Update spaCy pipeline

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer/pkuseg_processors filter=lfs diff=lfs merge=lfs -text
+transformer/model filter=lfs diff=lfs merge=lfs -text
+zh_core_web_trf-any-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,97 @@
+---
+tags:
+- spacy
+- token-classification
+language:
+- zh
+license: mit
+model-index:
+- name: zh_core_web_trf
+  results:
+  - task:
+      name: NER
+      type: token-classification
+    metrics:
+    - name: NER Precision
+      type: precision
+      value: 0.7608897127
+    - name: NER Recall
+      type: recall
+      value: 0.7217582418
+    - name: NER F Score
+      type: f_score
+      value: 0.7408075795
+  - task:
+      name: TAG
+      type: token-classification
+    metrics:
+    - name: TAG (XPOS) Accuracy
+      type: accuracy
+      value: 0.9175332527
+  - task:
+      name: UNLABELED_DEPENDENCIES
+      type: token-classification
+    metrics:
+    - name: Unlabeled Attachment Score (UAS)
+      type: f_score
+      value: 0.7572203056
+  - task:
+      name: LABELED_DEPENDENCIES
+      type: token-classification
+    metrics:
+    - name: Labeled Attachment Score (LAS)
+      type: f_score
+      value: 0.7145288854
+  - task:
+      name: SENTS
+      type: token-classification
+    metrics:
+    - name: Sentences F-Score
+      type: f_score
+      value: 0.6920716113
+---
+Chinese transformer pipeline (Transformer(name='bert-base-chinese', piece_encoder='bert-wordpiece', stride=152, type='bert', width=768, window=208, vocab_size=21128)). Components: transformer, tagger, parser, ner, attribute_ruler.
+
+| Feature | Description |
+| --- | --- |
+| **Name** | `zh_core_web_trf` |
+| **Version** | `3.7.2` |
+| **spaCy** | `>=3.7.0,<3.8.0` |
+| **Default Pipeline** | `transformer`, `tagger`, `parser`, `attribute_ruler`, `ner` |
+| **Components** | `transformer`, `tagger`, `parser`, `attribute_ruler`, `ner` |
+| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
+| **Sources** | [OntoNotes 5](https://catalog.ldc.upenn.edu/LDC2013T19) (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)<br>[CoreNLP Universal Dependencies Converter](https://nlp.stanford.edu/software/stanford-dependencies.html) (Stanford NLP Group)<br>[bert-base-chinese](https://huggingface.co/bert-base-chinese) (Hugging Face) |
+| **License** | `MIT` |
+| **Author** | [Explosion](https://explosion.ai) |
+
+### Label Scheme
+
+<details>
+
+<summary>View label scheme (99 labels for 3 components)</summary>
+
+| Component | Labels |
+| --- | --- |
+| **`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` |
+| **`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` |
+| **`ner`** | `CARDINAL`, `DATE`, `EVENT`, `FAC`, `GPE`, `LANGUAGE`, `LAW`, `LOC`, `MONEY`, `NORP`, `ORDINAL`, `ORG`, `PERCENT`, `PERSON`, `PRODUCT`, `QUANTITY`, `TIME`, `WORK_OF_ART` |
+
+</details>
+
+### Accuracy
+
+| Type | Score |
+| --- | --- |
+| `TOKEN_ACC` | 95.85 |
+| `TOKEN_P` | 94.58 |
+| `TOKEN_R` | 91.36 |
+| `TOKEN_F` | 92.94 |
+| `TAG_ACC` | 91.75 |
+| `SENTS_P` | 70.92 |
+| `SENTS_R` | 67.57 |
+| `SENTS_F` | 69.21 |
+| `DEP_UAS` | 75.72 |
+| `DEP_LAS` | 71.45 |
+| `ENTS_P` | 76.09 |
+| `ENTS_R` | 72.18 |
+| `ENTS_F` | 74.08 |

config.cfg

@@ -0,0 +1,257 @@
+[paths]
+train = null
+dev = null
+vectors = null
+init_tok2vec = null
+
+[system]
+gpu_allocator = "pytorch"
+seed = 1
+
+[nlp]
+lang = "zh"
+pipeline = ["transformer","tagger","parser","attribute_ruler","ner"]
+disabled = []
+before_creation = null
+after_creation = null
+after_pipeline_creation = null
+batch_size = 64
+vectors = {"@vectors":"spacy.Vectors.v1"}
+
+[nlp.tokenizer]
+@tokenizers = "spacy.zh.ChineseTokenizer"
+segmenter = "pkuseg"
+
+[components]
+
+[components.attribute_ruler]
+factory = "attribute_ruler"
+scorer = {"@scorers":"spacy.attribute_ruler_scorer.v1"}
+validate = false
+
+[components.ner]
+factory = "ner"
+incorrect_spans_key = null
+moves = null
+scorer = {"@scorers":"spacy.ner_scorer.v1"}
+update_with_oracle_cut_size = 100
+
+[components.ner.model]
+@architectures = "spacy.TransitionBasedParser.v2"
+state_type = "ner"
+extra_state_tokens = false
+hidden_width = 64
+maxout_pieces = 2
+use_upper = false
+nO = null
+
+[components.ner.model.tok2vec]
+@architectures = "spacy-curated-transformers.LastTransformerLayerListener.v1"
+width = ${components.transformer.model.hidden_width}
+upstream = "transformer"
+pooling = {"@layers":"reduce_mean.v1"}
+grad_factor = 1.0
+
+[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 = false
+nO = null
+
+[components.parser.model.tok2vec]
+@architectures = "spacy-curated-transformers.LastTransformerLayerListener.v1"
+width = ${components.transformer.model.hidden_width}
+upstream = "transformer"
+pooling = {"@layers":"reduce_mean.v1"}
+grad_factor = 1.0
+
+[components.tagger]
+factory = "tagger"
+label_smoothing = 0.0
+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-curated-transformers.LastTransformerLayerListener.v1"
+width = ${components.transformer.model.hidden_width}
+upstream = "transformer"
+pooling = {"@layers":"reduce_mean.v1"}
+grad_factor = 1.0
+
+[components.transformer]
+factory = "curated_transformer"
+all_layer_outputs = false
+frozen = false
+
+[components.transformer.model]
+@architectures = "spacy-curated-transformers.BertTransformer.v1"
+vocab_size = 21128
+hidden_width = 768
+piece_encoder = {"@architectures":"spacy-curated-transformers.BertWordpieceEncoder.v1"}
+attention_probs_dropout_prob = 0.1
+hidden_act = "gelu"
+hidden_dropout_prob = 0.1
+intermediate_width = 3072
+layer_norm_eps = 0.0
+max_position_embeddings = 512
+model_max_length = 512
+num_attention_heads = 12
+num_hidden_layers = 12
+padding_idx = 0
+type_vocab_size = 2
+torchscript = false
+mixed_precision = false
+wrapped_listener = null
+
+[components.transformer.model.grad_scaler_config]
+
+[components.transformer.model.with_spans]
+@architectures = "spacy-curated-transformers.WithStridedSpans.v1"
+stride = 152
+window = 208
+batch_size = 384
+
+[corpora]
+
+[corpora.dev]
+@readers = "spacy.Corpus.v1"
+path = ${paths.dev}
+gold_preproc = false
+max_length = 0
+limit = 0
+augmenter = null
+
+[corpora.train]
+@readers = "spacy.Corpus.v1"
+path = ${paths.train}
+gold_preproc = false
+max_length = 0
+limit = 0
+augmenter = null
+
+[training]
+train_corpus = "corpora.train"
+dev_corpus = "corpora.dev"
+seed = ${system:seed}
+gpu_allocator = ${system:gpu_allocator}
+dropout = 0.1
+accumulate_gradient = 3
+patience = 5000
+max_epochs = 0
+max_steps = 20000
+eval_frequency = 1000
+frozen_components = []
+before_to_disk = null
+annotating_components = []
+before_update = null
+
+[training.batcher]
+@batchers = "spacy.batch_by_words.v1"
+discard_oversize = false
+size = 2000
+tolerance = 0.2
+get_length = null
+
+[training.logger]
+@loggers = "spacy.ConsoleLogger.v1"
+progress_bar = false
+
+[training.optimizer]
+@optimizers = "Adam.v1"
+beta1 = 0.9
+beta2 = 0.999
+L2_is_weight_decay = true
+L2 = 0.01
+grad_clip = 1.0
+use_averages = true
+eps = 0.00000001
+
+[training.optimizer.learn_rate]
+@schedules = "warmup_linear.v1"
+warmup_steps = 250
+total_steps = 20000
+initial_rate = 0.00005
+
+[training.score_weights]
+tag_acc = 0.32
+dep_uas = 0.0
+dep_las = 0.32
+dep_las_per_type = null
+sents_p = null
+sents_r = null
+sents_f = 0.04
+ents_f = 0.32
+ents_p = 0.0
+ents_r = 0.0
+ents_per_type = null
+speed = 0.0
+
+[pretraining]
+
+[initialize]
+vocab_data = null
+vectors = ${paths.vectors}
+init_tok2vec = ${paths.init_tok2vec}
+before_init = null
+after_init = null
+
+[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.components.transformer]
+
+[initialize.components.transformer.encoder_loader]
+@model_loaders = "spacy-curated-transformers.HFTransformerEncoderLoader.v1"
+name = "bert-base-chinese"
+revision = "main"
+
+[initialize.components.transformer.piecer_loader]
+@model_loaders = "spacy-curated-transformers.HFPieceEncoderLoader.v1"
+name = "bert-base-chinese"
+revision = "main"
+
+[initialize.lookups]
+@misc = "spacy.LookupsDataLoader.v1"
+lang = ${nlp.lang}
+tables = []
+
+[initialize.tokenizer]
+pkuseg_model = "assets/pkuseg_model"
+pkuseg_user_dict = "default"

meta.json

@@ -0,0 +1,507 @@
+{
+  "lang":"zh",
+  "name":"core_web_trf",
+  "version":"3.7.2",
+  "description":"Chinese transformer pipeline (Transformer(name='bert-base-chinese', piece_encoder='bert-wordpiece', stride=152, type='bert', width=768, window=208, vocab_size=21128)). Components: transformer, tagger, parser, ner, attribute_ruler.",
+  "author":"Explosion",
+  "email":"contact@explosion.ai",
+  "url":"https://explosion.ai",
+  "license":"MIT",
+  "spacy_version":">=3.7.0,<3.8.0",
+  "spacy_git_version":"4ec41e98f",
+  "vectors":{
+    "width":0,
+    "vectors":0,
+    "keys":0,
+    "name":null
+  },
+  "labels":{
+    "transformer":[
+
+    ],
+    "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"
+    ],
+    "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":[
+    "transformer",
+    "tagger",
+    "parser",
+    "attribute_ruler",
+    "ner"
+  ],
+  "components":[
+    "transformer",
+    "tagger",
+    "parser",
+    "attribute_ruler",
+    "ner"
+  ],
+  "disabled":[
+
+  ],
+  "performance":{
+    "token_acc":0.9585384056,
+    "token_p":0.9458325855,
+    "token_r":0.9136060443,
+    "token_f":0.9294400505,
+    "tag_acc":0.9175332527,
+    "sents_p":0.7092434038,
+    "sents_r":0.6757116697,
+    "sents_f":0.6920716113,
+    "dep_uas":0.7572203056,
+    "dep_las":0.7145288854,
+    "dep_las_per_type":{
+      "dep":{
+        "p":0.5542676502,
+        "r":0.4251793473,
+        "f":0.4812167648
+      },
+      "case":{
+        "p":0.9020435069,
+        "r":0.8295344326,
+        "f":0.8642708268
+      },
+      "nmod:tmod":{
+        "p":0.7832446809,
+        "r":0.8013605442,
+        "f":0.7921990585
+      },
+      "nummod":{
+        "p":0.8815789474,
+        "r":0.5802798135,
+        "f":0.6998794697
+      },
+      "mark:clf":{
+        "p":0.9339393939,
+        "r":0.5747855278,
+        "f":0.711613946
+      },
+      "auxpass":{
+        "p":0.9095744681,
+        "r":0.9243243243,
+        "f":0.9168900804
+      },
+      "nsubj":{
+        "p":0.8642424242,
+        "r":0.7882324039,
+        "f":0.8244892715
+      },
+      "acl":{
+        "p":0.7845096814,
+        "r":0.6966167499,
+        "f":0.7379553467
+      },
+      "advmod":{
+        "p":0.868605557,
+        "r":0.7583314441,
+        "f":0.8097312999
+      },
+      "mark":{
+        "p":0.8348993289,
+        "r":0.8177037686,
+        "f":0.8262120877
+      },
+      "xcomp":{
+        "p":0.8014981273,
+        "r":0.6970684039,
+        "f":0.7456445993
+      },
+      "nmod:assmod":{
+        "p":0.8492146597,
+        "r":0.7572362278,
+        "f":0.8005923001
+      },
+      "det":{
+        "p":0.8788617886,
+        "r":0.633274751,
+        "f":0.7361252979
+      },
+      "amod":{
+        "p":0.8216442174,
+        "r":0.6948153967,
+        "f":0.7529261545
+      },
+      "nmod:prep":{
+        "p":0.8173109819,
+        "r":0.7226255293,
+        "f":0.7670573126
+      },
+      "root":{
+        "p":0.7621591746,
+        "r":0.6886965207,
+        "f":0.723567993
+      },
+      "aux:prtmod":{
+        "p":0.9551020408,
+        "r":0.8357142857,
+        "f":0.8914285714
+      },
+      "compound:nn":{
+        "p":0.7833185448,
+        "r":0.7468697124,
+        "f":0.764660026
+      },
+      "dobj":{
+        "p":0.8932703275,
+        "r":0.8120278477,
+        "f":0.8507138423
+      },
+      "ccomp":{
+        "p":0.7626977519,
+        "r":0.7122861586,
+        "f":0.7366304785
+      },
+      "advmod:rcomp":{
+        "p":0.8369230769,
+        "r":0.7534626039,
+        "f":0.7930029155
+      },
+      "nmod:topic":{
+        "p":0.4624505929,
+        "r":0.3798701299,
+        "f":0.4171122995
+      },
+      "cop":{
+        "p":0.8350515464,
+        "r":0.6254826255,
+        "f":0.7152317881
+      },
+      "discourse":{
+        "p":0.5836267606,
+        "r":0.547029703,
+        "f":0.5647359455
+      },
+      "neg":{
+        "p":0.8730650155,
+        "r":0.6706302021,
+        "f":0.7585743107
+      },
+      "aux:modal":{
+        "p":0.8915401302,
+        "r":0.8500517063,
+        "f":0.870301747
+      },
+      "nmod":{
+        "p":0.7740524781,
+        "r":0.7204884668,
+        "f":0.7463106114
+      },
+      "aux:ba":{
+        "p":0.9106145251,
+        "r":0.8670212766,
+        "f":0.8882833787
+      },
+      "advmod:loc":{
+        "p":0.7519379845,
+        "r":0.5756676558,
+        "f":0.6521008403
+      },
+      "aux:asp":{
+        "p":0.9163179916,
+        "r":0.8732057416,
+        "f":0.894242548
+      },
+      "conj":{
+        "p":0.6111647672,
+        "r":0.5981096408,
+        "f":0.6045667335
+      },
+      "nsubjpass":{
+        "p":0.9,
+        "r":0.72,
+        "f":0.8
+      },
+      "compound:vc":{
+        "p":0.4628820961,
+        "r":0.5492227979,
+        "f":0.5023696682
+      },
+      "advcl:loc":{
+        "p":0.6488549618,
+        "r":0.6071428571,
+        "f":0.6273062731
+      },
+      "cc":{
+        "p":0.7943396226,
+        "r":0.7471162378,
+        "f":0.7700045725
+      },
+      "advmod:dvp":{
+        "p":0.9212598425,
+        "r":0.7267080745,
+        "f":0.8125
+      },
+      "appos":{
+        "p":0.9382716049,
+        "r":0.8735632184,
+        "f":0.9047619048
+      },
+      "nmod:poss":{
+        "p":0.7280701754,
+        "r":0.6148148148,
+        "f":0.6666666667
+      },
+      "name":{
+        "p":0.6261682243,
+        "r":0.4962962963,
+        "f":0.5537190083
+      },
+      "nsubj:xsubj":{
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
+      },
+      "nmod:range":{
+        "p":0.8098859316,
+        "r":0.7147651007,
+        "f":0.7593582888
+      },
+      "parataxis:prnmod":{
+        "p":0.3442622951,
+        "r":0.1578947368,
+        "f":0.2164948454
+      },
+      "amod:ordmod":{
+        "p":0.7547169811,
+        "r":0.625,
+        "f":0.6837606838
+      },
+      "erased":{
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
+      },
+      "etc":{
+        "p":0.9277108434,
+        "r":0.9166666667,
+        "f":0.9221556886
+      }
+    },
+    "ents_p":0.7608897127,
+    "ents_r":0.7217582418,
+    "ents_f":0.7408075795,
+    "ents_per_type":{
+      "DATE":{
+        "p":0.7811607992,
+        "r":0.8136769078,
+        "f":0.7970873786
+      },
+      "GPE":{
+        "p":0.8325837081,
+        "r":0.8142717498,
+        "f":0.8233259204
+      },
+      "ORDINAL":{
+        "p":0.8488372093,
+        "r":0.7684210526,
+        "f":0.8066298343
+      },
+      "FAC":{
+        "p":0.3906976744,
+        "r":0.4516129032,
+        "f":0.4189526185
+      },
+      "LOC":{
+        "p":0.5012406948,
+        "r":0.5430107527,
+        "f":0.5212903226
+      },
+      "QUANTITY":{
+        "p":0.696,
+        "r":0.6444444444,
+        "f":0.6692307692
+      },
+      "ORG":{
+        "p":0.7461476075,
+        "r":0.700152207,
+        "f":0.7224185316
+      },
+      "PERSON":{
+        "p":0.8739386022,
+        "r":0.8621134021,
+        "f":0.8679857282
+      },
+      "CARDINAL":{
+        "p":0.6729088639,
+        "r":0.5433467742,
+        "f":0.6012269939
+      },
+      "NORP":{
+        "p":0.6961038961,
+        "r":0.5630252101,
+        "f":0.6225319396
+      },
+      "WORK_OF_ART":{
+        "p":0.5625,
+        "r":0.3,
+        "f":0.3913043478
+      },
+      "TIME":{
+        "p":0.7875647668,
+        "r":0.7378640777,
+        "f":0.7619047619
+      },
+      "MONEY":{
+        "p":0.9256198347,
+        "r":0.8296296296,
+        "f":0.875
+      },
+      "EVENT":{
+        "p":0.5430463576,
+        "r":0.6029411765,
+        "f":0.5714285714
+      },
+      "PERCENT":{
+        "p":0.869047619,
+        "r":0.8795180723,
+        "f":0.874251497
+      },
+      "PRODUCT":{
+        "p":0.3793103448,
+        "r":0.2244897959,
+        "f":0.2820512821
+      },
+      "LAW":{
+        "p":0.3571428571,
+        "r":0.25,
+        "f":0.2941176471
+      },
+      "LANGUAGE":{
+        "p":0.4666666667,
+        "r":0.7777777778,
+        "f":0.5833333333
+      }
+    },
+    "speed":2677.6055974261
+  },
+  "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":"bert-base-chinese",
+      "author":"Hugging Face",
+      "url":"https://huggingface.co/bert-base-chinese",
+      "license":""
+    }
+  ],
+  "requirements":[
+    "spacy-curated-transformers>=0.2.0,<0.3.0",
+    "spacy-pkuseg>=0.0.27,<0.1.0"
+  ]
+}

ner/cfg

@@ -0,0 +1,13 @@
+{
+  "moves":null,
+  "update_with_oracle_cut_size":100,
+  "multitasks":[
+
+  ],
+  "min_action_freq":1,
+  "learn_tokens":false,
+  "beam_width":1,
+  "beam_density":0.0,
+  "beam_update_prob":0.0,
+  "incorrect_spans_key":null
+}

ner/moves

@@ -0,0 +1 @@
+��moves��{"0":{},"1":{"GPE":15943,"ORG":15205,"DATE":14256,"PERSON":10912,"CARDINAL":7849,"TIME":2905,"NORP":2685,"EVENT":2602,"MONEY":2519,"LOC":2452,"FAC":2256,"WORK_OF_ART":2014,"QUANTITY":1717,"ORDINAL":1156,"PERCENT":852,"LAW":695,"PRODUCT":486,"LANGUAGE":336},"2":{"GPE":15943,"ORG":15205,"DATE":14256,"PERSON":10912,"CARDINAL":7849,"TIME":2905,"NORP":2685,"EVENT":2602,"MONEY":2519,"LOC":2452,"FAC":2256,"WORK_OF_ART":2014,"QUANTITY":1717,"ORDINAL":1156,"PERCENT":852,"LAW":695,"PRODUCT":486,"LANGUAGE":336},"3":{"GPE":15943,"ORG":15205,"DATE":14256,"PERSON":10912,"CARDINAL":7849,"TIME":2905,"NORP":2685,"EVENT":2602,"MONEY":2519,"LOC":2452,"FAC":2256,"WORK_OF_ART":2014,"QUANTITY":1717,"ORDINAL":1156,"PERCENT":852,"LAW":695,"PRODUCT":486,"LANGUAGE":336},"4":{"GPE":15943,"ORG":15205,"DATE":14256,"PERSON":10912,"CARDINAL":7849,"TIME":2905,"NORP":2685,"EVENT":2602,"MONEY":2519,"LOC":2452,"FAC":2256,"WORK_OF_ART":2014,"QUANTITY":1717,"ORDINAL":1156,"PERCENT":852,"LAW":695,"PRODUCT":486,"LANGUAGE":336,"":1},"5":{"":1}}�cfg��neg_key�

parser/cfg

@@ -0,0 +1,13 @@
+{
+  "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
+}

parser/moves

@@ -0,0 +1 @@
+��moves��{"0":{"":436297},"1":{"":282750},"2":{"advmod":61142,"nsubj":55539,"compound:nn":45994,"dep":43937,"punct":36396,"case":24751,"nmod:assmod":22308,"nmod:prep":21037,"amod":18609,"acl":12438,"conj":10993,"det":10371,"nummod":9922,"cop":9515,"cc":6289,"aux:modal":6003,"neg":5955,"nmod:tmod":5338,"nmod":5049,"xcomp":4333,"appos":2988,"nmod:topic":2532,"discourse":2283,"advmod:loc":1902,"aux:prtmod":1724,"aux:ba":1323,"auxpass":1240,"advmod:dvp":1193,"name":1117,"advcl:loc":1072,"compound:vc":834,"nmod:poss":657,"amod:ordmod":601,"dobj":441,"nsubjpass":276,"nsubj:xsubj||ccomp":64,"parataxis:prnmod":36,"nsubj:xsubj":32},"3":{"punct":74587,"dobj":46958,"conj":31352,"case":31222,"dep":20953,"mark:clf":18377,"ccomp":17748,"mark":16793,"aux:asp":8130,"discourse":4187,"advmod:rcomp":2519,"nmod:range":2021,"cc":1715,"nmod:prep":1690,"advmod":1162,"etc":943,"compound:vc":828,"parataxis:prnmod":724,"advmod:loc":571,"neg":70,"acl":43,"advcl:loc":42},"4":{"ROOT":36097}}�cfg��neg_key�

tagger/cfg

@@ -0,0 +1,43 @@
+{
+  "label_smoothing":0.0,
+  "labels":[
+    "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"
+  ],
+  "neg_prefix":"!",
+  "overwrite":false
+}

tokenizer/cfg

@@ -0,0 +1,3 @@
+{
+  "segmenter":"pkuseg"
+}

tokenizer/pkuseg_model/features.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd4322482a7018b9bce9216173ae9d2848efe6d310b468bbb4383fb55c874a18
+size 22685181

tokenizer/pkuseg_model/weights.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ada075eb25a854f71d6e6fa4e7d55e7be0ae049255b1f8f19d05c13b1b68c9e
+size 37508754

tokenizer/pkuseg_processors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdc3129ffe89371aeaf4abacde2b4f00f5e0ff3cae022e937b14c1ed2b54879e
+size 4527029

transformer/cfg

@@ -0,0 +1,3 @@
+{
+
+}

transformer/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d464d0cbb268568bf15914fa84f9feec3ee5445968ecf80b8b7ef87f11129f4
+size 406876695

vocab/key2row

@@ -0,0 +1 @@
+�

vocab/lookups.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76be8b528d0075f7aae98d6fa57a6d3c83ae480a8469e668d7b0af968995ac71
+size 1

vocab/vectors.cfg

@@ -0,0 +1,3 @@
+{
+  "mode":"default"
+}

zh_core_web_trf-any-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c68de47bebdf59de2489ce657e1398fe211c5a1dad0625a3c4b49436f1b45fa
+size 415130114