Update spaCy pipeline

README.md

@@ -13,22 +13,22 @@ model-index:
     metrics:
     - name: NER Precision
       type: precision
-      value: 0.9877300613
+      value: 0.9848121503
     - name: NER Recall
       type: recall
-      value: 0.9962871287
+      value: 0.9828480255
     - name: NER F Score
       type: f_score
-      value: 0.9919901417
+      value: 0.9838291076
 ---
 | Feature | Description |
 | --- | --- |
 | **Name** | `en_pipeline` |
 | **Version** | `0.0.0` |
 | **spaCy** | `>=3.7.5,<3.8.0` |
-| **Default Pipeline** | `transformer`, `ner` |
-| **Components** | `transformer`, `ner` |
-| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
+| **Default Pipeline** | `tok2vec`, `ner` |
+| **Components** | `tok2vec`, `ner` |
+| **Vectors** | 514157 keys, 514157 unique vectors (300 dimensions) |
 | **Sources** | n/a |
 | **License** | n/a |
 | **Author** | [n/a]() |
@@ -37,11 +37,11 @@ model-index:
 
 <details>
 
-<summary>View label scheme (10 labels for 1 components)</summary>
+<summary>View label scheme (26 labels for 1 components)</summary>
 
 | Component | Labels |
 | --- | --- |
-| **`ner`** | `CHEMICAL TERM`, `DECIMAL`, `FRACTION`, `LEADING ZERO`, `NUMBER`, `OPERATOR`, `RATIO`, `SI UNIT `, `THOUSANDS OPERATOR`, `TIME UNIT` |
+| **`ner`** | `ANGLE`, `CHEMICAL TERM`, `COUNTABLE`, `DECIMAL`, `EQU`, `EQUATION CITATION`, `FIGURE CITATION`, `FRACTION`, `GREEK VARIABLE`, `LEADING ZERO`, `NAMEDATE REF. CITATION`, `NUMBER`, `OPERATOR`, `ORDINAL`, `ORIENTATION`, `PERCENTAGE`, `RANGE`, `RATIO`, `ROMAN NUMBER`, `SI UNIT`, `SI UNIT `, `TABLE CITATION`, `THOUSANDS OPERATOR`, `THOUSANDS SEPARATOR`, `TIME UNIT`, `YEAR` |
 
 </details>
 
@@ -49,8 +49,8 @@ model-index:
 
 | Type | Score |
 | --- | --- |
-| `ENTS_F` | 99.20 |
-| `ENTS_P` | 98.77 |
-| `ENTS_R` | 99.63 |
-| `TRANSFORMER_LOSS` | 36683.04 |
-| `NER_LOSS` | 35818.80 |
+| `ENTS_F` | 98.38 |
+| `ENTS_P` | 98.48 |
+| `ENTS_R` | 98.28 |
+| `TOK2VEC_LOSS` | 34785.41 |
+| `NER_LOSS` | 84008.34 |

config.cfg

@@ -1,147 +1,145 @@
-[paths]
-train = "/content/drive/MyDrive/secmodel/train3.spacy"
-dev = "/content/drive/MyDrive/secmodel/train3.spacy"
-vectors = null
-init_tok2vec = null
-
-[system]
-gpu_allocator = "pytorch"
-seed = 0
-
-[nlp]
-lang = "en"
-pipeline = ["transformer","ner"]
-batch_size = 128
-disabled = []
-before_creation = null
-after_creation = null
-after_pipeline_creation = null
-tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
-vectors = {"@vectors":"spacy.Vectors.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 = "roberta-base"
-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
-before_update = 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]
-
+[paths]
+train = "model2k/train3.spacy"
+dev = "model2k/train3.spacy"
+vectors = "en_core_web_lg"
+init_tok2vec = null
+
+[system]
+gpu_allocator = null
+seed = 0
+
+[nlp]
+lang = "en"
+pipeline = ["tok2vec","ner"]
+batch_size = 1000
+disabled = []
+before_creation = null
+after_creation = null
+after_pipeline_creation = null
+tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
+vectors = {"@vectors":"spacy.Vectors.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
+before_update = 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]

en_pipeline-any-py3-none-any.whl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13f2aa9ee41c224f5308d0df8762fdfed2cdc0459bb78234277e721b764001e3
-size 425416363
+oid sha256:31590afe1ece15b8b726392f08ff4bde8a21e2f52559bdfc76faea25c5550b4d
+size 606850384

meta.json

@@ -10,53 +10,69 @@
   "spacy_version":">=3.7.5,<3.8.0",
   "spacy_git_version":"a6d0fc360",
   "vectors":{
-    "width":0,
-    "vectors":0,
-    "keys":0,
-    "name":null
+    "width":300,
+    "vectors":514157,
+    "keys":514157,
+    "name":"en_vectors"
   },
   "labels":{
-    "transformer":[
+    "tok2vec":[
 
     ],
     "ner":[
+      "ANGLE",
       "CHEMICAL TERM",
+      "COUNTABLE",
       "DECIMAL",
+      "EQU",
+      "EQUATION CITATION",
+      "FIGURE CITATION",
       "FRACTION",
+      "GREEK VARIABLE",
       "LEADING ZERO",
+      "NAMEDATE REF. CITATION",
       "NUMBER",
       "OPERATOR",
+      "ORDINAL",
+      "ORIENTATION",
+      "PERCENTAGE",
+      "RANGE",
       "RATIO",
+      "ROMAN NUMBER",
+      "SI UNIT",
       "SI UNIT ",
+      "TABLE CITATION",
       "THOUSANDS OPERATOR",
-      "TIME UNIT"
+      "THOUSANDS SEPARATOR",
+      "TIME UNIT",
+      "YEAR"
     ]
   },
   "pipeline":[
-    "transformer",
+    "tok2vec",
     "ner"
   ],
   "components":[
-    "transformer",
+    "tok2vec",
     "ner"
   ],
   "disabled":[
 
   ],
   "performance":{
-    "ents_f":0.9919901417,
-    "ents_p":0.9877300613,
-    "ents_r":0.9962871287,
+    "ents_f":0.9838291076,
+    "ents_p":0.9848121503,
+    "ents_r":0.9828480255,
     "ents_per_type":{
       "SI UNIT ":{
-        "p":0.9841584158,
-        "r":0.994,
-        "f":0.9890547264
+        "p":0.9837398374,
+        "r":0.968,
+        "f":0.9758064516
       },
       "TIME UNIT":{
-        "p":1.0,
+        "p":0.9897610922,
         "r":1.0,
-        "f":1.0
+        "f":0.9948542024
       },
       "NUMBER":{
         "p":1.0,
@@ -70,8 +86,8 @@
       },
       "OPERATOR":{
         "p":1.0,
-        "r":1.0,
-        "f":1.0
+        "r":0.9090909091,
+        "f":0.9523809524
       },
       "FRACTION":{
         "p":1.0,
@@ -79,30 +95,110 @@
         "f":1.0
       },
       "CHEMICAL TERM":{
-        "p":0.9814814815,
-        "r":1.0,
-        "f":0.9906542056
+        "p":0.9649122807,
+        "r":0.9821428571,
+        "f":0.9734513274
       },
       "DECIMAL":{
-        "p":0.6666666667,
-        "r":1.0,
-        "f":0.8
+        "p":1.0,
+        "r":0.9333333333,
+        "f":0.9655172414
       },
       "LEADING ZERO":{
+        "p":1.0,
+        "r":0.9310344828,
+        "f":0.9642857143
+      },
+      "RATIO":{
         "p":1.0,
         "r":1.0,
         "f":1.0
       },
-      "RATIO":{
+      "SI UNIT":{
+        "p":0.9716646989,
+        "r":0.9762752076,
+        "f":0.973964497
+      },
+      "THOUSANDS SEPARATOR":{
+        "p":1.0,
+        "r":0.9803921569,
+        "f":0.9900990099
+      },
+      "COUNTABLE":{
+        "p":1.0,
+        "r":1.0,
+        "f":1.0
+      },
+      "RANGE":{
+        "p":1.0,
+        "r":1.0,
+        "f":1.0
+      },
+      "ORDINAL":{
+        "p":1.0,
+        "r":1.0,
+        "f":1.0
+      },
+      "ANGLE":{
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
+      },
+      "EQUATION CITATION":{
+        "p":1.0,
+        "r":1.0,
+        "f":1.0
+      },
+      "NAMEDATE REF. CITATION":{
+        "p":1.0,
+        "r":1.0,
+        "f":1.0
+      },
+      "TABLE CITATION":{
+        "p":1.0,
+        "r":1.0,
+        "f":1.0
+      },
+      "FIGURE CITATION":{
+        "p":1.0,
+        "r":1.0,
+        "f":1.0
+      },
+      "YEAR":{
+        "p":1.0,
+        "r":1.0,
+        "f":1.0
+      },
+      "GREEK VARIABLE":{
+        "p":0.9910714286,
+        "r":1.0,
+        "f":0.9955156951
+      },
+      "EQU":{
+        "p":1.0,
+        "r":1.0,
+        "f":1.0
+      },
+      "PERCENTAGE":{
+        "p":1.0,
+        "r":1.0,
+        "f":1.0
+      },
+      "ORIENTATION":{
+        "p":1.0,
+        "r":1.0,
+        "f":1.0
+      },
+      "ROMAN NUMBER":{
         "p":1.0,
         "r":1.0,
         "f":1.0
       }
     },
-    "transformer_loss":366.8304179548,
-    "ner_loss":358.1879557502
+    "tok2vec_loss":347.8540632287,
+    "ner_loss":840.0833996674
   },
   "requirements":[
-    "spacy-transformers>=1.3.5,<1.4.0"
+
   ]
 }

ner/cfg

@@ -1,13 +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
+{
+  "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

@@ -1 +1 @@
-��moves��{"0":{},"1":{"SI UNIT ":1069,"TIME UNIT":447,"CHEMICAL TERM":72,"LEADING ZERO":6,"RATIO":5,"OPERATOR":5,"NUMBER":3,"FRACTION":3,"DECIMAL":2,"THOUSANDS OPERATOR":1},"2":{"SI UNIT ":1069,"TIME UNIT":447,"CHEMICAL TERM":72,"LEADING ZERO":6,"RATIO":5,"OPERATOR":5,"NUMBER":3,"FRACTION":3,"DECIMAL":2,"THOUSANDS OPERATOR":1},"3":{"SI UNIT ":1069,"TIME UNIT":447,"CHEMICAL TERM":72,"LEADING ZERO":6,"RATIO":5,"OPERATOR":5,"NUMBER":3,"FRACTION":3,"DECIMAL":2,"THOUSANDS OPERATOR":1},"4":{"SI UNIT ":1069,"TIME UNIT":447,"CHEMICAL TERM":72,"LEADING ZERO":6,"RATIO":5,"OPERATOR":5,"NUMBER":3,"FRACTION":3,"DECIMAL":2,"THOUSANDS OPERATOR":1,"":1},"5":{"":1}}�cfg��neg_key�
+��moves��{"0":{},"1":{"SI UNIT":1861,"SI UNIT ":1069,"EQUATION CITATION":780,"TIME UNIT":515,"ORIENTATION":150,"PERCENTAGE":147,"NAMEDATE REF. CITATION":119,"ORDINAL":115,"GREEK VARIABLE":111,"CHEMICAL TERM":75,"THOUSANDS SEPARATOR":51,"FIGURE CITATION":35,"NUMBER":31,"COUNTABLE":30,"LEADING ZERO":29,"TABLE CITATION":26,"ROMAN NUMBER":25,"YEAR":23,"DECIMAL":15,"RANGE":13,"OPERATOR":11,"RATIO":5,"FRACTION":3,"THOUSANDS OPERATOR":1,"EQU":1,"ANGLE":1},"2":{"SI UNIT":1861,"SI UNIT ":1069,"EQUATION CITATION":780,"TIME UNIT":515,"ORIENTATION":150,"PERCENTAGE":147,"NAMEDATE REF. CITATION":119,"ORDINAL":115,"GREEK VARIABLE":111,"CHEMICAL TERM":75,"THOUSANDS SEPARATOR":51,"FIGURE CITATION":35,"NUMBER":31,"COUNTABLE":30,"LEADING ZERO":29,"TABLE CITATION":26,"ROMAN NUMBER":25,"YEAR":23,"DECIMAL":15,"RANGE":13,"OPERATOR":11,"RATIO":5,"FRACTION":3,"THOUSANDS OPERATOR":1,"EQU":1,"ANGLE":1},"3":{"SI UNIT":1861,"SI UNIT ":1069,"EQUATION CITATION":780,"TIME UNIT":515,"ORIENTATION":150,"PERCENTAGE":147,"NAMEDATE REF. CITATION":119,"ORDINAL":115,"GREEK VARIABLE":111,"CHEMICAL TERM":75,"THOUSANDS SEPARATOR":51,"FIGURE CITATION":35,"NUMBER":31,"COUNTABLE":30,"LEADING ZERO":29,"TABLE CITATION":26,"ROMAN NUMBER":25,"YEAR":23,"DECIMAL":15,"RANGE":13,"OPERATOR":11,"RATIO":5,"FRACTION":3,"THOUSANDS OPERATOR":1,"EQU":1,"ANGLE":1},"4":{"SI UNIT":1861,"SI UNIT ":1069,"EQUATION CITATION":780,"TIME UNIT":515,"ORIENTATION":150,"PERCENTAGE":147,"NAMEDATE REF. CITATION":119,"ORDINAL":115,"GREEK VARIABLE":111,"CHEMICAL TERM":75,"THOUSANDS SEPARATOR":51,"FIGURE CITATION":35,"NUMBER":31,"COUNTABLE":30,"LEADING ZERO":29,"TABLE CITATION":26,"ROMAN NUMBER":25,"YEAR":23,"DECIMAL":15,"RANGE":13,"OPERATOR":11,"RATIO":5,"FRACTION":3,"THOUSANDS OPERATOR":1,"EQU":1,"ANGLE":1,"":1},"5":{"":1}}�cfg��neg_key�

tok2vec/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f436ab3fe63a7935643dc2890ec798a590ef1ed217ff377666230aed918e0412
+oid sha256:fffb638be4ef5565810b996e88f2f7fb0582f1bd67e306746d25c422f21c7eaf
 size 34434008

vocab/key2row

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76be8b528d0075f7aae98d6fa57a6d3c83ae480a8469e668d7b0af968995ac71
-size 1
+oid sha256:31566ae010da3d399eb1d930ae142757afd2601034a4be3bdb00d18881c8c06a
+size 7066303

vocab/strings.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:282296599e3b7dbbc1cdb0dcb849aff92eb335406e2e31493bd5ffced559408d
-size 25769
+oid sha256:9936f701b77503da8c75cc4c1603912acf11cd6bdfad048e3e566fee88a37c80
+size 11153853

vocab/vectors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14772b683e726436d5948ad3fff2b43d036ef2ebbe3458aafed6004e05a40706
-size 128
+oid sha256:234dcf234bfdf01775ae6182715d55eaacfcde8555b189f25440b56d3c39fd5d
+size 616988528

vocab/vectors.cfg

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