Update spaCy pipeline

.gitattributes

@@ -36,3 +36,5 @@ en_ner_sender_recipient-any-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
 ner/model filter=lfs diff=lfs merge=lfs -text
 vocab/strings.json 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

@@ -13,57 +13,22 @@ model-index:
     metrics:
     - name: NER Precision
       type: precision
-      value: 0.0
+      value: 0.3507720105
     - name: NER Recall
       type: recall
-      value: 0.0
+      value: 0.1265969114
     - name: NER F Score
       type: f_score
-      value: 0.0
-  - task:
-      name: TAG
-      type: token-classification
-    metrics:
-    - name: TAG (XPOS) Accuracy
-      type: accuracy
-      value: 0.0
-  - task:
-      name: LEMMA
-      type: token-classification
-    metrics:
-    - name: Lemma Accuracy
-      type: accuracy
-      value: 0.0
-  - task:
-      name: UNLABELED_DEPENDENCIES
-      type: token-classification
-    metrics:
-    - name: Unlabeled Attachment Score (UAS)
-      type: f_score
-      value: 0.0
-  - task:
-      name: LABELED_DEPENDENCIES
-      type: token-classification
-    metrics:
-    - name: Labeled Attachment Score (LAS)
-      type: f_score
-      value: 0.0
-  - task:
-      name: SENTS
-      type: token-classification
-    metrics:
-    - name: Sentences F-Score
-      type: f_score
-      value: 0.0
+      value: 0.1860475247
 ---
 | Feature | Description |
 | --- | --- |
 | **Name** | `en_ner_sender_recipient` |
-| **Version** | `0.0.0` |
+| **Version** | `0.0.2` |
 | **spaCy** | `>=3.4.3,<3.5.0` |
-| **Default Pipeline** | `tok2vec`, `tagger`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
-| **Components** | `tok2vec`, `tagger`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner` |
-| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
+| **Default Pipeline** | `tok2vec`, `ner` |
+| **Components** | `tok2vec`, `ner` |
+| **Vectors** | 514157 keys, 20000 unique vectors (300 dimensions) |
 | **Sources** | n/a |
 | **License** | n/a |
 | **Author** | [n/a]() |
@@ -72,13 +37,11 @@ model-index:
 
 <details>
 
-<summary>View label scheme (115 labels for 3 components)</summary>
+<summary>View label scheme (2 labels for 1 components)</summary>
 
 | Component | Labels |
 | --- | --- |
-| **`tagger`** | `$`, `''`, `,`, `-LRB-`, `-RRB-`, `.`, `:`, `ADD`, `AFX`, `CC`, `CD`, `DT`, `EX`, `FW`, `HYPH`, `IN`, `JJ`, `JJR`, `JJS`, `LS`, `MD`, `NFP`, `NN`, `NNP`, `NNPS`, `NNS`, `PDT`, `POS`, `PRP`, `PRP$`, `RB`, `RBR`, `RBS`, `RP`, `SYM`, `TO`, `UH`, `VB`, `VBD`, `VBG`, `VBN`, `VBP`, `VBZ`, `WDT`, `WP`, `WP$`, `WRB`, `XX`, `_SP`, ```` |
-| **`parser`** | `ROOT`, `acl`, `acomp`, `advcl`, `advmod`, `agent`, `amod`, `appos`, `attr`, `aux`, `auxpass`, `case`, `cc`, `ccomp`, `compound`, `conj`, `csubj`, `csubjpass`, `dative`, `dep`, `det`, `dobj`, `expl`, `intj`, `mark`, `meta`, `neg`, `nmod`, `npadvmod`, `nsubj`, `nsubjpass`, `nummod`, `oprd`, `parataxis`, `pcomp`, `pobj`, `poss`, `preconj`, `predet`, `prep`, `prt`, `punct`, `quantmod`, `relcl`, `xcomp` |
-| **`ner`** | `CARDINAL`, `DATE`, `EVENT`, `FAC`, `GPE`, `LANGUAGE`, `LAW`, `LOC`, `MONEY`, `NORP`, `ORDINAL`, `ORG`, `PERCENT`, `PERSON`, `PRODUCT`, `QUANTITY`, `RECIPIENT`, `SENDER`, `TIME`, `WORK_OF_ART` |
+| **`ner`** | `RECIPIENT`, `SENDER` |
 
 </details>
 
@@ -86,15 +49,8 @@ model-index:
 
 | Type | Score |
 | --- | --- |
-| `TAG_ACC` | 0.00 |
-| `DEP_UAS` | 0.00 |
-| `DEP_LAS` | 0.00 |
-| `DEP_LAS_PER_TYPE` | 0.00 |
-| `SENTS_P` | 0.00 |
-| `SENTS_R` | 0.00 |
-| `SENTS_F` | 0.00 |
-| `LEMMA_ACC` | 0.00 |
-| `ENTS_F` | 0.00 |
-| `ENTS_P` | 0.00 |
-| `ENTS_R` | 0.00 |
-| `NER_LOSS` | 6283.03 |
+| `ENTS_F` | 18.60 |
+| `ENTS_P` | 35.08 |
+| `ENTS_R` | 12.66 |
+| `TOK2VEC_LOSS` | 385.52 |
+| `NER_LOSS` | 4421.31 |

config.cfg

@@ -10,28 +10,16 @@ seed = 0
 
 [nlp]
 lang = "en"
-pipeline = ["tok2vec","tagger","parser","senter","attribute_ruler","lemmatizer","ner"]
-disabled = ["senter"]
+pipeline = ["tok2vec","ner"]
+batch_size = 1000
+disabled = []
 before_creation = null
 after_creation = null
 after_pipeline_creation = null
-batch_size = 256
 tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
 
 [components]
 
-[components.attribute_ruler]
-factory = "attribute_ruler"
-scorer = {"@scorers":"spacy.attribute_ruler_scorer.v1"}
-validate = false
-
-[components.lemmatizer]
-factory = "lemmatizer"
-mode = "rule"
-model = null
-overwrite = false
-scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
-
 [components.ner]
 factory = "ner"
 incorrect_spans_key = null
@@ -49,86 +37,9 @@ use_upper = true
 nO = null
 
 [components.ner.model.tok2vec]
-@architectures = "spacy.Tok2Vec.v2"
-
-[components.ner.model.tok2vec.embed]
-@architectures = "spacy.MultiHashEmbed.v2"
-width = 96
-attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
-rows = [5000,1000,2500,2500,50]
-include_static_vectors = false
-
-[components.ner.model.tok2vec.encode]
-@architectures = "spacy.MaxoutWindowEncoder.v2"
-width = 96
-depth = 4
-window_size = 1
-maxout_pieces = 3
-
-[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 = true
-nO = null
-
-[components.parser.model.tok2vec]
-@architectures = "spacy.Tok2VecListener.v1"
-width = 96
-upstream = "tok2vec"
-
-[components.senter]
-factory = "senter"
-overwrite = false
-scorer = {"@scorers":"spacy.senter_scorer.v1"}
-
-[components.senter.model]
-@architectures = "spacy.Tagger.v2"
-nO = null
-normalize = false
-
-[components.senter.model.tok2vec]
-@architectures = "spacy.Tok2Vec.v2"
-
-[components.senter.model.tok2vec.embed]
-@architectures = "spacy.MultiHashEmbed.v2"
-width = 16
-attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
-rows = [1000,500,500,500,50]
-include_static_vectors = false
-
-[components.senter.model.tok2vec.encode]
-@architectures = "spacy.MaxoutWindowEncoder.v2"
-width = 16
-depth = 2
-window_size = 1
-maxout_pieces = 2
-
-[components.tagger]
-factory = "tagger"
-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.Tok2VecListener.v1"
-width = 96
-upstream = "tok2vec"
+width = ${components.tok2vec.model.encode.width}
+upstream = "*"
 
 [components.tok2vec]
 factory = "tok2vec"
@@ -138,10 +49,10 @@ factory = "tok2vec"
 
 [components.tok2vec.model.embed]
 @architectures = "spacy.MultiHashEmbed.v2"
-width = 96
-attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
-rows = [5000,1000,2500,2500,50]
-include_static_vectors = false
+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"
@@ -155,33 +66,33 @@ maxout_pieces = 3
 [corpora.dev]
 @readers = "spacy.Corpus.v1"
 path = ${paths.dev}
-gold_preproc = false
 max_length = 0
+gold_preproc = false
 limit = 0
 augmenter = null
 
 [corpora.train]
 @readers = "spacy.Corpus.v1"
 path = ${paths.train}
-gold_preproc = false
 max_length = 0
+gold_preproc = false
 limit = 0
 augmenter = null
 
 [training]
-train_corpus = "corpora.train"
 dev_corpus = "corpora.dev"
-seed = ${system:seed}
-gpu_allocator = ${system:gpu_allocator}
+train_corpus = "corpora.train"
+seed = ${system.seed}
+gpu_allocator = ${system.gpu_allocator}
 dropout = 0.1
 accumulate_gradient = 1
 patience = 50
 max_epochs = 5
-max_steps = 500
+max_steps = 20000
 eval_frequency = 10
-frozen_components = ["tok2vec","tagger","parser","senter","attribute_ruler","lemmatizer"]
-before_to_disk = null
+frozen_components = []
 annotating_components = []
+before_to_disk = null
 
 [training.batcher]
 @batchers = "spacy.batch_by_words.v1"
@@ -207,60 +118,26 @@ beta2 = 0.999
 L2_is_weight_decay = true
 L2 = 0.01
 grad_clip = 1.0
-use_averages = true
+use_averages = false
 eps = 0.00000001
 learn_rate = 0.001
 
 [training.score_weights]
-tag_acc = 0.16
-dep_uas = 0.0
-dep_las = 0.16
-dep_las_per_type = null
-sents_p = null
-sents_r = null
-sents_f = 0.02
-lemma_acc = 0.5
-ents_f = 0.16
+ents_f = 1.0
 ents_p = 0.0
 ents_r = 0.0
 ents_per_type = null
-speed = 0.0
 
 [pretraining]
 
 [initialize]
-vocab_data = null
-vectors = null
+vectors = "en_core_web_md"
 init_tok2vec = ${paths.init_tok2vec}
-after_init = null
+vocab_data = null
 lookups = null
-
-[initialize.before_init]
-@callbacks = "spacy.copy_from_base_model.v1"
-tokenizer = "en_core_web_sm"
-vocab = "en_core_web_sm"
+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.tokenizer]

en_ner_sender_recipient-any-py3-none-any.whl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90dadf3d30fbb68e3d7bfce5d5b81fa039637f757f475dc18544df9f3dd6cd98
-size 15534931
+oid sha256:a95a8763493801e6c81c97433f4fb57bad661391dcbb62c35cc56e750978290b
+size 38187757

meta.json

@@ -1,7 +1,7 @@
 {
   "lang":"en",
   "name":"ner_sender_recipient",
-  "version":"0.0.0",
+  "version":"0.0.2",
   "description":"",
   "author":"",
   "email":"",
@@ -10,204 +10,49 @@
   "spacy_version":">=3.4.3,<3.5.0",
   "spacy_git_version":"63673a792",
   "vectors":{
-    "width":0,
-    "vectors":0,
-    "keys":0,
-    "name":null
+    "width":300,
+    "vectors":20000,
+    "keys":514157,
+    "name":"en_vectors"
   },
   "labels":{
     "tok2vec":[
 
-    ],
-    "tagger":[
-      "$",
-      "''",
-      ",",
-      "-LRB-",
-      "-RRB-",
-      ".",
-      ":",
-      "ADD",
-      "AFX",
-      "CC",
-      "CD",
-      "DT",
-      "EX",
-      "FW",
-      "HYPH",
-      "IN",
-      "JJ",
-      "JJR",
-      "JJS",
-      "LS",
-      "MD",
-      "NFP",
-      "NN",
-      "NNP",
-      "NNPS",
-      "NNS",
-      "PDT",
-      "POS",
-      "PRP",
-      "PRP$",
-      "RB",
-      "RBR",
-      "RBS",
-      "RP",
-      "SYM",
-      "TO",
-      "UH",
-      "VB",
-      "VBD",
-      "VBG",
-      "VBN",
-      "VBP",
-      "VBZ",
-      "WDT",
-      "WP",
-      "WP$",
-      "WRB",
-      "XX",
-      "_SP",
-      "``"
-    ],
-    "parser":[
-      "ROOT",
-      "acl",
-      "acomp",
-      "advcl",
-      "advmod",
-      "agent",
-      "amod",
-      "appos",
-      "attr",
-      "aux",
-      "auxpass",
-      "case",
-      "cc",
-      "ccomp",
-      "compound",
-      "conj",
-      "csubj",
-      "csubjpass",
-      "dative",
-      "dep",
-      "det",
-      "dobj",
-      "expl",
-      "intj",
-      "mark",
-      "meta",
-      "neg",
-      "nmod",
-      "npadvmod",
-      "nsubj",
-      "nsubjpass",
-      "nummod",
-      "oprd",
-      "parataxis",
-      "pcomp",
-      "pobj",
-      "poss",
-      "preconj",
-      "predet",
-      "prep",
-      "prt",
-      "punct",
-      "quantmod",
-      "relcl",
-      "xcomp"
-    ],
-    "attribute_ruler":[
-
-    ],
-    "lemmatizer":[
-
     ],
     "ner":[
-      "CARDINAL",
-      "DATE",
-      "EVENT",
-      "FAC",
-      "GPE",
-      "LANGUAGE",
-      "LAW",
-      "LOC",
-      "MONEY",
-      "NORP",
-      "ORDINAL",
-      "ORG",
-      "PERCENT",
-      "PERSON",
-      "PRODUCT",
-      "QUANTITY",
       "RECIPIENT",
-      "SENDER",
-      "TIME",
-      "WORK_OF_ART"
+      "SENDER"
     ]
   },
   "pipeline":[
     "tok2vec",
-    "tagger",
-    "parser",
-    "attribute_ruler",
-    "lemmatizer",
     "ner"
   ],
   "components":[
     "tok2vec",
-    "tagger",
-    "parser",
-    "senter",
-    "attribute_ruler",
-    "lemmatizer",
     "ner"
   ],
   "disabled":[
-    "senter"
+
   ],
   "performance":{
-    "tag_acc":0.0,
-    "dep_uas":0.0,
-    "dep_las":0.0,
-    "dep_las_per_type":0.0,
-    "sents_p":0.0,
-    "sents_r":0.0,
-    "sents_f":0.0,
-    "lemma_acc":0.0,
-    "ents_f":0.0,
-    "ents_p":0.0,
-    "ents_r":0.0,
+    "ents_f":0.1860475247,
+    "ents_p":0.3507720105,
+    "ents_r":0.1265969114,
     "ents_per_type":{
-      "RECIPIENT":{
-        "p":0.0,
-        "r":0.0,
-        "f":0.0
-      },
       "SENDER":{
-        "p":0.0,
-        "r":0.0,
-        "f":0.0
+        "p":0.4055570488,
+        "r":0.194699829,
+        "f":0.2630936553
       },
-      "ORG":{
-        "p":0.0,
-        "r":0.0,
-        "f":0.0
-      },
-      "NORP":{
-        "p":0.0,
-        "r":0.0,
-        "f":0.0
-      },
-      "PERSON":{
-        "p":0.0,
-        "r":0.0,
-        "f":0.0
+      "RECIPIENT":{
+        "p":0.1096984033,
+        "r":0.0189222962,
+        "f":0.0322770081
       }
     },
-    "speed":9876.0524883954,
-    "ner_loss":62.8303238856
+    "tok2vec_loss":3.855186481,
+    "ner_loss":44.2130982176
   },
   "requirements":[
 

ner/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5987be4099c23fe78b21ee2c8f7e265edb93859481e86f0ca768da5d844dcd5
-size 6286843
+oid sha256:189a45e7d5d37055e7799b3db371a7cf9741c89f81d968bcc6e08ed311739000
+size 128548

ner/moves

@@ -1 +1 @@
-��moves�|{"0":{},"1":{"ORG":56516,"DATE":40493,"PERSON":36534,"GPE":26745,"MONEY":15158,"CARDINAL":14109,"NORP":9641,"PERCENT":9199,"WORK_OF_ART":4488,"LOC":4055,"TIME":3678,"QUANTITY":3123,"FAC":3046,"EVENT":3021,"ORDINAL":2142,"PRODUCT":1787,"LAW":1624,"LANGUAGE":355,"RECIPIENT":-1,"SENDER":-2},"2":{"ORG":56516,"DATE":40493,"PERSON":36534,"GPE":26745,"MONEY":15158,"CARDINAL":14109,"NORP":9641,"PERCENT":9199,"WORK_OF_ART":4488,"LOC":4055,"TIME":3678,"QUANTITY":3123,"FAC":3046,"EVENT":3021,"ORDINAL":2142,"PRODUCT":1787,"LAW":1624,"LANGUAGE":355,"RECIPIENT":-1,"SENDER":-2},"3":{"ORG":56516,"DATE":40493,"PERSON":36534,"GPE":26745,"MONEY":15158,"CARDINAL":14109,"NORP":9641,"PERCENT":9199,"WORK_OF_ART":4488,"LOC":4055,"TIME":3678,"QUANTITY":3123,"FAC":3046,"EVENT":3021,"ORDINAL":2142,"PRODUCT":1787,"LAW":1624,"LANGUAGE":355,"RECIPIENT":-1,"SENDER":-2},"4":{"ORG":56516,"DATE":40493,"PERSON":36534,"GPE":26745,"MONEY":15158,"CARDINAL":14109,"NORP":9641,"PERCENT":9199,"WORK_OF_ART":4488,"LOC":4055,"TIME":3678,"QUANTITY":3123,"FAC":3046,"EVENT":3021,"ORDINAL":2142,"PRODUCT":1787,"LAW":1624,"LANGUAGE":355,"":1,"RECIPIENT":-1,"SENDER":-2},"5":{"":1}}�cfg��neg_key�
+��movesټ{"0":{},"1":{"SENDER":719197,"RECIPIENT":449266},"2":{"SENDER":719197,"RECIPIENT":449266},"3":{"SENDER":719197,"RECIPIENT":449266},"4":{"SENDER":719197,"RECIPIENT":449266,"":1},"5":{"":1}}�cfg��neg_key�

tok2vec/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6967e88ec7b0680d94a75500c46fe19a1b1e01ef5f608a58826077e45af5010d
-size 6139229
+oid sha256:11003ef7119f40f6ef584d13cd6dc24bc311765500065005548ff53b21e6df96
+size 6235418

vocab/key2row

@@ -1 +1,3 @@
-�
+version https://git-lfs.github.com/spec/v1
+oid sha256:389912f67e81a52fbabb7edf8e36a0c3700b0b20d6dc6ef71bd56eb91ba08a0a
+size 6165224

vocab/lookups.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ddd140ecac6a8c4592e9146d6e30074569ffaed97ee51edc9587dc510f8934c
-size 69982
+oid sha256:76be8b528d0075f7aae98d6fa57a6d3c83ae480a8469e668d7b0af968995ac71
+size 1

vocab/strings.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecc9a63592bc3e2226ee4def1e7d75dfd682fbacecfa93c920a4369f209e87cd
-size 11474263
+oid sha256:91d19e8896925d0f3afce0c586d5ca5e796db05fbf8092fc4389c090752dc930
+size 19785939