Update spaCy pipeline

README.md

@@ -14,25 +14,25 @@ model-index:
     metrics:
     - name: NER Precision
       type: precision
-      value: 0.5991309071
+      value: 0.5919354839
     - name: NER Recall
       type: recall
-      value: 0.5768828452
+      value: 0.5758368201
     - name: NER F Score
       type: f_score
-      value: 0.5877964295
+      value: 0.5837751856
 ---
 A Named Entity Recognition (NER) model to extract SKILL, EXPERIENCE and BENEFIT from job adverts.
 
 | Feature | Description |
 | --- | --- |
 | **Name** | `en_skillner` |
-| **Version** | `3.5.0` |
-| **spaCy** | `>=3.5.3,<3.6.0` |
+| **Version** | `3.7.1` |
+| **spaCy** | `>=3.7.4,<3.8.0` |
 | **Default Pipeline** | `tok2vec`, `tagger`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
 | **Components** | `tok2vec`, `tagger`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner` |
 | **Vectors** | 514157 keys, 514157 unique vectors (300 dimensions) |
-| **Sources** | [OntoNotes 5](https://catalog.ldc.upenn.edu/LDC2013T19) (Ralph Weischedel, Martha Palmer, Mitchell Marcus, Eduard Hovy, Sameer Pradhan, Lance Ramshaw, Nianwen Xue, Ann Taylor, Jeff Kaufman, Michelle Franchini, Mohammed El-Bachouti, Robert Belvin, Ann Houston)<br />[ClearNLP Constituent-to-Dependency Conversion](https://github.com/clir/clearnlp-guidelines/blob/master/md/components/dependency_conversion.md) (Emory University)<br />[WordNet 3.0](https://wordnet.princeton.edu/) (Princeton University)<br />[Explosion Vectors (OSCAR 2109 + Wikipedia + OpenSubtitles + WMT News Crawl)](https://github.com/explosion/spacy-vectors-builder) (Explosion) |
+| **Sources** | [OntoNotes 5](https://catalog.ldc.upenn.edu/LDC2013T19) (Ralph Weischedel, Martha Palmer, Mitchell Marcus, Eduard Hovy, Sameer Pradhan, Lance Ramshaw, Nianwen Xue, Ann Taylor, Jeff Kaufman, Michelle Franchini, Mohammed El-Bachouti, Robert Belvin, Ann Houston)<br>[ClearNLP Constituent-to-Dependency Conversion](https://github.com/clir/clearnlp-guidelines/blob/master/md/components/dependency_conversion.md) (Emory University)<br>[WordNet 3.0](https://wordnet.princeton.edu/) (Princeton University)<br>[Explosion Vectors (OSCAR 2109 + Wikipedia + OpenSubtitles + WMT News Crawl)](https://github.com/explosion/spacy-vectors-builder) (Explosion) |
 | **License** | `MIT` |
 | **Author** | [nestauk](https://explosion.ai) |
 
@@ -52,15 +52,15 @@ A Named Entity Recognition (NER) model to extract SKILL, EXPERIENCE and BENEFIT
 
 | Type | Score |
 | --- | --- |
-| `ENTS_P` | 59.91 |
-| `ENTS_R` | 57.69 |
-| `ENTS_F` | 58.78 |
-| `SKILL_P` | 72.77 |
-| `SKILL_R` | 72.38 |
-| `SKILL_F` | 72.57 |
-| `EXPERIENCE_P` | 56.00 |
-| `EXPERIENCE_R` | 47.73 |
-| `EXPERIENCE_F` | 51.53 |
-| `BENEFIT_P` | 77.42 |
-| `BENEFIT_R` | 35.82 |
-| `BENEFIT_F` | 48.98 |
+| `ENTS_P` | 59.19 |
+| `ENTS_R` | 57.58 |
+| `ENTS_F` | 58.38 |
+| `SKILL_P` | 72.19 |
+| `SKILL_R` | 72.62 |
+| `SKILL_F` | 72.40 |
+| `EXPERIENCE_P` | 52.14 |
+| `EXPERIENCE_R` | 41.48 |
+| `EXPERIENCE_F` | 46.20 |
+| `BENEFIT_P` | 75.61 |
+| `BENEFIT_R` | 46.27 |
+| `BENEFIT_F` | 57.41 |

config.cfg

@@ -17,6 +17,7 @@ after_creation = null
 after_pipeline_creation = null
 batch_size = 256
 tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
+vectors = {"@vectors":"spacy.Vectors.v1"}
 
 [components]
 
@@ -116,6 +117,7 @@ maxout_pieces = 2
 
 [components.tagger]
 factory = "tagger"
+label_smoothing = 0.0
 neg_prefix = "!"
 overwrite = false
 scorer = {"@scorers":"spacy.tagger_scorer.v1"}

en_skillner-any-py3-none-any.whl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aebd76db8a853da31818688df06486b6bd9728c0647a818307ef7251bd7c4d8c
-size 587688924
+oid sha256:9b840315f54eda471ecbeece805f216c4c25b519a88a6962084730d7803c54d1
+size 587689424

meta.json

@@ -1,14 +1,14 @@
 {
   "lang":"en",
   "name":"skillner",
-  "version":"3.5.0",
+  "version":"3.7.1",
   "description":"A Named Entity Recognition (NER) model to extract SKILL, EXPERIENCE and BENEFIT from job adverts.",
   "author":"nestauk",
   "email":"contact@explosion.ai",
   "url":"https://explosion.ai",
   "license":"MIT",
-  "spacy_version":">=3.5.3,<3.6.0",
-  "spacy_git_version":"9e0322de1",
+  "spacy_version":">=3.7.4,<3.8.0",
+  "spacy_git_version":"bd2c17e20",
   "vectors":{
     "width":300,
     "vectors":514157,
@@ -43,54 +43,54 @@
     "senter"
   ],
   "performance":{
-    "ents_p":0.5991309071,
-    "ents_r":0.5768828452,
-    "ents_f":0.5877964295,
-    "skill_p":0.7277108434,
-    "skill_r":0.7237866986,
-    "skill_f":0.7257434665,
-    "experience_p":0.56,
-    "experience_r":0.4772727273,
-    "experience_f":0.5153374233,
-    "benefit_p":0.7741935484,
-    "benefit_r":0.3582089552,
-    "benefit_f":0.4897959184,
+    "ents_p":0.5919354839,
+    "ents_r":0.5758368201,
+    "ents_f":0.5837751856,
+    "skill_p":0.721858249,
+    "skill_r":0.7261833433,
+    "skill_f":0.7240143369,
+    "experience_p":0.5214285714,
+    "experience_r":0.4147727273,
+    "experience_f":0.4620253165,
+    "benefit_p":0.756097561,
+    "benefit_r":0.4626865672,
+    "benefit_f":0.5740740741,
     "ents_per_type":{
       "SKILL":{
-        "correct":1208,
+        "correct":1212,
         "incorrect":32,
         "partial":0,
-        "missed":429,
-        "spurious":420,
+        "missed":425,
+        "spurious":435,
         "possible":1669,
-        "actual":1660,
-        "precision":0.7277108434,
-        "recall":0.7237866986,
-        "f1":0.7257434665
+        "actual":1679,
+        "precision":0.721858249,
+        "recall":0.7261833433,
+        "f1":0.7240143369
       },
       "EXPERIENCE":{
-        "correct":84,
-        "incorrect":37,
+        "correct":73,
+        "incorrect":39,
         "partial":0,
-        "missed":55,
-        "spurious":29,
+        "missed":64,
+        "spurious":28,
         "possible":176,
-        "actual":150,
-        "precision":0.56,
-        "recall":0.4772727273,
-        "f1":0.5153374233
+        "actual":140,
+        "precision":0.5214285714,
+        "recall":0.4147727273,
+        "f1":0.4620253165
       },
       "BENEFIT":{
-        "correct":24,
-        "incorrect":3,
+        "correct":31,
+        "incorrect":4,
         "partial":0,
-        "missed":40,
-        "spurious":4,
+        "missed":32,
+        "spurious":6,
         "possible":67,
-        "actual":31,
-        "precision":0.7741935484,
-        "recall":0.3582089552,
-        "f1":0.4897959184
+        "actual":41,
+        "precision":0.756097561,
+        "recall":0.4626865672,
+        "f1":0.5740740741
       }
     }
   },

ner/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dd953e4cc7eeaa1052539fcb71b312a0650910a310fb84b5eac2d89e993e8c0
+oid sha256:feadcb06a1ff7169640e3394e886c696675ccc6d651ebe5bf862fa97d761e0fe
 size 6384063

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,"EXPERIENCE":-1,"SKILL":-2,"BENEFIT":-3},"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,"EXPERIENCE":-1,"SKILL":-2,"BENEFIT":-3},"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,"EXPERIENCE":-1,"SKILL":-2,"BENEFIT":-3},"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,"EXPERIENCE":-1,"SKILL":-2,"BENEFIT":-3},"5":{"":1}}�cfg��neg_key�
+��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,"SKILL":-1,"EXPERIENCE":-2,"BENEFIT":-3},"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,"SKILL":-1,"EXPERIENCE":-2,"BENEFIT":-3},"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,"SKILL":-1,"EXPERIENCE":-2,"BENEFIT":-3},"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,"SKILL":-1,"EXPERIENCE":-2,"BENEFIT":-3},"5":{"":1}}�cfg��neg_key�

tagger/cfg

@@ -1,4 +1,5 @@
 {
+  "label_smoothing":0.0,
   "labels":[
     "$",
     "''",

vocab/lookups.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ddd140ecac6a8c4592e9146d6e30074569ffaed97ee51edc9587dc510f8934c
-size 69982
+oid sha256:fce9c883c56165f29573cc938c2a1c9d417ac61bd8f56b671dd5f7996de70682
+size 70040