Update spaCy pipeline

.gitattributes

@@ -30,3 +30,7 @@ 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
+fr_ner4archives_v3_with_vectors-any-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+tok2vec/model filter=lfs diff=lfs merge=lfs -text
+vocab/vectors filter=lfs diff=lfs merge=lfs -text
+vocab/key2row filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,56 @@
+---
+tags:
+- spacy
+- token-classification
+language:
+- fr
+model-index:
+- name: fr_ner4archives_v3_with_vectors
+  results:
+  - task:
+      name: NER
+      type: token-classification
+    metrics:
+    - name: NER Precision
+      type: precision
+      value: 0.8829593693
+    - name: NER Recall
+      type: recall
+      value: 0.8489795918
+    - name: NER F Score
+      type: f_score
+      value: 0.8656361474
+---
+| Feature | Description |
+| --- | --- |
+| **Name** | `fr_ner4archives_v3_with_vectors` |
+| **Version** | `0.0.0` |
+| **spaCy** | `>=3.4.1,<3.5.0` |
+| **Default Pipeline** | `tok2vec`, `ner` |
+| **Components** | `tok2vec`, `ner` |
+| **Vectors** | 500000 keys, 500000 unique vectors (300 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`** | `EVENT`, `LOCATION`, `ORGANISATION`, `PERSON`, `TITLE` |
+
+</details>
+
+### Accuracy
+
+| Type | Score |
+| --- | --- |
+| `ENTS_F` | 86.56 |
+| `ENTS_P` | 88.30 |
+| `ENTS_R` | 84.90 |
+| `TOK2VEC_LOSS` | 13527.63 |
+| `NER_LOSS` | 58805.82 |

config.cfg

@@ -0,0 +1,143 @@
+[paths]
+train = "corpus/train.spacy"
+dev = "corpus/dev.spacy"
+vectors = "fr_core_news_lg"
+init_tok2vec = null
+
+[system]
+gpu_allocator = null
+seed = 0
+
+[nlp]
+lang = "fr"
+pipeline = ["tok2vec","ner"]
+batch_size = 1000
+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 = true
+nO = null
+
+[components.ner.model.tok2vec]
+@architectures = "spacy.Tok2VecListener.v1"
+width = ${components.tok2vec.model.encode.width}
+upstream = "*"
+
+[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"]
+rows = [5000,1000,2500,2500]
+include_static_vectors = true
+
+[components.tok2vec.model.encode]
+@architectures = "spacy.MaxoutWindowEncoder.v2"
+width = 256
+depth = 8
+window_size = 1
+maxout_pieces = 3
+
+[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]
+dev_corpus = "corpora.dev"
+train_corpus = "corpora.train"
+seed = ${system.seed}
+gpu_allocator = ${system.gpu_allocator}
+dropout = 0.1
+accumulate_gradient = 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_words.v1"
+discard_oversize = false
+tolerance = 0.2
+get_length = null
+
+[training.batcher.size]
+@schedules = "compounding.v1"
+start = 100
+stop = 1000
+compound = 1.001
+t = 0.0
+
+[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
+learn_rate = 0.001
+
+[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.tokenizer]

fr_ner4archives_v3_with_vectors-any-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c938618ce84a919008d17822980cfd914f9ad8f73231a64cd1ffcaa80ab09f2
+size 587683378

meta.json

@@ -0,0 +1,78 @@
+{
+  "lang":"fr",
+  "name":"ner4archives_v3_with_vectors",
+  "version":"0.0.0",
+  "description":"",
+  "author":"",
+  "email":"",
+  "url":"",
+  "license":"",
+  "spacy_version":">=3.4.1,<3.5.0",
+  "spacy_git_version":"Unknown",
+  "vectors":{
+    "width":300,
+    "vectors":500000,
+    "keys":500000,
+    "name":"fr_vectors"
+  },
+  "labels":{
+    "tok2vec":[
+
+    ],
+    "ner":[
+      "EVENT",
+      "LOCATION",
+      "ORGANISATION",
+      "PERSON",
+      "TITLE"
+    ]
+  },
+  "pipeline":[
+    "tok2vec",
+    "ner"
+  ],
+  "components":[
+    "tok2vec",
+    "ner"
+  ],
+  "disabled":[
+
+  ],
+  "performance":{
+    "ents_f":0.8656361474,
+    "ents_p":0.8829593693,
+    "ents_r":0.8489795918,
+    "ents_per_type":{
+      "PERSON":{
+        "p":0.932938856,
+        "r":0.9043977055,
+        "f":0.9184466019
+      },
+      "LOCATION":{
+        "p":0.9138576779,
+        "r":0.8714285714,
+        "f":0.8921389397
+      },
+      "ORGANISATION":{
+        "p":0.8111888112,
+        "r":0.7972508591,
+        "f":0.8041594454
+      },
+      "TITLE":{
+        "p":0.8270440252,
+        "r":0.796969697,
+        "f":0.8117283951
+      },
+      "EVENT":{
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
+      }
+    },
+    "tok2vec_loss":135.2763410674,
+    "ner_loss":588.0582341063
+  },
+  "requirements":[
+
+  ]
+}

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�
X{"0":{},"1":{"PERSON":3649,"LOCATION":3166,"TITLE":2698,"ORGANISATION":2352,"EVENT":81},"2":{"PERSON":3649,"LOCATION":3166,"TITLE":2698,"ORGANISATION":2352,"EVENT":81},"3":{"PERSON":3649,"LOCATION":3166,"TITLE":2698,"ORGANISATION":2352,"EVENT":81},"4":{"PERSON":3649,"LOCATION":3166,"TITLE":2698,"ORGANISATION":2352,"EVENT":81,"":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 sha256:08c81c17d3ab25e37394dd25f6e8b7b88366988db264e40748c10c310b6cf608
+size 34434008

vocab/key2row

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d310125304022a2ff941d0224a09dc113048bc06a6d2bc1d551a163cb789c85c
+size 6868181

vocab/lookups.bin

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

vocab/vectors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:055541ce7b97e6d7bc98e75678cf1e58c71c962c1e77ebc674b7247e3ffb75b8
+size 600000128

vocab/vectors.cfg

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