Update spaCy pipeline
Browse files- README.md +10 -10
- de_pipeline-any-py3-none-any.whl +2 -2
- meta.json +23 -53
- ner/model +0 -0
- ner/moves +1 -1
- transformer/model +1 -1
- vocab/strings.json +0 -16
README.md
CHANGED
@@ -13,13 +13,13 @@ 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 |
| --- | --- |
|
@@ -37,11 +37,11 @@ model-index:
|
|
37 |
|
38 |
<details>
|
39 |
|
40 |
-
<summary>View label scheme (
|
41 |
|
42 |
| Component | Labels |
|
43 |
| --- | --- |
|
44 |
-
| **`ner`** | `GPE`, `
|
45 |
|
46 |
</details>
|
47 |
|
@@ -49,8 +49,8 @@ model-index:
|
|
49 |
|
50 |
| Type | Score |
|
51 |
| --- | --- |
|
52 |
-
| `ENTS_F` | 89.
|
53 |
-
| `ENTS_P` |
|
54 |
-
| `ENTS_R` |
|
55 |
-
| `TRANSFORMER_LOSS` |
|
56 |
-
| `NER_LOSS` |
|
|
|
13 |
metrics:
|
14 |
- name: NER Precision
|
15 |
type: precision
|
16 |
+
value: 0.9067489887
|
17 |
- name: NER Recall
|
18 |
type: recall
|
19 |
+
value: 0.8826943005
|
20 |
- name: NER F Score
|
21 |
type: f_score
|
22 |
+
value: 0.8945599664
|
23 |
---
|
24 |
| Feature | Description |
|
25 |
| --- | --- |
|
|
|
37 |
|
38 |
<details>
|
39 |
|
40 |
+
<summary>View label scheme (5 labels for 1 components)</summary>
|
41 |
|
42 |
| Component | Labels |
|
43 |
| --- | --- |
|
44 |
+
| **`ner`** | `GPE`, `LOC`, `ORG`, `OTH`, `PER` |
|
45 |
|
46 |
</details>
|
47 |
|
|
|
49 |
|
50 |
| Type | Score |
|
51 |
| --- | --- |
|
52 |
+
| `ENTS_F` | 89.46 |
|
53 |
+
| `ENTS_P` | 90.67 |
|
54 |
+
| `ENTS_R` | 88.27 |
|
55 |
+
| `TRANSFORMER_LOSS` | 91081.74 |
|
56 |
+
| `NER_LOSS` | 126122.54 |
|
de_pipeline-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 sha256:5970c272bd35a3ec94ef7d9d7f387c9ce24cba78090f917fb56fc0654046ce94
|
3 |
+
size 465196261
|
meta.json
CHANGED
@@ -21,15 +21,10 @@
|
|
21 |
],
|
22 |
"ner":[
|
23 |
"GPE",
|
24 |
-
"GPE*",
|
25 |
"LOC",
|
26 |
-
"LOC*",
|
27 |
"ORG",
|
28 |
-
"ORG*",
|
29 |
"OTH",
|
30 |
-
"
|
31 |
-
"PER",
|
32 |
-
"PER*"
|
33 |
]
|
34 |
},
|
35 |
"pipeline":[
|
@@ -44,63 +39,38 @@
|
|
44 |
|
45 |
],
|
46 |
"performance":{
|
47 |
-
"ents_f":0.
|
48 |
-
"ents_p":0.
|
49 |
-
"ents_r":0.
|
50 |
"ents_per_type":{
|
51 |
"GPE":{
|
52 |
-
"p":0.
|
53 |
-
"r":0.
|
54 |
-
"f":0.
|
55 |
-
},
|
56 |
-
"PER*":{
|
57 |
-
"p":0.9723535831,
|
58 |
-
"r":0.9755474453,
|
59 |
-
"f":0.9739478958
|
60 |
-
},
|
61 |
-
"ORG":{
|
62 |
-
"p":0.890672016,
|
63 |
-
"r":0.8532308431,
|
64 |
-
"f":0.8715495031
|
65 |
},
|
66 |
"PER":{
|
67 |
-
"p":0.
|
68 |
-
"r":0.
|
69 |
-
"f":0.
|
70 |
},
|
71 |
-
"
|
72 |
-
"p":0.
|
73 |
-
"r":0.
|
74 |
-
"f":0.
|
75 |
-
},
|
76 |
-
"LOC":{
|
77 |
-
"p":0.8064971751,
|
78 |
-
"r":0.6578341014,
|
79 |
-
"f":0.7246192893
|
80 |
},
|
81 |
"OTH":{
|
82 |
-
"p":0.
|
83 |
-
"r":0.
|
84 |
-
"f":0.
|
85 |
-
},
|
86 |
-
"ORG*":{
|
87 |
-
"p":0.7511389522,
|
88 |
-
"r":0.7841854935,
|
89 |
-
"f":0.7673065736
|
90 |
},
|
91 |
-
"LOC
|
92 |
-
"p":0.
|
93 |
-
"r":0.
|
94 |
-
"f":0.
|
95 |
-
},
|
96 |
-
"GPE*":{
|
97 |
-
"p":0.922005571,
|
98 |
-
"r":0.8073170732,
|
99 |
-
"f":0.8608582575
|
100 |
}
|
101 |
},
|
102 |
-
"transformer_loss":
|
103 |
-
"ner_loss":
|
104 |
},
|
105 |
"requirements":[
|
106 |
"spacy-transformers>=1.3.4,<1.4.0"
|
|
|
21 |
],
|
22 |
"ner":[
|
23 |
"GPE",
|
|
|
24 |
"LOC",
|
|
|
25 |
"ORG",
|
|
|
26 |
"OTH",
|
27 |
+
"PER"
|
|
|
|
|
28 |
]
|
29 |
},
|
30 |
"pipeline":[
|
|
|
39 |
|
40 |
],
|
41 |
"performance":{
|
42 |
+
"ents_f":0.8945599664,
|
43 |
+
"ents_p":0.9067489887,
|
44 |
+
"ents_r":0.8826943005,
|
45 |
"ents_per_type":{
|
46 |
"GPE":{
|
47 |
+
"p":0.9188587335,
|
48 |
+
"r":0.9434124035,
|
49 |
+
"f":0.9309737009
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
50 |
},
|
51 |
"PER":{
|
52 |
+
"p":0.962408436,
|
53 |
+
"r":0.9491148686,
|
54 |
+
"f":0.9557154277
|
55 |
},
|
56 |
+
"ORG":{
|
57 |
+
"p":0.8456036288,
|
58 |
+
"r":0.8292557742,
|
59 |
+
"f":0.8373499179
|
|
|
|
|
|
|
|
|
|
|
60 |
},
|
61 |
"OTH":{
|
62 |
+
"p":0.7113578138,
|
63 |
+
"r":0.5678254942,
|
64 |
+
"f":0.6315390447
|
|
|
|
|
|
|
|
|
|
|
65 |
},
|
66 |
+
"LOC":{
|
67 |
+
"p":0.7875523639,
|
68 |
+
"r":0.6441507587,
|
69 |
+
"f":0.7086698977
|
|
|
|
|
|
|
|
|
|
|
70 |
}
|
71 |
},
|
72 |
+
"transformer_loss":910.8173626132,
|
73 |
+
"ner_loss":1261.2253521142
|
74 |
},
|
75 |
"requirements":[
|
76 |
"spacy-transformers>=1.3.4,<1.4.0"
|
ner/model
CHANGED
Binary files a/ner/model and b/ner/model differ
|
|
ner/moves
CHANGED
@@ -1 +1 @@
|
|
1 |
-
��moves
|
|
|
1 |
+
��moves�{"0":{},"1":{"PER":32988,"ORG":18724,"GPE":12219,"OTH":6117,"LOC":4435},"2":{"PER":32988,"ORG":18724,"GPE":12219,"OTH":6117,"LOC":4435},"3":{"PER":32988,"ORG":18724,"GPE":12219,"OTH":6117,"LOC":4435},"4":{"PER":32988,"ORG":18724,"GPE":12219,"OTH":6117,"LOC":4435,"":1},"5":{"":1}}�cfg��neg_key�
|
transformer/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 502258447
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5acdf0eb16389c4401ad28321ab8dd9afe5e45360b27d0d31aa396f612e73c31
|
3 |
size 502258447
|
vocab/strings.json
CHANGED
@@ -26076,7 +26076,6 @@
|
|
26076 |
"EPLS",
|
26077 |
"EPs",
|
26078 |
"ER",
|
26079 |
-
"ER*",
|
26080 |
"ERE",
|
26081 |
"ERK",
|
26082 |
"ERN",
|
@@ -35898,7 +35897,6 @@
|
|
35898 |
"GOLIATH",
|
35899 |
"GOTT",
|
35900 |
"GOs",
|
35901 |
-
"GPE*",
|
35902 |
"GPS",
|
35903 |
"GPh",
|
35904 |
"GRP",
|
@@ -56048,7 +56046,6 @@
|
|
56048 |
"LMUA",
|
56049 |
"LMV",
|
56050 |
"LO",
|
56051 |
-
"LOC*",
|
56052 |
"LOCKERBIE",
|
56053 |
"LOK-VOGEL",
|
56054 |
"LOKALKOLORATUR",
|
@@ -68335,7 +68332,6 @@
|
|
68335 |
"OBERBAUMBR\u00dcCKE",
|
68336 |
"OBR",
|
68337 |
"OBWOHL",
|
68338 |
-
"OC*",
|
68339 |
"OCDE",
|
68340 |
"OCH",
|
68341 |
"ODY",
|
@@ -68387,7 +68383,6 @@
|
|
68387 |
"OREL",
|
68388 |
"OREL-Gruppe",
|
68389 |
"ORF",
|
68390 |
-
"ORG*",
|
68391 |
"ORK",
|
68392 |
"ORM",
|
68393 |
"ORT",
|
@@ -68405,7 +68400,6 @@
|
|
68405 |
"OTC",
|
68406 |
"OTE",
|
68407 |
"OTH",
|
68408 |
-
"OTH*",
|
68409 |
"OTO",
|
68410 |
"OTT",
|
68411 |
"OUP",
|
@@ -69965,7 +69959,6 @@
|
|
69965 |
"PDSlern",
|
69966 |
"PDT",
|
69967 |
"PDU",
|
69968 |
-
"PE*",
|
69969 |
"PEC",
|
69970 |
"PEL",
|
69971 |
"PEN",
|
@@ -69977,7 +69970,6 @@
|
|
69977 |
"PEN-Zentrum",
|
69978 |
"PEN-Zentrums",
|
69979 |
"PER",
|
69980 |
-
"PER*",
|
69981 |
"PES-M\u00e4nner",
|
69982 |
"PET",
|
69983 |
"PET-Flasche",
|
@@ -75538,7 +75530,6 @@
|
|
75538 |
"REWE",
|
75539 |
"REWE-Sprecher",
|
75540 |
"RFF",
|
75541 |
-
"RG*",
|
75542 |
"RGE",
|
75543 |
"RGI",
|
75544 |
"RGW",
|
@@ -91935,7 +91926,6 @@
|
|
91935 |
"TG",
|
91936 |
"TGV",
|
91937 |
"TH",
|
91938 |
-
"TH*",
|
91939 |
"THA-Aufsichtsrat",
|
91940 |
"THC",
|
91941 |
"THC-Gehalt",
|
@@ -106542,7 +106532,6 @@
|
|
106542 |
"XXX'x",
|
106543 |
"XXX'xxx",
|
106544 |
"XXX'xxxx",
|
106545 |
-
"XXX*",
|
106546 |
"XXX-",
|
106547 |
"XXX-\"Xxxxx",
|
106548 |
"XXX-\"Xxxxx\"",
|
@@ -160614,7 +160603,6 @@
|
|
160614 |
"go\u00dfberg-baustelle",
|
160615 |
"go\u00dfberg-computer",
|
160616 |
"gpe",
|
160617 |
-
"gpe*",
|
160618 |
"gph",
|
160619 |
"gps",
|
160620 |
"gr.",
|
@@ -185321,7 +185309,6 @@
|
|
185321 |
"lobte",
|
185322 |
"lobten",
|
185323 |
"loc",
|
185324 |
-
"loc*",
|
185325 |
"local",
|
185326 |
"locarno",
|
185327 |
"location",
|
@@ -198975,7 +198962,6 @@
|
|
198975 |
"orestie",
|
198976 |
"orf",
|
198977 |
"org",
|
198978 |
-
"org*",
|
198979 |
"orgaisation",
|
198980 |
"organ",
|
198981 |
"organe",
|
@@ -199563,7 +199549,6 @@
|
|
199563 |
"otelos",
|
199564 |
"otero",
|
199565 |
"oth",
|
199566 |
-
"oth*",
|
199567 |
"othe",
|
199568 |
"other",
|
199569 |
"othi",
|
@@ -201356,7 +201341,6 @@
|
|
201356 |
"peptimist",
|
201357 |
"pepusch",
|
201358 |
"per",
|
201359 |
-
"per*",
|
201360 |
"per-arne",
|
201361 |
"peralta",
|
201362 |
"perborate",
|
|
|
26076 |
"EPLS",
|
26077 |
"EPs",
|
26078 |
"ER",
|
|
|
26079 |
"ERE",
|
26080 |
"ERK",
|
26081 |
"ERN",
|
|
|
35897 |
"GOLIATH",
|
35898 |
"GOTT",
|
35899 |
"GOs",
|
|
|
35900 |
"GPS",
|
35901 |
"GPh",
|
35902 |
"GRP",
|
|
|
56046 |
"LMUA",
|
56047 |
"LMV",
|
56048 |
"LO",
|
|
|
56049 |
"LOCKERBIE",
|
56050 |
"LOK-VOGEL",
|
56051 |
"LOKALKOLORATUR",
|
|
|
68332 |
"OBERBAUMBR\u00dcCKE",
|
68333 |
"OBR",
|
68334 |
"OBWOHL",
|
|
|
68335 |
"OCDE",
|
68336 |
"OCH",
|
68337 |
"ODY",
|
|
|
68383 |
"OREL",
|
68384 |
"OREL-Gruppe",
|
68385 |
"ORF",
|
|
|
68386 |
"ORK",
|
68387 |
"ORM",
|
68388 |
"ORT",
|
|
|
68400 |
"OTC",
|
68401 |
"OTE",
|
68402 |
"OTH",
|
|
|
68403 |
"OTO",
|
68404 |
"OTT",
|
68405 |
"OUP",
|
|
|
69959 |
"PDSlern",
|
69960 |
"PDT",
|
69961 |
"PDU",
|
|
|
69962 |
"PEC",
|
69963 |
"PEL",
|
69964 |
"PEN",
|
|
|
69970 |
"PEN-Zentrum",
|
69971 |
"PEN-Zentrums",
|
69972 |
"PER",
|
|
|
69973 |
"PES-M\u00e4nner",
|
69974 |
"PET",
|
69975 |
"PET-Flasche",
|
|
|
75530 |
"REWE",
|
75531 |
"REWE-Sprecher",
|
75532 |
"RFF",
|
|
|
75533 |
"RGE",
|
75534 |
"RGI",
|
75535 |
"RGW",
|
|
|
91926 |
"TG",
|
91927 |
"TGV",
|
91928 |
"TH",
|
|
|
91929 |
"THA-Aufsichtsrat",
|
91930 |
"THC",
|
91931 |
"THC-Gehalt",
|
|
|
106532 |
"XXX'x",
|
106533 |
"XXX'xxx",
|
106534 |
"XXX'xxxx",
|
|
|
106535 |
"XXX-",
|
106536 |
"XXX-\"Xxxxx",
|
106537 |
"XXX-\"Xxxxx\"",
|
|
|
160603 |
"go\u00dfberg-baustelle",
|
160604 |
"go\u00dfberg-computer",
|
160605 |
"gpe",
|
|
|
160606 |
"gph",
|
160607 |
"gps",
|
160608 |
"gr.",
|
|
|
185309 |
"lobte",
|
185310 |
"lobten",
|
185311 |
"loc",
|
|
|
185312 |
"local",
|
185313 |
"locarno",
|
185314 |
"location",
|
|
|
198962 |
"orestie",
|
198963 |
"orf",
|
198964 |
"org",
|
|
|
198965 |
"orgaisation",
|
198966 |
"organ",
|
198967 |
"organe",
|
|
|
199549 |
"otelos",
|
199550 |
"otero",
|
199551 |
"oth",
|
|
|
199552 |
"othe",
|
199553 |
"other",
|
199554 |
"othi",
|
|
|
201341 |
"peptimist",
|
201342 |
"pepusch",
|
201343 |
"per",
|
|
|
201344 |
"per-arne",
|
201345 |
"peralta",
|
201346 |
"perborate",
|