Update spaCy pipeline
Browse files- README.md +12 -12
- config.cfg +6 -5
- en_Spacy_Custom_ner2-any-py3-none-any.whl +2 -2
- meta.json +33 -45
- ner/model +0 -0
- ner/moves +1 -1
- tok2vec/model +2 -2
- vocab/key2row +2 -2
- vocab/strings.json +0 -0
- vocab/vectors +2 -2
README.md
CHANGED
|
@@ -13,22 +13,22 @@ model-index:
|
|
| 13 |
metrics:
|
| 14 |
- name: NER Precision
|
| 15 |
type: precision
|
| 16 |
-
value: 0.
|
| 17 |
- name: NER Recall
|
| 18 |
type: recall
|
| 19 |
-
value: 0.
|
| 20 |
- name: NER F Score
|
| 21 |
type: f_score
|
| 22 |
-
value: 0.
|
| 23 |
---
|
| 24 |
| Feature | Description |
|
| 25 |
| --- | --- |
|
| 26 |
| **Name** | `en_Spacy_Custom_ner2` |
|
| 27 |
| **Version** | `0.0.0` |
|
| 28 |
-
| **spaCy** | `>=3.
|
| 29 |
| **Default Pipeline** | `tok2vec`, `ner` |
|
| 30 |
| **Components** | `tok2vec`, `ner` |
|
| 31 |
-
| **Vectors** |
|
| 32 |
| **Sources** | n/a |
|
| 33 |
| **License** | n/a |
|
| 34 |
| **Author** | [n/a]() |
|
|
@@ -37,11 +37,11 @@ model-index:
|
|
| 37 |
|
| 38 |
<details>
|
| 39 |
|
| 40 |
-
<summary>View label scheme (
|
| 41 |
|
| 42 |
| Component | Labels |
|
| 43 |
| --- | --- |
|
| 44 |
-
| **`ner`** | `
|
| 45 |
|
| 46 |
</details>
|
| 47 |
|
|
@@ -49,8 +49,8 @@ model-index:
|
|
| 49 |
|
| 50 |
| Type | Score |
|
| 51 |
| --- | --- |
|
| 52 |
-
| `ENTS_F` | 99.
|
| 53 |
-
| `ENTS_P` | 99.
|
| 54 |
-
| `ENTS_R` | 99.
|
| 55 |
-
| `TOK2VEC_LOSS` |
|
| 56 |
-
| `NER_LOSS` |
|
|
|
|
| 13 |
metrics:
|
| 14 |
- name: NER Precision
|
| 15 |
type: precision
|
| 16 |
+
value: 0.9907894737
|
| 17 |
- name: NER Recall
|
| 18 |
type: recall
|
| 19 |
+
value: 0.996031746
|
| 20 |
- name: NER F Score
|
| 21 |
type: f_score
|
| 22 |
+
value: 0.9934036939
|
| 23 |
---
|
| 24 |
| Feature | Description |
|
| 25 |
| --- | --- |
|
| 26 |
| **Name** | `en_Spacy_Custom_ner2` |
|
| 27 |
| **Version** | `0.0.0` |
|
| 28 |
+
| **spaCy** | `>=3.7.2,<3.8.0` |
|
| 29 |
| **Default Pipeline** | `tok2vec`, `ner` |
|
| 30 |
| **Components** | `tok2vec`, `ner` |
|
| 31 |
+
| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
|
| 32 |
| **Sources** | n/a |
|
| 33 |
| **License** | n/a |
|
| 34 |
| **Author** | [n/a]() |
|
|
|
|
| 37 |
|
| 38 |
<details>
|
| 39 |
|
| 40 |
+
<summary>View label scheme (14 labels for 1 components)</summary>
|
| 41 |
|
| 42 |
| Component | Labels |
|
| 43 |
| --- | --- |
|
| 44 |
+
| **`ner`** | `BOOK`, `COMODITY`, `CONTAINER COUNT`, `CONTAINER SIZE`, `CONTAINER SIZE-COUNT`, `DESTINATION`, `ENQUIRY`, `HELP`, `INCOTERM`, `KYC`, `ORIGIN`, `SEARCH RATES`, `SHIP`, `SHIPMENT TYPE` |
|
| 45 |
|
| 46 |
</details>
|
| 47 |
|
|
|
|
| 49 |
|
| 50 |
| Type | Score |
|
| 51 |
| --- | --- |
|
| 52 |
+
| `ENTS_F` | 99.34 |
|
| 53 |
+
| `ENTS_P` | 99.08 |
|
| 54 |
+
| `ENTS_R` | 99.60 |
|
| 55 |
+
| `TOK2VEC_LOSS` | 7290.77 |
|
| 56 |
+
| `NER_LOSS` | 70900.21 |
|
config.cfg
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
[paths]
|
| 2 |
train = "./training_data.spacy"
|
| 3 |
dev = "./training_data.spacy"
|
| 4 |
-
vectors =
|
| 5 |
init_tok2vec = null
|
| 6 |
|
| 7 |
[system]
|
|
@@ -11,12 +11,13 @@ seed = 0
|
|
| 11 |
[nlp]
|
| 12 |
lang = "en"
|
| 13 |
pipeline = ["tok2vec","ner"]
|
| 14 |
-
batch_size =
|
| 15 |
disabled = []
|
| 16 |
before_creation = null
|
| 17 |
after_creation = null
|
| 18 |
after_pipeline_creation = null
|
| 19 |
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
|
|
|
|
| 20 |
|
| 21 |
[components]
|
| 22 |
|
|
@@ -52,12 +53,12 @@ factory = "tok2vec"
|
|
| 52 |
width = ${components.tok2vec.model.encode.width}
|
| 53 |
attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
|
| 54 |
rows = [5000,1000,2500,2500]
|
| 55 |
-
include_static_vectors =
|
| 56 |
|
| 57 |
[components.tok2vec.model.encode]
|
| 58 |
@architectures = "spacy.MaxoutWindowEncoder.v2"
|
| 59 |
-
width =
|
| 60 |
-
depth =
|
| 61 |
window_size = 1
|
| 62 |
maxout_pieces = 3
|
| 63 |
|
|
|
|
| 1 |
[paths]
|
| 2 |
train = "./training_data.spacy"
|
| 3 |
dev = "./training_data.spacy"
|
| 4 |
+
vectors = null
|
| 5 |
init_tok2vec = null
|
| 6 |
|
| 7 |
[system]
|
|
|
|
| 11 |
[nlp]
|
| 12 |
lang = "en"
|
| 13 |
pipeline = ["tok2vec","ner"]
|
| 14 |
+
batch_size = 1000
|
| 15 |
disabled = []
|
| 16 |
before_creation = null
|
| 17 |
after_creation = null
|
| 18 |
after_pipeline_creation = null
|
| 19 |
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
|
| 20 |
+
vectors = {"@vectors":"spacy.Vectors.v1"}
|
| 21 |
|
| 22 |
[components]
|
| 23 |
|
|
|
|
| 53 |
width = ${components.tok2vec.model.encode.width}
|
| 54 |
attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
|
| 55 |
rows = [5000,1000,2500,2500]
|
| 56 |
+
include_static_vectors = false
|
| 57 |
|
| 58 |
[components.tok2vec.model.encode]
|
| 59 |
@architectures = "spacy.MaxoutWindowEncoder.v2"
|
| 60 |
+
width = 96
|
| 61 |
+
depth = 4
|
| 62 |
window_size = 1
|
| 63 |
maxout_pieces = 3
|
| 64 |
|
en_Spacy_Custom_ner2-any-py3-none-any.whl
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55064fcd52899715cf7a340a538072dad8f74dcf882ce630db03851860b2bc73
|
| 3 |
+
size 5688225
|
meta.json
CHANGED
|
@@ -7,20 +7,19 @@
|
|
| 7 |
"email":"",
|
| 8 |
"url":"",
|
| 9 |
"license":"",
|
| 10 |
-
"spacy_version":">=3.
|
| 11 |
-
"spacy_git_version":"
|
| 12 |
"vectors":{
|
| 13 |
-
"width":
|
| 14 |
-
"vectors":
|
| 15 |
-
"keys":
|
| 16 |
-
"name":
|
| 17 |
},
|
| 18 |
"labels":{
|
| 19 |
"tok2vec":[
|
| 20 |
|
| 21 |
],
|
| 22 |
"ner":[
|
| 23 |
-
"AGENT_FALLBACK",
|
| 24 |
"BOOK",
|
| 25 |
"COMODITY",
|
| 26 |
"CONTAINER COUNT",
|
|
@@ -34,8 +33,7 @@
|
|
| 34 |
"ORIGIN",
|
| 35 |
"SEARCH RATES",
|
| 36 |
"SHIP",
|
| 37 |
-
"SHIPMENT TYPE"
|
| 38 |
-
"WELCOME_MSG"
|
| 39 |
]
|
| 40 |
},
|
| 41 |
"pipeline":[
|
|
@@ -50,24 +48,29 @@
|
|
| 50 |
|
| 51 |
],
|
| 52 |
"performance":{
|
| 53 |
-
"ents_f":0.
|
| 54 |
-
"ents_p":0.
|
| 55 |
-
"ents_r":0.
|
| 56 |
"ents_per_type":{
|
| 57 |
-
"
|
| 58 |
"p":1.0,
|
| 59 |
"r":1.0,
|
| 60 |
"f":1.0
|
| 61 |
},
|
| 62 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 63 |
"p":1.0,
|
| 64 |
"r":1.0,
|
| 65 |
"f":1.0
|
| 66 |
},
|
| 67 |
-
"
|
| 68 |
-
"p":
|
| 69 |
"r":1.0,
|
| 70 |
-
"f":
|
| 71 |
},
|
| 72 |
"BOOK":{
|
| 73 |
"p":1.0,
|
|
@@ -75,24 +78,19 @@
|
|
| 75 |
"f":1.0
|
| 76 |
},
|
| 77 |
"SHIP":{
|
| 78 |
-
"p":0.
|
| 79 |
"r":1.0,
|
| 80 |
-
"f":0.
|
| 81 |
},
|
| 82 |
"CONTAINER SIZE":{
|
| 83 |
-
"p":0.9905660377,
|
| 84 |
-
"r":0.9905660377,
|
| 85 |
-
"f":0.9905660377
|
| 86 |
-
},
|
| 87 |
-
"SHIPMENT TYPE":{
|
| 88 |
"p":1.0,
|
| 89 |
-
"r":
|
| 90 |
-
"f":
|
| 91 |
},
|
| 92 |
"ENQUIRY":{
|
| 93 |
-
"p":0.
|
| 94 |
"r":1.0,
|
| 95 |
-
"f":0.
|
| 96 |
},
|
| 97 |
"HELP":{
|
| 98 |
"p":1.0,
|
|
@@ -110,9 +108,9 @@
|
|
| 110 |
"f":1.0
|
| 111 |
},
|
| 112 |
"COMODITY":{
|
| 113 |
-
"p":0.
|
| 114 |
-
"r":
|
| 115 |
-
"f":0.
|
| 116 |
},
|
| 117 |
"CONTAINER COUNT":{
|
| 118 |
"p":1.0,
|
|
@@ -120,23 +118,13 @@
|
|
| 120 |
"f":1.0
|
| 121 |
},
|
| 122 |
"CONTAINER SIZE-COUNT":{
|
| 123 |
-
"p":
|
| 124 |
-
"r":0.9615384615,
|
| 125 |
-
"f":0.9803921569
|
| 126 |
-
},
|
| 127 |
-
"AGENT_FALLBACK":{
|
| 128 |
-
"p":1.0,
|
| 129 |
"r":1.0,
|
| 130 |
-
"f":
|
| 131 |
-
},
|
| 132 |
-
"WELCOME_MSG":{
|
| 133 |
-
"p":1.0,
|
| 134 |
-
"r":1.0,
|
| 135 |
-
"f":1.0
|
| 136 |
}
|
| 137 |
},
|
| 138 |
-
"tok2vec_loss":
|
| 139 |
-
"ner_loss":
|
| 140 |
},
|
| 141 |
"requirements":[
|
| 142 |
|
|
|
|
| 7 |
"email":"",
|
| 8 |
"url":"",
|
| 9 |
"license":"",
|
| 10 |
+
"spacy_version":">=3.7.2,<3.8.0",
|
| 11 |
+
"spacy_git_version":"a89eae928",
|
| 12 |
"vectors":{
|
| 13 |
+
"width":0,
|
| 14 |
+
"vectors":0,
|
| 15 |
+
"keys":0,
|
| 16 |
+
"name":null
|
| 17 |
},
|
| 18 |
"labels":{
|
| 19 |
"tok2vec":[
|
| 20 |
|
| 21 |
],
|
| 22 |
"ner":[
|
|
|
|
| 23 |
"BOOK",
|
| 24 |
"COMODITY",
|
| 25 |
"CONTAINER COUNT",
|
|
|
|
| 33 |
"ORIGIN",
|
| 34 |
"SEARCH RATES",
|
| 35 |
"SHIP",
|
| 36 |
+
"SHIPMENT TYPE"
|
|
|
|
| 37 |
]
|
| 38 |
},
|
| 39 |
"pipeline":[
|
|
|
|
| 48 |
|
| 49 |
],
|
| 50 |
"performance":{
|
| 51 |
+
"ents_f":0.9934036939,
|
| 52 |
+
"ents_p":0.9907894737,
|
| 53 |
+
"ents_r":0.996031746,
|
| 54 |
"ents_per_type":{
|
| 55 |
+
"ORIGIN":{
|
| 56 |
"p":1.0,
|
| 57 |
"r":1.0,
|
| 58 |
"f":1.0
|
| 59 |
},
|
| 60 |
+
"DESTINATION":{
|
| 61 |
+
"p":0.995,
|
| 62 |
+
"r":0.995,
|
| 63 |
+
"f":0.995
|
| 64 |
+
},
|
| 65 |
+
"SHIPMENT TYPE":{
|
| 66 |
"p":1.0,
|
| 67 |
"r":1.0,
|
| 68 |
"f":1.0
|
| 69 |
},
|
| 70 |
+
"SEARCH RATES":{
|
| 71 |
+
"p":1.0,
|
| 72 |
"r":1.0,
|
| 73 |
+
"f":1.0
|
| 74 |
},
|
| 75 |
"BOOK":{
|
| 76 |
"p":1.0,
|
|
|
|
| 78 |
"f":1.0
|
| 79 |
},
|
| 80 |
"SHIP":{
|
| 81 |
+
"p":0.987654321,
|
| 82 |
"r":1.0,
|
| 83 |
+
"f":0.9937888199
|
| 84 |
},
|
| 85 |
"CONTAINER SIZE":{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 86 |
"p":1.0,
|
| 87 |
+
"r":0.9795918367,
|
| 88 |
+
"f":0.9896907216
|
| 89 |
},
|
| 90 |
"ENQUIRY":{
|
| 91 |
+
"p":0.875,
|
| 92 |
"r":1.0,
|
| 93 |
+
"f":0.9333333333
|
| 94 |
},
|
| 95 |
"HELP":{
|
| 96 |
"p":1.0,
|
|
|
|
| 108 |
"f":1.0
|
| 109 |
},
|
| 110 |
"COMODITY":{
|
| 111 |
+
"p":0.9130434783,
|
| 112 |
+
"r":1.0,
|
| 113 |
+
"f":0.9545454545
|
| 114 |
},
|
| 115 |
"CONTAINER COUNT":{
|
| 116 |
"p":1.0,
|
|
|
|
| 118 |
"f":1.0
|
| 119 |
},
|
| 120 |
"CONTAINER SIZE-COUNT":{
|
| 121 |
+
"p":0.962962963,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 122 |
"r":1.0,
|
| 123 |
+
"f":0.9811320755
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 124 |
}
|
| 125 |
},
|
| 126 |
+
"tok2vec_loss":72.9077196514,
|
| 127 |
+
"ner_loss":709.0020859699
|
| 128 |
},
|
| 129 |
"requirements":[
|
| 130 |
|
ner/model
CHANGED
|
Binary files a/ner/model and b/ner/model differ
|
|
|
ner/moves
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
��moves�
|
|
|
|
| 1 |
+
��moves�|{"0":{},"1":{"DESTINATION":313,"ORIGIN":295,"CONTAINER SIZE":174,"SHIP":80,"SHIPMENT TYPE":60,"CONTAINER SIZE-COUNT":39,"COMODITY":31,"BOOK":28,"ENQUIRY":17,"INCOTERM":9,"HELP":8,"CONTAINER COUNT":8,"SEARCH RATES":7,"KYC":2},"2":{"DESTINATION":313,"ORIGIN":295,"CONTAINER SIZE":174,"SHIP":80,"SHIPMENT TYPE":60,"CONTAINER SIZE-COUNT":39,"COMODITY":31,"BOOK":28,"ENQUIRY":17,"INCOTERM":9,"HELP":8,"CONTAINER COUNT":8,"SEARCH RATES":7,"KYC":2},"3":{"DESTINATION":313,"ORIGIN":295,"CONTAINER SIZE":174,"SHIP":80,"SHIPMENT TYPE":60,"CONTAINER SIZE-COUNT":39,"COMODITY":31,"BOOK":28,"ENQUIRY":17,"INCOTERM":9,"HELP":8,"CONTAINER COUNT":8,"SEARCH RATES":7,"KYC":2},"4":{"DESTINATION":313,"ORIGIN":295,"CONTAINER SIZE":174,"SHIP":80,"SHIPMENT TYPE":60,"CONTAINER SIZE-COUNT":39,"COMODITY":31,"BOOK":28,"ENQUIRY":17,"INCOTERM":9,"HELP":8,"CONTAINER COUNT":8,"SEARCH RATES":7,"KYC":2,"":1},"5":{"":1}}�cfg��neg_key�
|
tok2vec/model
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:242b2c12c6efec38ede80c052b45333201ddec15e45ce1ff6f486fc9888e6c8f
|
| 3 |
+
size 6009091
|
vocab/key2row
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76be8b528d0075f7aae98d6fa57a6d3c83ae480a8469e668d7b0af968995ac71
|
| 3 |
+
size 1
|
vocab/strings.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
vocab/vectors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14772b683e726436d5948ad3fff2b43d036ef2ebbe3458aafed6004e05a40706
|
| 3 |
+
size 128
|