dd038b536",
"vectors":{
"width":300,
"vectors":20000,
"keys":500000,
"name":"zh_vectors"
},
"labels":{
"tok2vec":[
],
"tagger":[
"AD",
"AS",
"BA",
"CC",
"CD",
"CS",
"DEC",
"DEG",
"DER",
"DEV",
"DT",
"ETC",
"FW",
"IJ",
"INF",
"JJ",
"LB",
"LC",
"M",
"MSP",
"NN",
"NR",
"NT",
"OD",
"ON",
"P",
"PN",
"PU",
"SB",
"SP",
"URL",
"VA",
"VC",
"VE",
"VV",
"X",
"_SP"
],
"parser":[
"ROOT",
"acl",
"advcl:loc",
"advmod",
"advmod:dvp",
"advmod:loc",
"advmod:rcomp",
"amod",
"amod:ordmod",
"appos",
"aux:asp",
"aux:ba",
"aux:modal",
"aux:prtmod",
"auxpass",
"case",
"cc",
"ccomp",
"compound:nn",
"compound:vc",
"conj",
"cop",
"dep",
"det",
"discourse",
"dobj",
"etc",
"mark",
"mark:clf",
"name",
"neg",
"nmod",
"nmod:assmod",
"nmod:poss",
"nmod:prep",
"nmod:range",
"nmod:tmod",
"nmod:topic",
"nsubj",
"nsubj:xsubj",
"nsubjpass",
"nummod",
"parataxis:prnmod",
"punct",
"xcomp"
],
"attribute_ruler":[
],
"ner":[
"CARDINAL",
"DATE",
"EVENT",
"FAC",
"GPE",
"LANGUAGE",
"LAW",
"LOC",
"MONEY",
"NORP",
"ORDINAL",
"ORG",
"PERCENT",
"PERSON",
"PRODUCT",
"QUANTITY",
"TIME",
"WORK_OF_ART"
]
},
"pipeline":[
"tok2vec",
"tagger",
"parser",
"attribute_ruler",
"ner"
],
"components":[
"tok2vec",
"tagger",
"parser",
"senter",
"attribute_ruler",
"ner"
],
"disabled":[
"senter"
],
"performance":{
"token_acc":0.9788303388,
"token_p":0.9458325855,
"token_r":0.9136060443,
"token_f":0.9294400505,
"tag_acc":0.9008590446,
"sents_p":0.7826398852,
"sents_r":0.7264857666,
"sents_f":0.7535180869,
"dep_uas":0.7039779048,
"dep_las":0.6517336371,
"dep_las_per_type":{
"dep":{
"p":0.4830434783,
"r":0.3367687178,
"f":0.3968565815
},
"case":{
"p":0.8127335997,
"r":0.7645489816,
"f":0.7879052914
},
"nmod:tmod":{
"p":0.7217847769,
"r":0.7482993197,
"f":0.7348029392
},
"nummod":{
"p":0.8354037267,
"r":0.5376415723,
"f":0.6542359141
},
"mark:clf":{
"p":0.9290479078,
"r":0.5714285714,
"f":0.7076212471
},
"auxpass":{
"p":0.8756756757,
"r":0.8756756757,
"f":0.8756756757
},
"nsubj":{
"p":0.7779833488,
"r":0.7231298366,
"f":0.7495543672
},
"acl":{
"p":0.6736703874,
"r":0.5690515807,
"f":0.6169573061
},
"advmod":{
"p":0.8179051484,
"r":0.7311267286,
"f":0.7720852286
},
"mark":{
"p":0.7384830154,
"r":0.6954425942,
"f":0.7163168585
},
"xcomp":{
"p":0.7678244973,
"r":0.6840390879,
"f":0.7235142119
},
"nmod:assmod":{
"p":0.7572123177,
"r":0.7270463741,
"f":0.7418228009
},
"det":{
"p":0.8389694042,
"r":0.6104276508,
"f":0.7066802306
},
"amod":{
"p":0.7720183486,
"r":0.6610369207,
"f":0.7122302158
},
"nmod:prep":{
"p":0.6889194769,
"r":0.6055656382,
"f":0.6445589182
},
"root":{
"p":0.74074777,
"r":0.6497419677,
"f":0.6922667613
},
"aux:prtmod":{
"p":0.9392712551,
"r":0.8285714286,
"f":0.880455408
},
"compound:nn":{
"p":0.7327857393,
"r":0.7094754653,
"f":0.7209422283
},
"dobj":{
"p":0.8002915452,
"r":0.7318915716,
"f":0.7645647969
},
"ccomp":{
"p":0.6348892405,
"r":0.6240279938,
"f":0.6294117647
},
"advmod:rcomp":{
"p":0.8301282051,
"r":0.7174515235,
"f":0.7696879643
},
"nmod:topic":{
"p":0.3196347032,
"r":0.2272727273,
"f":0.265654649
},
"cop":{
"p":0.7382113821,
"r":0.5842985843,
"f":0.6522988506
},
"discourse":{
"p":0.5618604651,
"r":0.498349835,
"f":0.5282028859
},
"neg":{
"p":0.8276374443,
"r":0.6623067776,
"f":0.7357992074
},
"aux:modal":{
"p":0.8614072495,
"r":0.83557394,
"f":0.8482939633
},
"nmod":{
"p":0.6971608833,
"r":0.5997286296,
"f":0.6447848286
},
"aux:ba":{
"p":0.8021978022,
"r":0.7765957447,
"f":0.7891891892
},
"advmod:loc":{
"p":0.618852459,
"r":0.4480712166,
"f":0.5197934596
},
"aux:asp":{
"p":0.9115702479,
"r":0.879585327,
"f":0.8952922078
},
"conj":{
"p":0.4956505295,
"r":0.495463138,
"f":0.495556816
},
"nsubjpass":{
"p":0.7674418605,
"r":0.66,
"f":0.7096774194
},
"compound:vc":{
"p":0.4491017964,
"r":0.3886010363,
"f":0.4166666667
},
"advcl:loc":{
"p":0.4959349593,
"r":0.4357142857,
"f":0.463878327
},
"cc":{
"p":0.7056603774,
"r":0.6637089618,
"f":0.6840420668
},
"advmod:dvp":{
"p":0.8217054264,
"r":0.6583850932,
"f":0.7310344828
},
"nmod:range":{
"p":0.7442748092,
"r":0.6543624161,
"f":0.6964285714
},
"appos":{
"p":0.8775,
"r":0.8068965517,
"f":0.8407185629
},
"nmod:poss":{
"p":0.6804123711,
"r":0.4888888889,
"f":0.5689655172
},
"name":{
"p":0.6454545455,
"r":0.5259259259,
"f":0.5795918367
},
"nsubj:xsubj":{
"p":0.0,
"r":0.0,
"f":0.0
},
"parataxis:prnmod":{
"p":0.4444444444,
"r":0.1203007519,
"f":0.1893491124
},
"amod:ordmod":{
"p":0.5967741935,
"r":0.578125,
"f":0.5873015873
},
"erased":{
"p":0.0,
"r":0.0,
"f":0.0
},
"etc":{
"p":0.8735632184,
"r":0.9047619048,
"f":0.8888888889
}
},
"ents_p":0.7221830158,
"ents_r":0.6747252747,
"ents_f":0.6976479945,
"ents_per_type":{
"DATE":{
"p":0.7737983035,
"r":0.8136769078,
"f":0.793236715
},
"GPE":{
"p":0.7543546226,
"r":0.8255131965,
"f":0.7883313886
},
"ORDINAL":{
"p":0.8531073446,
"r":0.7947368421,
"f":0.8228882834
},
"FAC":{
"p":0.5428571429,
"r":0.3064516129,
"f":0.3917525773
},
"ORG":{
"p":0.6842961758,
"r":0.6400304414,
"f":0.6614235155
},
"LOC":{
"p":0.5247148289,
"r":0.3709677419,
"f":0.4346456693
},
"QUANTITY":{
"p":0.7477477477,
"r":0.6148148148,
"f":0.674796748
},
"CARDINAL":{
"p":0.6025345622,
"r":0.5272177419,
"f":0.5623655914
},
"PERSON":{
"p":0.7744708995,
"r":0.7545103093,
"f":0.7643603133
},
"NORP":{
"p":0.6803797468,
"r":0.4516806723,
"f":0.5429292929
},
"WORK_OF_ART":{
"p":0.6075949367,
"r":0.32,
"f":0.4192139738
},
"TIME":{
"p":0.7487922705,
"r":0.7524271845,
"f":0.7506053269
},
"MONEY":{
"p":0.9396551724,
"r":0.8074074074,
"f":0.8685258964
},
"PERCENT":{
"p":0.8192771084,
"r":0.8192771084,
"f":0.8192771084
},
"EVENT":{
"p":0.5204081633,
"r":0.375,
"f":0.4358974359
},
"PRODUCT":{
"p":0.0,
"r":0.0,
"f":0.0
},
"LAW":{
"p":0.5909090909,
"r":0.2166666667,
"f":0.3170731707
},
"LANGUAGE":{
"p":0.5384615385,
"r":0.7777777778,
"f":0.6363636364
}
},
"speed":8210.2192509121
},
"sources":[
{
"name":"OntoNotes 5",
"url":"https://catalog.ldc.upenn.edu/LDC2013T19",
"license":"commercial (licensed by Explosion)",
"author":"Ralph Weischedel, Martha Palmer, Mitchell Marcus, Eduard Hovy, Sameer Pradhan, Lance Ramshaw, Nianwen Xue, Ann Taylor, Jeff Kaufman, Michelle Franchini, Mohammed El-Bachouti, Robert Belvin, Ann Houston"
},
{
"name":"CoreNLP Universal Dependencies Converter",
"url":"https://nlp.stanford.edu/software/stanford-dependencies.html",
"author":"Stanford NLP Group",
"license":"Citation provided for reference, no code packaged with model"
},
{
"name":"Explosion fastText Vectors (cbow, OSCAR Common Crawl + Wikipedia)",
"url":"https://spacy.io",
"license":"CC0",
"author":"Explosion"
}
],
"requirements":[
"spacy-pkuseg>=0.0.27,<0.1.0"
]
}