Update spaCy pipeline

.gitattributes

@@ -32,3 +32,5 @@ 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
+nl_middle_dutch_spacy-any-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+transformer/model filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,56 @@
+---
+tags:
+- spacy
+- token-classification
+language:
+- nl
+model-index:
+- name: nl_middle_dutch_spacy
+  results:
+  - task:
+      name: NER
+      type: token-classification
+    metrics:
+    - name: NER Precision
+      type: precision
+      value: 0.9371146732
+    - name: NER Recall
+      type: recall
+      value: 0.9268292683
+    - name: NER F Score
+      type: f_score
+      value: 0.9319435929
+---
+| Feature | Description |
+| --- | --- |
+| **Name** | `nl_middle_dutch_spacy` |
+| **Version** | `0.0.0` |
+| **spaCy** | `>=3.4.4,<3.5.0` |
+| **Default Pipeline** | `transformer`, `ner` |
+| **Components** | `transformer`, `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 (8 labels for 1 components)</summary>
+
+| Component | Labels |
+| --- | --- |
+| **`ner`** | `B-DATE`, `B-LOC`, `B-MONEY`, `B-PERS`, `I-DATE`, `I-LOC`, `I-MONEY`, `I-PERS` |
+
+</details>
+
+### Accuracy
+
+| Type | Score |
+| --- | --- |
+| `ENTS_F` | 93.19 |
+| `ENTS_P` | 93.71 |
+| `ENTS_R` | 92.68 |
+| `TRANSFORMER_LOSS` | 10410.86 |
+| `NER_LOSS` | 27922.80 |

config.cfg

@@ -0,0 +1,148 @@
+[paths]
+train = "./data/training_data_TRAIN.spacy"
+dev = "./data/training_data_DEV.spacy"
+vectors = null
+init_tok2vec = null
+
+[system]
+gpu_allocator = "pytorch"
+seed = 0
+
+[nlp]
+lang = "nl"
+pipeline = ["transformer","ner"]
+batch_size = 128
+disabled = []
+before_creation = null
+after_creation = null
+after_pipeline_creation = null
+tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
+
+[components]
+
+[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-transformers.TransformerListener.v1"
+grad_factor = 1.0
+pooling = {"@layers":"reduce_mean.v1"}
+upstream = "*"
+
+[components.transformer]
+factory = "transformer"
+max_batch_items = 4096
+set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}
+
+[components.transformer.model]
+@architectures = "spacy-transformers.TransformerModel.v3"
+name = "GroNLP/bert-base-dutch-cased"
+mixed_precision = false
+
+[components.transformer.model.get_spans]
+@span_getters = "spacy-transformers.strided_spans.v1"
+window = 128
+stride = 96
+
+[components.transformer.model.grad_scaler_config]
+
+[components.transformer.model.tokenizer_config]
+use_fast = true
+
+[components.transformer.model.transformer_config]
+
+[corpora]
+
+[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
+
+[training]
+accumulate_gradient = 3
+dev_corpus = "corpora.dev"
+train_corpus = "corpora.train"
+seed = ${system.seed}
+gpu_allocator = ${system.gpu_allocator}
+dropout = 0.1
+patience = 1600
+max_epochs = 0
+max_steps = 20000
+eval_frequency = 200
+frozen_components = []
+annotating_components = []
+before_to_disk = null
+
+[training.batcher]
+@batchers = "spacy.batch_by_padded.v1"
+discard_oversize = true
+size = 2000
+buffer = 256
+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 = false
+eps = 0.00000001
+
+[training.optimizer.learn_rate]
+@schedules = "warmup_linear.v1"
+warmup_steps = 250
+total_steps = 20000
+initial_rate = 0.00005
+
+[training.score_weights]
+ents_f = 1.0
+ents_p = 0.0
+ents_r = 0.0
+ents_per_type = null
+
+[pretraining]
+
+[initialize]
+vectors = ${paths.vectors}
+init_tok2vec = ${paths.init_tok2vec}
+vocab_data = null
+lookups = null
+before_init = null
+after_init = null
+
+[initialize.components]
+
+[initialize.components.ner]
+
+
+[initialize.tokenizer]

meta.json

@@ -0,0 +1,96 @@
+{
+  "lang":"nl",
+  "name":"middle_dutch_spacy",
+  "version":"0.0.0",
+  "description":"",
+  "author":"",
+  "email":"",
+  "url":"",
+  "license":"",
+  "spacy_version":">=3.4.4,<3.5.0",
+  "spacy_git_version":"Unknown",
+  "vectors":{
+    "width":0,
+    "vectors":0,
+    "keys":0,
+    "name":null
+  },
+  "labels":{
+    "transformer":[
+
+    ],
+    "ner":[
+      "B-DATE",
+      "B-LOC",
+      "B-MONEY",
+      "B-PERS",
+      "I-DATE",
+      "I-LOC",
+      "I-MONEY",
+      "I-PERS"
+    ]
+  },
+  "pipeline":[
+    "transformer",
+    "ner"
+  ],
+  "components":[
+    "transformer",
+    "ner"
+  ],
+  "disabled":[
+
+  ],
+  "performance":{
+    "ents_f":0.9319435929,
+    "ents_p":0.9371146732,
+    "ents_r":0.9268292683,
+    "ents_per_type":{
+      "B-LOC":{
+        "p":0.8333333333,
+        "r":0.8333333333,
+        "f":0.8333333333
+      },
+      "B-PERS":{
+        "p":0.9547511312,
+        "r":0.9173913043,
+        "f":0.9356984479
+      },
+      "I-PERS":{
+        "p":0.9431818182,
+        "r":0.8877005348,
+        "f":0.914600551
+      },
+      "I-LOC":{
+        "p":0.875,
+        "r":0.9333333333,
+        "f":0.9032258065
+      },
+      "B-MONEY":{
+        "p":0.8684210526,
+        "r":0.9166666667,
+        "f":0.8918918919
+      },
+      "I-MONEY":{
+        "p":0.9017857143,
+        "r":0.9619047619,
+        "f":0.930875576
+      },
+      "B-DATE":{
+        "p":0.9523809524,
+        "r":0.9523809524,
+        "f":0.9523809524
+      },
+      "I-DATE":{
+        "p":0.9931506849,
+        "r":1.0,
+        "f":0.9965635739
+      }
+    },
+    "transformer_loss":104.1086276464,
+    "ner_loss":279.2280184802
+  },
+  "requirements":[
+    "spacy-transformers>=1.2.0,<1.3.0"
+  ]
+}

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":{"B-PERS":1740,"I-PERS":1658,"I-DATE":1114,"I-MONEY":856,"B-LOC":634,"B-MONEY":333,"B-DATE":296,"I-LOC":100},"2":{"B-PERS":1740,"I-PERS":1658,"I-DATE":1114,"I-MONEY":856,"B-LOC":634,"B-MONEY":333,"B-DATE":296,"I-LOC":100},"3":{"B-PERS":1740,"I-PERS":1658,"I-DATE":1114,"I-MONEY":856,"B-LOC":634,"B-MONEY":333,"B-DATE":296,"I-LOC":100},"4":{"B-PERS":1740,"I-PERS":1658,"I-DATE":1114,"I-MONEY":856,"B-LOC":634,"B-MONEY":333,"B-DATE":296,"I-LOC":100,"":1},"5":{"":1}}�cfg��neg_key�

nl_middle_dutch_spacy-any-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:353d28eca4e30b329a13b8b4f516cabf87971f791b9e3eeabec7458f50cd15e1
+size 406131344

transformer/cfg

@@ -0,0 +1,3 @@
+{
+  "max_batch_items":4096
+}

transformer/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:400f16e778d441d7f62969f6fe0794833b21e9699914389a069d3665edcc48c5
+size 437590591

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"
+}