Upload ja_ner_ja v0.2.0 spaCy NER model

.gitattributes

@@ -33,3 +33,5 @@ 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
+ner/model filter=lfs diff=lfs merge=lfs -text
+tok2vec/model filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,33 @@
+| Feature | Description |
+| --- | --- |
+| **Name** | `ja_ner_ja` |
+| **Version** | `0.2.0` |
+| **spaCy** | `>=3.8.13,<3.9.0` |
+| **Default Pipeline** | `tok2vec`, `ner` |
+| **Components** | `tok2vec`, `ner` |
+| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
+| **Sources** | n/a |
+| **License** | n/a |
+| **Author** | [n/a]() |
+
+### Label Scheme
+
+<details>
+
+<summary>View label scheme (5 labels for 1 components)</summary>
+
+| Component | Labels |
+| --- | --- |
+| **`ner`** | `ADDRESS`, `BANK_ACCOUNT`, `DATE_OF_BIRTH`, `ORGANIZATION`, `PERSON` |
+
+</details>
+
+### Accuracy
+
+| Type | Score |
+| --- | --- |
+| `ENTS_F` | 92.21 |
+| `ENTS_P` | 93.09 |
+| `ENTS_R` | 91.36 |
+| `TOK2VEC_LOSS` | 217008.45 |
+| `NER_LOSS` | 32370.94 |

config.cfg

@@ -0,0 +1,150 @@
+[paths]
+train = "data/processed/ja-v02/train.spacy"
+dev = "data/processed/ja-v02/dev.spacy"
+vectors = null
+init_tok2vec = null
+
+[system]
+seed = 0
+gpu_allocator = null
+
+[nlp]
+lang = "ja"
+pipeline = ["tok2vec", "ner"]
+batch_size = 1000
+disabled = []
+before_creation = null
+after_creation = null
+after_pipeline_creation = null
+
+[training]
+gpu_allocator = ""
+seed = 42
+patience = 1600
+max_epochs = 50
+max_steps = 20000
+eval_frequency = 200
+frozen_components = []
+annotating_components = []
+before_to_disk = null
+before_update = null
+dropout = 0.1
+accumulate_gradient = 1
+dev_corpus = "corpora.dev"
+train_corpus = "corpora.train"
+
+[corpora]
+
+[initialize]
+vectors = ${paths.vectors}
+init_tok2vec = ${paths.init_tok2vec}
+vocab_data = null
+lookups = null
+before_init = null
+after_init = null
+
+[components]
+
+[pretraining]
+
+[nlp.tokenizer]
+@tokenizers = "spacy.ja.JapaneseTokenizer"
+split_mode = null
+
+[nlp.vectors]
+@vectors = "spacy.Vectors.v1"
+
+[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 = false
+eps = 1e-08
+
+[training.batcher]
+@batchers = "spacy.batch_by_words.v1"
+discard_oversize = false
+tolerance = 0.2
+get_length = null
+
+[training.logger]
+@loggers = "spacy.ConsoleLogger.v1"
+progress_bar = true
+
+[training.score_weights]
+ents_f = 1.0
+ents_p = 0.0
+ents_r = 0.0
+ents_per_type = null
+
+[corpora.dev]
+@readers = "spacy.Corpus.v1"
+path = ${paths.dev}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
+
+[corpora.train]
+@readers = "spacy.Corpus.v1"
+path = ${paths.train}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
+
+[initialize.tokenizer]
+
+[initialize.components]
+
+[components.tok2vec]
+factory = "tok2vec"
+
+[components.ner]
+factory = "ner"
+moves = null
+update_with_oracle_cut_size = 100
+incorrect_spans_key = null
+
+[training.optimizer.learn_rate]
+@schedules = "warmup_linear.v1"
+warmup_steps = 250
+total_steps = 20000
+initial_rate = 0.001
+
+[training.batcher.size]
+@schedules = "compounding.v1"
+start = 100
+stop = 1000
+compound = 1.001
+t = 0.0
+
+[components.tok2vec.model]
+@architectures = "spacy.HashEmbedCNN.v2"
+pretrained_vectors = false
+width = 128
+depth = 4
+embed_size = 2000
+window_size = 1
+maxout_pieces = 3
+subword_features = true
+
+[components.ner.model]
+@architectures = "spacy.TransitionBasedParser.v2"
+state_type = "ner"
+extra_state_tokens = false
+hidden_width = 64
+maxout_pieces = 2
+use_upper = true
+nO = null
+
+[components.ner.scorer]
+@scorers = "spacy.ner_scorer.v1"
+
+[components.ner.model.tok2vec]
+@architectures = "spacy.Tok2VecListener.v1"
+width = ${components.tok2vec.model.width}
+upstream = "*"

meta.json

@@ -0,0 +1,78 @@
+{
+  "lang":"ja",
+  "name":"ner_ja",
+  "version":"0.2.0",
+  "description":"",
+  "author":"",
+  "email":"",
+  "url":"",
+  "license":"",
+  "spacy_version":">=3.8.13,<3.9.0",
+  "spacy_git_version":"fdca647",
+  "vectors":{
+    "width":0,
+    "vectors":0,
+    "keys":0,
+    "name":null
+  },
+  "labels":{
+    "tok2vec":[
+
+    ],
+    "ner":[
+      "ADDRESS",
+      "BANK_ACCOUNT",
+      "DATE_OF_BIRTH",
+      "ORGANIZATION",
+      "PERSON"
+    ]
+  },
+  "pipeline":[
+    "tok2vec",
+    "ner"
+  ],
+  "components":[
+    "tok2vec",
+    "ner"
+  ],
+  "disabled":[
+
+  ],
+  "performance":{
+    "ents_f":0.9221388368,
+    "ents_p":0.9308712121,
+    "ents_r":0.9135687732,
+    "ents_per_type":{
+      "PERSON":{
+        "p":0.9503968254,
+        "r":0.9485148515,
+        "f":0.9494549058
+      },
+      "DATE_OF_BIRTH":{
+        "p":0.8720930233,
+        "r":0.8720930233,
+        "f":0.8720930233
+      },
+      "ADDRESS":{
+        "p":0.9035532995,
+        "r":0.9673913043,
+        "f":0.9343832021
+      },
+      "ORGANIZATION":{
+        "p":0.929245283,
+        "r":0.8277310924,
+        "f":0.8755555556
+      },
+      "BANK_ACCOUNT":{
+        "p":0.9473684211,
+        "r":0.8571428571,
+        "f":0.9
+      }
+    },
+    "tok2vec_loss":2170.0845423367,
+    "ner_loss":323.7093811035
+  },
+  "requirements":[
+    "spacy>=3.8.13,<3.9.0"
+  ]
+}

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/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e9f80641f85dfc83c6bd1714438e7ce7764ebdbf7b450ebd450afb5864675e4
+size 139863

ner/moves

@@ -0,0 +1 @@
+��moves�
�{"0":{},"1":{"ADDRESS":17695,"PERSON":9999,"ORGANIZATION":7444,"BANK_ACCOUNT":3861,"DATE_OF_BIRTH":3451},"2":{"ADDRESS":17695,"PERSON":9999,"ORGANIZATION":7444,"BANK_ACCOUNT":3861,"DATE_OF_BIRTH":3451},"3":{"ADDRESS":17695,"PERSON":9999,"ORGANIZATION":7444,"BANK_ACCOUNT":3861,"DATE_OF_BIRTH":3451},"4":{"ADDRESS":17695,"PERSON":9999,"ORGANIZATION":7444,"BANK_ACCOUNT":3861,"DATE_OF_BIRTH":3451,"":1},"5":{"":1}}�cfg��neg_key�

tok2vec/cfg

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

tok2vec/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d05d47c9a380f411084d22d76e661232bdc9a0c2f7787baa30d4de15868d66e6
+size 5724617

tokenizer/cfg

@@ -0,0 +1,3 @@
+{
+  "split_mode":null
+}

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"
+}