added new invoice ml model v 0.2.0
This commit is contained in:
parent
c4f0e9c5d6
commit
2ebd24fe54
20 changed files with 60290 additions and 81873 deletions
Binary file not shown.
|
|
@ -5,33 +5,21 @@ vectors = null
|
||||||
init_tok2vec = null
|
init_tok2vec = null
|
||||||
|
|
||||||
[system]
|
[system]
|
||||||
gpu_allocator = null
|
|
||||||
seed = 0
|
seed = 0
|
||||||
|
gpu_allocator = null
|
||||||
|
|
||||||
[nlp]
|
[nlp]
|
||||||
lang = "en"
|
lang = "de"
|
||||||
pipeline = ["tok2vec","tagger","parser","senter","attribute_ruler","lemmatizer","ner"]
|
pipeline = ["ner"]
|
||||||
disabled = ["tagger","parser","senter"]
|
disabled = []
|
||||||
before_creation = null
|
before_creation = null
|
||||||
after_creation = null
|
after_creation = null
|
||||||
after_pipeline_creation = null
|
after_pipeline_creation = null
|
||||||
batch_size = 256
|
batch_size = 1000
|
||||||
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
|
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
|
||||||
|
|
||||||
[components]
|
[components]
|
||||||
|
|
||||||
[components.attribute_ruler]
|
|
||||||
factory = "attribute_ruler"
|
|
||||||
scorer = {"@scorers":"spacy.attribute_ruler_scorer.v1"}
|
|
||||||
validate = false
|
|
||||||
|
|
||||||
[components.lemmatizer]
|
|
||||||
factory = "lemmatizer"
|
|
||||||
mode = "rule"
|
|
||||||
model = null
|
|
||||||
overwrite = false
|
|
||||||
scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
|
|
||||||
|
|
||||||
[components.ner]
|
[components.ner]
|
||||||
factory = "ner"
|
factory = "ner"
|
||||||
incorrect_spans_key = null
|
incorrect_spans_key = null
|
||||||
|
|
@ -49,106 +37,14 @@ use_upper = true
|
||||||
nO = null
|
nO = null
|
||||||
|
|
||||||
[components.ner.model.tok2vec]
|
[components.ner.model.tok2vec]
|
||||||
@architectures = "spacy.Tok2Vec.v2"
|
@architectures = "spacy.HashEmbedCNN.v2"
|
||||||
|
pretrained_vectors = null
|
||||||
[components.ner.model.tok2vec.embed]
|
|
||||||
@architectures = "spacy.MultiHashEmbed.v2"
|
|
||||||
width = 96
|
|
||||||
attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
|
|
||||||
rows = [5000,1000,2500,2500,50]
|
|
||||||
include_static_vectors = false
|
|
||||||
|
|
||||||
[components.ner.model.tok2vec.encode]
|
|
||||||
@architectures = "spacy.MaxoutWindowEncoder.v2"
|
|
||||||
width = 96
|
|
||||||
depth = 4
|
|
||||||
window_size = 1
|
|
||||||
maxout_pieces = 3
|
|
||||||
|
|
||||||
[components.parser]
|
|
||||||
factory = "parser"
|
|
||||||
learn_tokens = false
|
|
||||||
min_action_freq = 30
|
|
||||||
moves = null
|
|
||||||
scorer = {"@scorers":"spacy.parser_scorer.v1"}
|
|
||||||
update_with_oracle_cut_size = 100
|
|
||||||
|
|
||||||
[components.parser.model]
|
|
||||||
@architectures = "spacy.TransitionBasedParser.v2"
|
|
||||||
state_type = "parser"
|
|
||||||
extra_state_tokens = false
|
|
||||||
hidden_width = 64
|
|
||||||
maxout_pieces = 2
|
|
||||||
use_upper = true
|
|
||||||
nO = null
|
|
||||||
|
|
||||||
[components.parser.model.tok2vec]
|
|
||||||
@architectures = "spacy.Tok2VecListener.v1"
|
|
||||||
width = ${components.tok2vec.model.encode:width}
|
|
||||||
upstream = "tok2vec"
|
|
||||||
|
|
||||||
[components.senter]
|
|
||||||
factory = "senter"
|
|
||||||
overwrite = false
|
|
||||||
scorer = {"@scorers":"spacy.senter_scorer.v1"}
|
|
||||||
|
|
||||||
[components.senter.model]
|
|
||||||
@architectures = "spacy.Tagger.v2"
|
|
||||||
nO = null
|
|
||||||
normalize = false
|
|
||||||
|
|
||||||
[components.senter.model.tok2vec]
|
|
||||||
@architectures = "spacy.Tok2Vec.v2"
|
|
||||||
|
|
||||||
[components.senter.model.tok2vec.embed]
|
|
||||||
@architectures = "spacy.MultiHashEmbed.v2"
|
|
||||||
width = 16
|
|
||||||
attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
|
|
||||||
rows = [1000,500,500,500,50]
|
|
||||||
include_static_vectors = false
|
|
||||||
|
|
||||||
[components.senter.model.tok2vec.encode]
|
|
||||||
@architectures = "spacy.MaxoutWindowEncoder.v2"
|
|
||||||
width = 16
|
|
||||||
depth = 2
|
|
||||||
window_size = 1
|
|
||||||
maxout_pieces = 2
|
|
||||||
|
|
||||||
[components.tagger]
|
|
||||||
factory = "tagger"
|
|
||||||
neg_prefix = "!"
|
|
||||||
overwrite = false
|
|
||||||
scorer = {"@scorers":"spacy.tagger_scorer.v1"}
|
|
||||||
|
|
||||||
[components.tagger.model]
|
|
||||||
@architectures = "spacy.Tagger.v2"
|
|
||||||
nO = null
|
|
||||||
normalize = false
|
|
||||||
|
|
||||||
[components.tagger.model.tok2vec]
|
|
||||||
@architectures = "spacy.Tok2VecListener.v1"
|
|
||||||
width = ${components.tok2vec.model.encode:width}
|
|
||||||
upstream = "tok2vec"
|
|
||||||
|
|
||||||
[components.tok2vec]
|
|
||||||
factory = "tok2vec"
|
|
||||||
|
|
||||||
[components.tok2vec.model]
|
|
||||||
@architectures = "spacy.Tok2Vec.v2"
|
|
||||||
|
|
||||||
[components.tok2vec.model.embed]
|
|
||||||
@architectures = "spacy.MultiHashEmbed.v2"
|
|
||||||
width = ${components.tok2vec.model.encode:width}
|
|
||||||
attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
|
|
||||||
rows = [5000,1000,2500,2500,50]
|
|
||||||
include_static_vectors = false
|
|
||||||
|
|
||||||
[components.tok2vec.model.encode]
|
|
||||||
@architectures = "spacy.MaxoutWindowEncoder.v2"
|
|
||||||
width = 96
|
width = 96
|
||||||
depth = 4
|
depth = 4
|
||||||
|
embed_size = 2000
|
||||||
window_size = 1
|
window_size = 1
|
||||||
maxout_pieces = 3
|
maxout_pieces = 3
|
||||||
|
subword_features = true
|
||||||
|
|
||||||
[corpora]
|
[corpora]
|
||||||
|
|
||||||
|
|
@ -169,19 +65,19 @@ limit = 0
|
||||||
augmenter = null
|
augmenter = null
|
||||||
|
|
||||||
[training]
|
[training]
|
||||||
train_corpus = "corpora.train"
|
seed = ${system.seed}
|
||||||
dev_corpus = "corpora.dev"
|
gpu_allocator = ${system.gpu_allocator}
|
||||||
seed = ${system:seed}
|
|
||||||
gpu_allocator = ${system:gpu_allocator}
|
|
||||||
dropout = 0.1
|
dropout = 0.1
|
||||||
accumulate_gradient = 1
|
accumulate_gradient = 1
|
||||||
patience = 5000
|
patience = 1600
|
||||||
max_epochs = 0
|
max_epochs = 0
|
||||||
max_steps = 100000
|
max_steps = 20000
|
||||||
eval_frequency = 1000
|
eval_frequency = 200
|
||||||
frozen_components = []
|
frozen_components = []
|
||||||
before_to_disk = null
|
|
||||||
annotating_components = []
|
annotating_components = []
|
||||||
|
dev_corpus = "corpora.dev"
|
||||||
|
train_corpus = "corpora.train"
|
||||||
|
before_to_disk = null
|
||||||
|
|
||||||
[training.batcher]
|
[training.batcher]
|
||||||
@batchers = "spacy.batch_by_words.v1"
|
@batchers = "spacy.batch_by_words.v1"
|
||||||
|
|
@ -207,60 +103,26 @@ beta2 = 0.999
|
||||||
L2_is_weight_decay = true
|
L2_is_weight_decay = true
|
||||||
L2 = 0.01
|
L2 = 0.01
|
||||||
grad_clip = 1.0
|
grad_clip = 1.0
|
||||||
use_averages = true
|
use_averages = false
|
||||||
eps = 0.00000001
|
eps = 0.00000001
|
||||||
learn_rate = 0.001
|
learn_rate = 0.001
|
||||||
|
|
||||||
[training.score_weights]
|
[training.score_weights]
|
||||||
tag_acc = 0.16
|
ents_f = 1.0
|
||||||
dep_uas = 0.0
|
|
||||||
dep_las = 0.16
|
|
||||||
dep_las_per_type = null
|
|
||||||
sents_p = null
|
|
||||||
sents_r = null
|
|
||||||
sents_f = 0.02
|
|
||||||
lemma_acc = 0.5
|
|
||||||
ents_f = 0.16
|
|
||||||
ents_p = 0.0
|
ents_p = 0.0
|
||||||
ents_r = 0.0
|
ents_r = 0.0
|
||||||
ents_per_type = null
|
ents_per_type = null
|
||||||
speed = 0.0
|
|
||||||
|
|
||||||
[pretraining]
|
[pretraining]
|
||||||
|
|
||||||
[initialize]
|
[initialize]
|
||||||
vocab_data = null
|
|
||||||
vectors = ${paths.vectors}
|
vectors = ${paths.vectors}
|
||||||
init_tok2vec = ${paths.init_tok2vec}
|
init_tok2vec = ${paths.init_tok2vec}
|
||||||
|
vocab_data = null
|
||||||
|
lookups = null
|
||||||
before_init = null
|
before_init = null
|
||||||
after_init = null
|
after_init = null
|
||||||
|
|
||||||
[initialize.components]
|
[initialize.components]
|
||||||
|
|
||||||
[initialize.components.ner]
|
|
||||||
|
|
||||||
[initialize.components.ner.labels]
|
|
||||||
@readers = "spacy.read_labels.v1"
|
|
||||||
path = "corpus/labels/ner.json"
|
|
||||||
require = false
|
|
||||||
|
|
||||||
[initialize.components.parser]
|
|
||||||
|
|
||||||
[initialize.components.parser.labels]
|
|
||||||
@readers = "spacy.read_labels.v1"
|
|
||||||
path = "corpus/labels/parser.json"
|
|
||||||
require = false
|
|
||||||
|
|
||||||
[initialize.components.tagger]
|
|
||||||
|
|
||||||
[initialize.components.tagger.labels]
|
|
||||||
@readers = "spacy.read_labels.v1"
|
|
||||||
path = "corpus/labels/tagger.json"
|
|
||||||
require = false
|
|
||||||
|
|
||||||
[initialize.lookups]
|
|
||||||
@misc = "spacy.LookupsDataLoader.v1"
|
|
||||||
lang = ${nlp.lang}
|
|
||||||
tables = ["lexeme_norm"]
|
|
||||||
|
|
||||||
[initialize.tokenizer]
|
[initialize.tokenizer]
|
||||||
File diff suppressed because one or more lines are too long
|
|
@ -1,14 +1,14 @@
|
||||||
{
|
{
|
||||||
"lang":"en",
|
"lang":"de",
|
||||||
"name":"core_web_sm",
|
"name":"pipeline",
|
||||||
"version":"3.4.0",
|
"version":"0.0.0",
|
||||||
"description":"English pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter, ner, attribute_ruler, lemmatizer.",
|
"spacy_version":">=3.4.1,<3.5.0",
|
||||||
"author":"Explosion",
|
"description":"",
|
||||||
"email":"contact@explosion.ai",
|
"author":"",
|
||||||
"url":"https://explosion.ai",
|
"email":"",
|
||||||
"license":"MIT",
|
"url":"",
|
||||||
"spacy_version":">=3.4.0,<3.5.0",
|
"license":"",
|
||||||
"spacy_git_version":"dd038b536",
|
"spacy_git_version":"Unknown",
|
||||||
"vectors":{
|
"vectors":{
|
||||||
"width":0,
|
"width":0,
|
||||||
"vectors":0,
|
"vectors":0,
|
||||||
|
|
@ -17,133 +17,7 @@
|
||||||
"mode":"default"
|
"mode":"default"
|
||||||
},
|
},
|
||||||
"labels":{
|
"labels":{
|
||||||
"tok2vec":[
|
|
||||||
|
|
||||||
],
|
|
||||||
"tagger":[
|
|
||||||
"$",
|
|
||||||
"''",
|
|
||||||
",",
|
|
||||||
"-LRB-",
|
|
||||||
"-RRB-",
|
|
||||||
".",
|
|
||||||
":",
|
|
||||||
"ADD",
|
|
||||||
"AFX",
|
|
||||||
"CC",
|
|
||||||
"CD",
|
|
||||||
"DT",
|
|
||||||
"EX",
|
|
||||||
"FW",
|
|
||||||
"HYPH",
|
|
||||||
"IN",
|
|
||||||
"JJ",
|
|
||||||
"JJR",
|
|
||||||
"JJS",
|
|
||||||
"LS",
|
|
||||||
"MD",
|
|
||||||
"NFP",
|
|
||||||
"NN",
|
|
||||||
"NNP",
|
|
||||||
"NNPS",
|
|
||||||
"NNS",
|
|
||||||
"PDT",
|
|
||||||
"POS",
|
|
||||||
"PRP",
|
|
||||||
"PRP$",
|
|
||||||
"RB",
|
|
||||||
"RBR",
|
|
||||||
"RBS",
|
|
||||||
"RP",
|
|
||||||
"SYM",
|
|
||||||
"TO",
|
|
||||||
"UH",
|
|
||||||
"VB",
|
|
||||||
"VBD",
|
|
||||||
"VBG",
|
|
||||||
"VBN",
|
|
||||||
"VBP",
|
|
||||||
"VBZ",
|
|
||||||
"WDT",
|
|
||||||
"WP",
|
|
||||||
"WP$",
|
|
||||||
"WRB",
|
|
||||||
"XX",
|
|
||||||
"_SP",
|
|
||||||
"``"
|
|
||||||
],
|
|
||||||
"parser":[
|
|
||||||
"ROOT",
|
|
||||||
"acl",
|
|
||||||
"acomp",
|
|
||||||
"advcl",
|
|
||||||
"advmod",
|
|
||||||
"agent",
|
|
||||||
"amod",
|
|
||||||
"appos",
|
|
||||||
"attr",
|
|
||||||
"aux",
|
|
||||||
"auxpass",
|
|
||||||
"case",
|
|
||||||
"cc",
|
|
||||||
"ccomp",
|
|
||||||
"compound",
|
|
||||||
"conj",
|
|
||||||
"csubj",
|
|
||||||
"csubjpass",
|
|
||||||
"dative",
|
|
||||||
"dep",
|
|
||||||
"det",
|
|
||||||
"dobj",
|
|
||||||
"expl",
|
|
||||||
"intj",
|
|
||||||
"mark",
|
|
||||||
"meta",
|
|
||||||
"neg",
|
|
||||||
"nmod",
|
|
||||||
"npadvmod",
|
|
||||||
"nsubj",
|
|
||||||
"nsubjpass",
|
|
||||||
"nummod",
|
|
||||||
"oprd",
|
|
||||||
"parataxis",
|
|
||||||
"pcomp",
|
|
||||||
"pobj",
|
|
||||||
"poss",
|
|
||||||
"preconj",
|
|
||||||
"predet",
|
|
||||||
"prep",
|
|
||||||
"prt",
|
|
||||||
"punct",
|
|
||||||
"quantmod",
|
|
||||||
"relcl",
|
|
||||||
"xcomp"
|
|
||||||
],
|
|
||||||
"attribute_ruler":[
|
|
||||||
|
|
||||||
],
|
|
||||||
"lemmatizer":[
|
|
||||||
|
|
||||||
],
|
|
||||||
"ner":[
|
"ner":[
|
||||||
"CARDINAL",
|
|
||||||
"DATE",
|
|
||||||
"EVENT",
|
|
||||||
"FAC",
|
|
||||||
"GPE",
|
|
||||||
"LANGUAGE",
|
|
||||||
"LAW",
|
|
||||||
"LOC",
|
|
||||||
"MONEY",
|
|
||||||
"NORP",
|
|
||||||
"ORDINAL",
|
|
||||||
"ORG",
|
|
||||||
"PERCENT",
|
|
||||||
"PERSON",
|
|
||||||
"PRODUCT",
|
|
||||||
"QUANTITY",
|
|
||||||
"TIME",
|
|
||||||
"WORK_OF_ART",
|
|
||||||
"cdtr.bic",
|
"cdtr.bic",
|
||||||
"cdtr.iban",
|
"cdtr.iban",
|
||||||
"cdtr.name",
|
"cdtr.name",
|
||||||
|
|
@ -153,376 +27,12 @@
|
||||||
]
|
]
|
||||||
},
|
},
|
||||||
"pipeline":[
|
"pipeline":[
|
||||||
"tok2vec",
|
|
||||||
"attribute_ruler",
|
|
||||||
"lemmatizer",
|
|
||||||
"ner"
|
"ner"
|
||||||
],
|
],
|
||||||
"components":[
|
"components":[
|
||||||
"tok2vec",
|
|
||||||
"tagger",
|
|
||||||
"parser",
|
|
||||||
"senter",
|
|
||||||
"attribute_ruler",
|
|
||||||
"lemmatizer",
|
|
||||||
"ner"
|
"ner"
|
||||||
],
|
],
|
||||||
"disabled":[
|
"disabled":[
|
||||||
"tagger",
|
|
||||||
"parser",
|
|
||||||
"senter"
|
|
||||||
],
|
|
||||||
"performance":{
|
|
||||||
"token_acc":0.9993092439,
|
|
||||||
"token_p":0.9956819193,
|
|
||||||
"token_r":0.9957659295,
|
|
||||||
"token_f":0.9957239226,
|
|
||||||
"tag_acc":0.9726250474,
|
|
||||||
"sents_p":0.9191788296,
|
|
||||||
"sents_r":0.8890428129,
|
|
||||||
"sents_f":0.9038596962,
|
|
||||||
"dep_uas":0.9165718428,
|
|
||||||
"dep_las":0.8978441095,
|
|
||||||
"dep_las_per_type":{
|
|
||||||
"prep":{
|
|
||||||
"p":0.8546376267,
|
|
||||||
"r":0.8635553026,
|
|
||||||
"f":0.8590733226
|
|
||||||
},
|
|
||||||
"det":{
|
|
||||||
"p":0.9768701389,
|
|
||||||
"r":0.9781048683,
|
|
||||||
"f":0.9774871137
|
|
||||||
},
|
|
||||||
"pobj":{
|
|
||||||
"p":0.9605592002,
|
|
||||||
"r":0.9659532692,
|
|
||||||
"f":0.9632486833
|
|
||||||
},
|
|
||||||
"nsubj":{
|
|
||||||
"p":0.9545715675,
|
|
||||||
"r":0.9463745893,
|
|
||||||
"f":0.9504554055
|
|
||||||
},
|
|
||||||
"aux":{
|
|
||||||
"p":0.9798401421,
|
|
||||||
"r":0.9821953174,
|
|
||||||
"f":0.9810163162
|
|
||||||
},
|
|
||||||
"advmod":{
|
|
||||||
"p":0.8545653823,
|
|
||||||
"r":0.8527679623,
|
|
||||||
"f":0.8536657262
|
|
||||||
},
|
|
||||||
"relcl":{
|
|
||||||
"p":0.7656695157,
|
|
||||||
"r":0.7801161103,
|
|
||||||
"f":0.7728253055
|
|
||||||
},
|
|
||||||
"root":{
|
|
||||||
"p":0.91776518,
|
|
||||||
"r":0.8864041164,
|
|
||||||
"f":0.9018120805
|
|
||||||
},
|
|
||||||
"xcomp":{
|
|
||||||
"p":0.882290562,
|
|
||||||
"r":0.895908112,
|
|
||||||
"f":0.889047195
|
|
||||||
},
|
|
||||||
"amod":{
|
|
||||||
"p":0.9154102213,
|
|
||||||
"r":0.908649174,
|
|
||||||
"f":0.9120171674
|
|
||||||
},
|
|
||||||
"compound":{
|
|
||||||
"p":0.9121588361,
|
|
||||||
"r":0.9287703275,
|
|
||||||
"f":0.9203896355
|
|
||||||
},
|
|
||||||
"poss":{
|
|
||||||
"p":0.9735258724,
|
|
||||||
"r":0.9770531401,
|
|
||||||
"f":0.9752863171
|
|
||||||
},
|
|
||||||
"ccomp":{
|
|
||||||
"p":0.7657557167,
|
|
||||||
"r":0.8389002037,
|
|
||||||
"f":0.8006609
|
|
||||||
},
|
|
||||||
"attr":{
|
|
||||||
"p":0.9032126881,
|
|
||||||
"r":0.9339781329,
|
|
||||||
"f":0.9183378127
|
|
||||||
},
|
|
||||||
"case":{
|
|
||||||
"p":0.9773063641,
|
|
||||||
"r":0.9914914915,
|
|
||||||
"f":0.9843478261
|
|
||||||
},
|
|
||||||
"mark":{
|
|
||||||
"p":0.9002893975,
|
|
||||||
"r":0.9067302597,
|
|
||||||
"f":0.9034983498
|
|
||||||
},
|
|
||||||
"intj":{
|
|
||||||
"p":0.6514555468,
|
|
||||||
"r":0.6065934066,
|
|
||||||
"f":0.6282245827
|
|
||||||
},
|
|
||||||
"advcl":{
|
|
||||||
"p":0.6653050804,
|
|
||||||
"r":0.6562578696,
|
|
||||||
"f":0.6607505071
|
|
||||||
},
|
|
||||||
"cc":{
|
|
||||||
"p":0.8285611165,
|
|
||||||
"r":0.8237052984,
|
|
||||||
"f":0.8261260721
|
|
||||||
},
|
|
||||||
"neg":{
|
|
||||||
"p":0.9452191235,
|
|
||||||
"r":0.9523331661,
|
|
||||||
"f":0.9487628093
|
|
||||||
},
|
|
||||||
"conj":{
|
|
||||||
"p":0.7577601192,
|
|
||||||
"r":0.7682527694,
|
|
||||||
"f":0.7629703713
|
|
||||||
},
|
|
||||||
"nsubjpass":{
|
|
||||||
"p":0.9216589862,
|
|
||||||
"r":0.9230769231,
|
|
||||||
"f":0.9223674097
|
|
||||||
},
|
|
||||||
"auxpass":{
|
|
||||||
"p":0.946875,
|
|
||||||
"r":0.9662870159,
|
|
||||||
"f":0.9564825254
|
|
||||||
},
|
|
||||||
"dobj":{
|
|
||||||
"p":0.919205298,
|
|
||||||
"r":0.940154594,
|
|
||||||
"f":0.9295619288
|
|
||||||
},
|
|
||||||
"nummod":{
|
|
||||||
"p":0.9373886485,
|
|
||||||
"r":0.9300505051,
|
|
||||||
"f":0.9337051591
|
|
||||||
},
|
|
||||||
"npadvmod":{
|
|
||||||
"p":0.7748549323,
|
|
||||||
"r":0.7115452931,
|
|
||||||
"f":0.7418518519
|
|
||||||
},
|
|
||||||
"prt":{
|
|
||||||
"p":0.8097199341,
|
|
||||||
"r":0.8808243728,
|
|
||||||
"f":0.843776824
|
|
||||||
},
|
|
||||||
"pcomp":{
|
|
||||||
"p":0.8756183746,
|
|
||||||
"r":0.8676470588,
|
|
||||||
"f":0.8716144917
|
|
||||||
},
|
|
||||||
"expl":{
|
|
||||||
"p":0.9809322034,
|
|
||||||
"r":0.9914346895,
|
|
||||||
"f":0.9861554846
|
|
||||||
},
|
|
||||||
"acl":{
|
|
||||||
"p":0.7327887981,
|
|
||||||
"r":0.6852154937,
|
|
||||||
"f":0.7082041162
|
|
||||||
},
|
|
||||||
"agent":{
|
|
||||||
"p":0.8959044369,
|
|
||||||
"r":0.9408602151,
|
|
||||||
"f":0.9178321678
|
|
||||||
},
|
|
||||||
"dative":{
|
|
||||||
"p":0.7846153846,
|
|
||||||
"r":0.7018348624,
|
|
||||||
"f":0.7409200969
|
|
||||||
},
|
|
||||||
"acomp":{
|
|
||||||
"p":0.9127423823,
|
|
||||||
"r":0.8965986395,
|
|
||||||
"f":0.90459849
|
|
||||||
},
|
|
||||||
"dep":{
|
|
||||||
"p":0.3786764706,
|
|
||||||
"r":0.1672077922,
|
|
||||||
"f":0.231981982
|
|
||||||
},
|
|
||||||
"csubj":{
|
|
||||||
"p":0.7393939394,
|
|
||||||
"r":0.7218934911,
|
|
||||||
"f":0.7305389222
|
|
||||||
},
|
|
||||||
"quantmod":{
|
|
||||||
"p":0.8694493783,
|
|
||||||
"r":0.7952883834,
|
|
||||||
"f":0.8307170132
|
|
||||||
},
|
|
||||||
"nmod":{
|
|
||||||
"p":0.7147169811,
|
|
||||||
"r":0.577087142,
|
|
||||||
"f":0.6385704653
|
|
||||||
},
|
|
||||||
"appos":{
|
|
||||||
"p":0.7100509495,
|
|
||||||
"r":0.6650759219,
|
|
||||||
"f":0.686827957
|
|
||||||
},
|
|
||||||
"predet":{
|
|
||||||
"p":0.8636363636,
|
|
||||||
"r":0.8969957082,
|
|
||||||
"f":0.88
|
|
||||||
},
|
|
||||||
"preconj":{
|
|
||||||
"p":0.5769230769,
|
|
||||||
"r":0.6976744186,
|
|
||||||
"f":0.6315789474
|
|
||||||
},
|
|
||||||
"oprd":{
|
|
||||||
"p":0.8160535117,
|
|
||||||
"r":0.728358209,
|
|
||||||
"f":0.7697160883
|
|
||||||
},
|
|
||||||
"parataxis":{
|
|
||||||
"p":0.5835694051,
|
|
||||||
"r":0.4468546638,
|
|
||||||
"f":0.5061425061
|
|
||||||
},
|
|
||||||
"meta":{
|
|
||||||
"p":0.8666666667,
|
|
||||||
"r":0.5,
|
|
||||||
"f":0.6341463415
|
|
||||||
},
|
|
||||||
"csubjpass":{
|
|
||||||
"p":0.5,
|
|
||||||
"r":0.6666666667,
|
|
||||||
"f":0.5714285714
|
|
||||||
}
|
|
||||||
},
|
|
||||||
"ents_p":0.8565043157,
|
|
||||||
"ents_r":0.8348858173,
|
|
||||||
"ents_f":0.8455569081,
|
|
||||||
"ents_per_type":{
|
|
||||||
"DATE":{
|
|
||||||
"p":0.8804768041,
|
|
||||||
"r":0.8676190476,
|
|
||||||
"f":0.8740006396
|
|
||||||
},
|
|
||||||
"GPE":{
|
|
||||||
"p":0.9239884393,
|
|
||||||
"r":0.8917712692,
|
|
||||||
"f":0.9075940383
|
|
||||||
},
|
|
||||||
"ORDINAL":{
|
|
||||||
"p":0.7910447761,
|
|
||||||
"r":0.8229813665,
|
|
||||||
"f":0.8066971081
|
|
||||||
},
|
|
||||||
"ORG":{
|
|
||||||
"p":0.8107606679,
|
|
||||||
"r":0.8109756098,
|
|
||||||
"f":0.8108681246
|
|
||||||
},
|
|
||||||
"FAC":{
|
|
||||||
"p":0.3902439024,
|
|
||||||
"r":0.3692307692,
|
|
||||||
"f":0.3794466403
|
|
||||||
},
|
|
||||||
"CARDINAL":{
|
|
||||||
"p":0.8266978923,
|
|
||||||
"r":0.8394768133,
|
|
||||||
"f":0.8330383481
|
|
||||||
},
|
|
||||||
"PERSON":{
|
|
||||||
"p":0.8648820905,
|
|
||||||
"r":0.885770235,
|
|
||||||
"f":0.8752015479
|
|
||||||
},
|
|
||||||
"NORP":{
|
|
||||||
"p":0.9130787977,
|
|
||||||
"r":0.8992,
|
|
||||||
"f":0.9060862555
|
|
||||||
},
|
|
||||||
"TIME":{
|
|
||||||
"p":0.7492163009,
|
|
||||||
"r":0.6988304094,
|
|
||||||
"f":0.7231467474
|
|
||||||
},
|
|
||||||
"LOC":{
|
|
||||||
"p":0.7158273381,
|
|
||||||
"r":0.6337579618,
|
|
||||||
"f":0.6722972973
|
|
||||||
},
|
|
||||||
"QUANTITY":{
|
|
||||||
"p":0.7971014493,
|
|
||||||
"r":0.6043956044,
|
|
||||||
"f":0.6875
|
|
||||||
},
|
|
||||||
"EVENT":{
|
|
||||||
"p":0.6373626374,
|
|
||||||
"r":0.3333333333,
|
|
||||||
"f":0.4377358491
|
|
||||||
},
|
|
||||||
"WORK_OF_ART":{
|
|
||||||
"p":0.5230769231,
|
|
||||||
"r":0.3505154639,
|
|
||||||
"f":0.4197530864
|
|
||||||
},
|
|
||||||
"LAW":{
|
|
||||||
"p":0.6304347826,
|
|
||||||
"r":0.453125,
|
|
||||||
"f":0.5272727273
|
|
||||||
},
|
|
||||||
"MONEY":{
|
|
||||||
"p":0.9179548157,
|
|
||||||
"r":0.9114521842,
|
|
||||||
"f":0.9146919431
|
|
||||||
},
|
|
||||||
"PERCENT":{
|
|
||||||
"p":0.9171974522,
|
|
||||||
"r":0.8820826953,
|
|
||||||
"f":0.8992974239
|
|
||||||
},
|
|
||||||
"PRODUCT":{
|
|
||||||
"p":0.5,
|
|
||||||
"r":0.2274881517,
|
|
||||||
"f":0.3127035831
|
|
||||||
},
|
|
||||||
"LANGUAGE":{
|
|
||||||
"p":0.8,
|
|
||||||
"r":0.625,
|
|
||||||
"f":0.701754386
|
|
||||||
}
|
|
||||||
},
|
|
||||||
"speed":9012.0225085527
|
|
||||||
},
|
|
||||||
"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":"ClearNLP Constituent-to-Dependency Conversion",
|
|
||||||
"url":"https://github.com/clir/clearnlp-guidelines/blob/master/md/components/dependency_conversion.md",
|
|
||||||
"license":"Citation provided for reference, no code packaged with model",
|
|
||||||
"author":"Emory University"
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name":"WordNet 3.0",
|
|
||||||
"url":"https://wordnet.princeton.edu/",
|
|
||||||
"author":"Princeton University",
|
|
||||||
"license":"WordNet 3.0 License"
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"requirements":[
|
|
||||||
|
|
||||||
]
|
]
|
||||||
}
|
}
|
||||||
Binary file not shown.
|
|
@ -1 +1 @@
|
||||||
‚¥movesÚ¤{"0":{},"1":{"ORG":56516,"DATE":40493,"PERSON":36534,"GPE":26745,"MONEY":15158,"CARDINAL":14109,"NORP":9641,"PERCENT":9199,"WORK_OF_ART":4488,"LOC":4055,"TIME":3678,"QUANTITY":3123,"FAC":3046,"EVENT":3021,"ORDINAL":2142,"PRODUCT":1787,"LAW":1624,"LANGUAGE":355,"invoice.total":-1,"invoice.number":-2,"invoice.date":-3,"cdtr.name":-4,"cdtr.iban":-5,"cdtr.bic":-6},"2":{"ORG":56516,"DATE":40493,"PERSON":36534,"GPE":26745,"MONEY":15158,"CARDINAL":14109,"NORP":9641,"PERCENT":9199,"WORK_OF_ART":4488,"LOC":4055,"TIME":3678,"QUANTITY":3123,"FAC":3046,"EVENT":3021,"ORDINAL":2142,"PRODUCT":1787,"LAW":1624,"LANGUAGE":355,"invoice.total":-1,"invoice.number":-2,"invoice.date":-3,"cdtr.name":-4,"cdtr.iban":-5,"cdtr.bic":-6},"3":{"ORG":56516,"DATE":40493,"PERSON":36534,"GPE":26745,"MONEY":15158,"CARDINAL":14109,"NORP":9641,"PERCENT":9199,"WORK_OF_ART":4488,"LOC":4055,"TIME":3678,"QUANTITY":3123,"FAC":3046,"EVENT":3021,"ORDINAL":2142,"PRODUCT":1787,"LAW":1624,"LANGUAGE":355,"invoice.total":-1,"invoice.number":-2,"invoice.date":-3,"cdtr.name":-4,"cdtr.iban":-5,"cdtr.bic":-6},"4":{"ORG":56516,"DATE":40493,"PERSON":36534,"GPE":26745,"MONEY":15158,"CARDINAL":14109,"NORP":9641,"PERCENT":9199,"WORK_OF_ART":4488,"LOC":4055,"TIME":3678,"QUANTITY":3123,"FAC":3046,"EVENT":3021,"ORDINAL":2142,"PRODUCT":1787,"LAW":1624,"LANGUAGE":355,"":1,"invoice.total":-1,"invoice.number":-2,"invoice.date":-3,"cdtr.name":-4,"cdtr.iban":-5,"cdtr.bic":-6},"5":{"":1}}£cfg<66>§neg_keyÀ
|
‚¥movesÚÄ{"0":{},"1":{"invoice.total":-1,"invoice.number":-2,"invoice.date":-3,"cdtr.name":-4,"cdtr.iban":-5,"cdtr.bic":-6},"2":{"invoice.total":-1,"invoice.number":-2,"invoice.date":-3,"cdtr.name":-4,"cdtr.iban":-5,"cdtr.bic":-6},"3":{"invoice.total":-1,"invoice.number":-2,"invoice.date":-3,"cdtr.name":-4,"cdtr.iban":-5,"cdtr.bic":-6},"4":{"":1,"invoice.total":-1,"invoice.number":-2,"invoice.date":-3,"cdtr.name":-4,"cdtr.iban":-5,"cdtr.bic":-6},"5":{"":1}}£cfg<66>§neg_keyÀ
|
||||||
|
|
@ -1,13 +0,0 @@
|
||||||
{
|
|
||||||
"moves":null,
|
|
||||||
"update_with_oracle_cut_size":100,
|
|
||||||
"multitasks":[
|
|
||||||
|
|
||||||
],
|
|
||||||
"min_action_freq":30,
|
|
||||||
"learn_tokens":false,
|
|
||||||
"beam_width":1,
|
|
||||||
"beam_density":0.0,
|
|
||||||
"beam_update_prob":0.0,
|
|
||||||
"incorrect_spans_key":null
|
|
||||||
}
|
|
||||||
Binary file not shown.
|
|
@ -1 +0,0 @@
|
||||||
‚¥movesÚ {"0":{"":994332},"1":{"":999432},"2":{"det":172595,"nsubj":165748,"compound":116623,"amod":105184,"aux":86667,"punct":65478,"advmod":62763,"poss":36443,"mark":27941,"nummod":22598,"auxpass":15594,"prep":14001,"nsubjpass":13856,"neg":12357,"cc":10739,"nmod":9562,"advcl":9062,"npadvmod":8168,"quantmod":7101,"intj":6464,"ccomp":5896,"dobj":3427,"expl":3360,"dep":2871,"predet":1944,"parataxis":1837,"csubj":1428,"preconj":621,"pobj||prep":616,"attr":578,"meta":376,"advmod||conj":368,"dobj||xcomp":352,"acomp":284,"nsubj||ccomp":224,"dative":206,"advmod||xcomp":149,"dobj||ccomp":70,"csubjpass":64,"dobj||conj":62,"prep||conj":51,"acl":48,"prep||nsubj":41,"prep||dobj":36,"xcomp":34,"advmod||ccomp":32,"oprd":31},"3":{"punct":183790,"pobj":182191,"prep":174008,"dobj":89615,"conj":59687,"cc":51930,"ccomp":30385,"advmod":22861,"xcomp":21021,"relcl":20969,"advcl":19828,"attr":17741,"acomp":16922,"appos":15265,"case":13388,"acl":12085,"pcomp":10324,"dep":10116,"npadvmod":9796,"prt":8179,"agent":3903,"dative":3866,"nsubj":3470,"neg":2906,"amod":2839,"intj":2819,"nummod":2732,"oprd":2301,"parataxis":1261,"quantmod":319,"nmod":294,"acl||dobj":200,"prep||dobj":190,"prep||nsubj":162,"acl||nsubj":159,"appos||nsubj":145,"relcl||dobj":134,"relcl||nsubj":111,"aux":103,"expl":96,"meta":92,"appos||dobj":86,"preconj":71,"csubj":65,"prep||nsubjpass":55,"prep||advmod":54,"prep||acomp":53,"det":51,"nsubjpass":45,"relcl||pobj":42,"acl||nsubjpass":42,"mark":40,"auxpass":39,"prep||pobj":36,"relcl||nsubjpass":32,"appos||nsubjpass":31},"4":{"ROOT":111664}}£cfg<66>§neg_keyÀ
|
|
||||||
|
|
@ -1,3 +0,0 @@
|
||||||
{
|
|
||||||
"overwrite":false
|
|
||||||
}
|
|
||||||
Binary file not shown.
|
|
@ -1,56 +0,0 @@
|
||||||
{
|
|
||||||
"labels":[
|
|
||||||
"$",
|
|
||||||
"''",
|
|
||||||
",",
|
|
||||||
"-LRB-",
|
|
||||||
"-RRB-",
|
|
||||||
".",
|
|
||||||
":",
|
|
||||||
"ADD",
|
|
||||||
"AFX",
|
|
||||||
"CC",
|
|
||||||
"CD",
|
|
||||||
"DT",
|
|
||||||
"EX",
|
|
||||||
"FW",
|
|
||||||
"HYPH",
|
|
||||||
"IN",
|
|
||||||
"JJ",
|
|
||||||
"JJR",
|
|
||||||
"JJS",
|
|
||||||
"LS",
|
|
||||||
"MD",
|
|
||||||
"NFP",
|
|
||||||
"NN",
|
|
||||||
"NNP",
|
|
||||||
"NNPS",
|
|
||||||
"NNS",
|
|
||||||
"PDT",
|
|
||||||
"POS",
|
|
||||||
"PRP",
|
|
||||||
"PRP$",
|
|
||||||
"RB",
|
|
||||||
"RBR",
|
|
||||||
"RBS",
|
|
||||||
"RP",
|
|
||||||
"SYM",
|
|
||||||
"TO",
|
|
||||||
"UH",
|
|
||||||
"VB",
|
|
||||||
"VBD",
|
|
||||||
"VBG",
|
|
||||||
"VBN",
|
|
||||||
"VBP",
|
|
||||||
"VBZ",
|
|
||||||
"WDT",
|
|
||||||
"WP",
|
|
||||||
"WP$",
|
|
||||||
"WRB",
|
|
||||||
"XX",
|
|
||||||
"_SP",
|
|
||||||
"``"
|
|
||||||
],
|
|
||||||
"neg_prefix":"!",
|
|
||||||
"overwrite":false
|
|
||||||
}
|
|
||||||
Binary file not shown.
|
|
@ -1,3 +0,0 @@
|
||||||
{
|
|
||||||
|
|
||||||
}
|
|
||||||
Binary file not shown.
File diff suppressed because one or more lines are too long
Binary file not shown.
File diff suppressed because it is too large
Load diff
|
|
@ -7,11 +7,6 @@
|
||||||
<item name="workflow.userid"><value xsi:type="xs:string">admin</value></item>
|
<item name="workflow.userid"><value xsi:type="xs:string">admin</value></item>
|
||||||
<item name="workflow.password"><value xsi:type="xs:string">imixs4.null</value></item>
|
<item name="workflow.password"><value xsi:type="xs:string">imixs4.null</value></item>
|
||||||
|
|
||||||
<!-- Erledigte Rechnungen" -->
|
|
||||||
<item name="workflow.query"><value xsi:type="xs:string">($workflowgroup:"Rechnungseingang" OR $workflowgroup:"Sachrechnung") AND ($taskid:5900)</value></item>
|
|
||||||
|
|
||||||
<item name="workflow.pagesize"><value xsi:type="xs:int">10</value></item>
|
|
||||||
<item name="workflow.pageindex"><value xsi:type="xs:int">0</value></item>
|
|
||||||
<item name="workflow.entities">
|
<item name="workflow.entities">
|
||||||
<value xsi:type="xs:string">cdtr.name</value>
|
<value xsi:type="xs:string">cdtr.name</value>
|
||||||
<value xsi:type="xs:string">cdtr.iban</value>
|
<value xsi:type="xs:string">cdtr.iban</value>
|
||||||
|
|
@ -39,13 +34,19 @@
|
||||||
<item name="ml.training.filepattern"><value xsi:type="xs:string">.pdf|.PDF</value></item>
|
<item name="ml.training.filepattern"><value xsi:type="xs:string">.pdf|.PDF</value></item>
|
||||||
<!-- LOW | GOOD -->
|
<!-- LOW | GOOD -->
|
||||||
<item name="ml.training.quality"><value xsi:type="xs:string">LOW</value></item>
|
<item name="ml.training.quality"><value xsi:type="xs:string">LOW</value></item>
|
||||||
<item name="ml.training.iterations"><value xsi:type="xs:string">1</value></item>
|
|
||||||
<item name="ml.training.dropoutrate"><value xsi:type="xs:string">0.25</value></item>
|
|
||||||
|
|
||||||
|
|
||||||
<!-- ML Max Accuracy - should be between 1 and 0 -->
|
|
||||||
<item name="ml.options"><value xsi:type="xs:string">min_losses=0</value></item>
|
|
||||||
|
|
||||||
|
<!-- Define the training set and taining mode -->
|
||||||
|
<item name="workflow.query"><value xsi:type="xs:string">($workflowgroup:"Rechnungseingang" OR $workflowgroup:"Sachrechnung") AND ($taskid:5900)</value></item>
|
||||||
|
<item name="workflow.pagesize"><value xsi:type="xs:int">1000</value></item>
|
||||||
|
<item name="workflow.pageindex"><value xsi:type="xs:int">0</value></item>
|
||||||
|
<item name="ml.training.iterations"><value xsi:type="xs:string">10</value></item>
|
||||||
|
<item name="ml.training.dropoutrate"><value xsi:type="xs:string">0.0</value></item>
|
||||||
|
<item name="ml.options">
|
||||||
|
<value xsi:type="xs:string">min_losses=0.0&retrain_rate=100</value>
|
||||||
|
</item>
|
||||||
|
|
||||||
|
|
||||||
</document>
|
</document>
|
||||||
|
|
||||||
|
|
||||||
|
|
|
||||||
|
|
@ -384,7 +384,7 @@ Betrag: <itemvalue>_amount</itemvalue> (Brutto € <itemvalue>_amount_brutto</it
|
||||||
</imixs:item>
|
</imixs:item>
|
||||||
<imixs:item name="txtactivityresult" type="xs:string">
|
<imixs:item name="txtactivityresult" type="xs:string">
|
||||||
<imixs:value><![CDATA[<ml-config name="model">invoice-de-0.2.0</ml-config>
|
<imixs:value><![CDATA[<ml-config name="model">invoice-de-0.2.0</ml-config>
|
||||||
<ml-config name="options">min_losses=0.001</ml-config>
|
<ml-config name="options">min_losses=0.1&retrain_rate=25</ml-config>
|
||||||
<ml-config name="filename.pattern">((PDF|pdf)$)</ml-config>
|
<ml-config name="filename.pattern">((PDF|pdf)$)</ml-config>
|
||||||
<ml-config name="entity">
|
<ml-config name="entity">
|
||||||
<name>invoice.total</name>
|
<name>invoice.total</name>
|
||||||
|
|
@ -635,6 +635,7 @@ Betrag: <itemvalue>_amount</itemvalue> (Brutto € <itemvalue>_amount_brutto</it
|
||||||
<bpmn2:sequenceFlow id="SequenceFlow_17" sourceRef="IntermediateCatchEvent_7" targetRef="IntermediateCatchEvent_5"/>
|
<bpmn2:sequenceFlow id="SequenceFlow_17" sourceRef="IntermediateCatchEvent_7" targetRef="IntermediateCatchEvent_5"/>
|
||||||
<bpmn2:textAnnotation id="TextAnnotation_2">
|
<bpmn2:textAnnotation id="TextAnnotation_2">
|
||||||
<bpmn2:text>min_losses = 1.0 - 22.12.2021 geändert auf 0.001
|
<bpmn2:text>min_losses = 1.0 - 22.12.2021 geändert auf 0.001
|
||||||
|
retrain_rate=25
|
||||||
filename.pattern = (PDF|pdf)$</bpmn2:text>
|
filename.pattern = (PDF|pdf)$</bpmn2:text>
|
||||||
</bpmn2:textAnnotation>
|
</bpmn2:textAnnotation>
|
||||||
<bpmn2:association id="Association_1" sourceRef="TextAnnotation_2" targetRef="IntermediateCatchEvent_4"/>
|
<bpmn2:association id="Association_1" sourceRef="TextAnnotation_2" targetRef="IntermediateCatchEvent_4"/>
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue