Update spaCy pipeline
Browse files- README.md +11 -11
- config.cfg +2 -2
- en_docusco_spacy_fc_trf-any-py3-none-any.whl +2 -2
- meta.json +65 -65
- ner/model +0 -0
- ner/moves +1 -1
- tagger/model +0 -0
- transformer/model +1 -1
README.md
CHANGED
@@ -14,27 +14,27 @@ model-index:
|
|
14 |
metrics:
|
15 |
- name: NER Precision
|
16 |
type: precision
|
17 |
-
value: 0.
|
18 |
- name: NER Recall
|
19 |
type: recall
|
20 |
-
value: 0.
|
21 |
- name: NER F Score
|
22 |
type: f_score
|
23 |
-
value: 0.
|
24 |
- task:
|
25 |
name: TAG
|
26 |
type: token-classification
|
27 |
metrics:
|
28 |
- name: TAG (XPOS) Accuracy
|
29 |
type: accuracy
|
30 |
-
value: 0.
|
31 |
---
|
32 |
English pipeline for part-of-speech and rhetorical tagging.
|
33 |
|
34 |
| Feature | Description |
|
35 |
| --- | --- |
|
36 |
| **Name** | `en_docusco_spacy_fc_trf` |
|
37 |
-
| **Version** | `1.
|
38 |
| **spaCy** | `>=3.4.3,<3.5.0` |
|
39 |
| **Default Pipeline** | `transformer`, `tagger`, `ner` |
|
40 |
| **Components** | `transformer`, `tagger`, `ner` |
|
@@ -61,9 +61,9 @@ English pipeline for part-of-speech and rhetorical tagging.
|
|
61 |
| Type | Score |
|
62 |
| --- | --- |
|
63 |
| `TAG_ACC` | 98.39 |
|
64 |
-
| `ENTS_F` | 88.
|
65 |
-
| `ENTS_P` | 88.
|
66 |
-
| `ENTS_R` | 88.
|
67 |
-
| `TRANSFORMER_LOSS` |
|
68 |
-
| `TAGGER_LOSS` |
|
69 |
-
| `NER_LOSS` |
|
|
|
14 |
metrics:
|
15 |
- name: NER Precision
|
16 |
type: precision
|
17 |
+
value: 0.889028963
|
18 |
- name: NER Recall
|
19 |
type: recall
|
20 |
+
value: 0.8833963688
|
21 |
- name: NER F Score
|
22 |
type: f_score
|
23 |
+
value: 0.886203716
|
24 |
- task:
|
25 |
name: TAG
|
26 |
type: token-classification
|
27 |
metrics:
|
28 |
- name: TAG (XPOS) Accuracy
|
29 |
type: accuracy
|
30 |
+
value: 0.9838746739
|
31 |
---
|
32 |
English pipeline for part-of-speech and rhetorical tagging.
|
33 |
|
34 |
| Feature | Description |
|
35 |
| --- | --- |
|
36 |
| **Name** | `en_docusco_spacy_fc_trf` |
|
37 |
+
| **Version** | `1.1` |
|
38 |
| **spaCy** | `>=3.4.3,<3.5.0` |
|
39 |
| **Default Pipeline** | `transformer`, `tagger`, `ner` |
|
40 |
| **Components** | `transformer`, `tagger`, `ner` |
|
|
|
61 |
| Type | Score |
|
62 |
| --- | --- |
|
63 |
| `TAG_ACC` | 98.39 |
|
64 |
+
| `ENTS_F` | 88.62 |
|
65 |
+
| `ENTS_P` | 88.90 |
|
66 |
+
| `ENTS_R` | 88.34 |
|
67 |
+
| `TRANSFORMER_LOSS` | 2319800.36 |
|
68 |
+
| `TAGGER_LOSS` | 669777.78 |
|
69 |
+
| `NER_LOSS` | 2048423.35 |
|
config.cfg
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
[paths]
|
2 |
-
train =
|
3 |
-
dev =
|
4 |
vectors = null
|
5 |
init_tok2vec = null
|
6 |
|
|
|
1 |
[paths]
|
2 |
+
train = "/content/drive/MyDrive/DS Bert/SpacyTrain/spacy_train_cd.spacy"
|
3 |
+
dev = "/content/drive/MyDrive/DS Bert/SpacyTrain/spacy_test_cd.spacy"
|
4 |
vectors = null
|
5 |
init_tok2vec = null
|
6 |
|
en_docusco_spacy_fc_trf-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:db56eaa997e86c8da4c1e0ecb3cfbfe0f26eae97dc57fe04f6f7cbe8f1b37a14
|
3 |
+
size 464889500
|
meta.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"lang":"en",
|
3 |
"name":"docusco_spacy_fc_trf",
|
4 |
-
"version":"1.
|
5 |
"description":"English pipeline for part-of-speech and rhetorical tagging.",
|
6 |
"author":"David Brown",
|
7 |
"email":"[email protected]",
|
@@ -307,110 +307,110 @@
|
|
307 |
|
308 |
],
|
309 |
"performance":{
|
310 |
-
"tag_acc":0.
|
311 |
-
"ents_f":0.
|
312 |
-
"ents_p":0.
|
313 |
-
"ents_r":0.
|
314 |
"ents_per_type":{
|
315 |
"ActorsFirstPerson":{
|
316 |
-
"p":0.
|
317 |
-
"r":0.
|
318 |
-
"f":0.
|
319 |
},
|
320 |
"ActorsAbstractions":{
|
321 |
-
"p":0.
|
322 |
-
"r":0.
|
323 |
-
"f":0.
|
324 |
},
|
325 |
"SentimentPositive":{
|
326 |
-
"p":0.
|
327 |
-
"r":0.
|
328 |
-
"f":0.
|
329 |
},
|
330 |
"ActorsPeople":{
|
331 |
-
"p":0.
|
332 |
-
"r":0.
|
333 |
-
"f":0.
|
334 |
},
|
335 |
"SignpostingMetadiscourse":{
|
336 |
-
"p":0.
|
337 |
-
"r":0.
|
338 |
-
"f":0.
|
339 |
},
|
340 |
"OrganizationReasoning":{
|
341 |
-
"p":0.
|
342 |
-
"r":0.
|
343 |
-
"f":0.
|
344 |
},
|
345 |
"SentimentNegative":{
|
346 |
-
"p":0.
|
347 |
-
"r":0.
|
348 |
-
"f":0.
|
349 |
},
|
350 |
"OrganizationNarrative":{
|
351 |
-
"p":0.
|
352 |
-
"r":0.
|
353 |
-
"f":0.
|
354 |
},
|
355 |
"ActorsPublicEntities":{
|
356 |
-
"p":0.
|
357 |
-
"r":0.
|
358 |
-
"f":0.
|
359 |
},
|
360 |
"ConfidenceHedged":{
|
361 |
-
"p":0.
|
362 |
-
"r":0.
|
363 |
-
"f":0.
|
364 |
},
|
365 |
"StanceEmphatic":{
|
366 |
-
"p":0.
|
367 |
-
"r":0.
|
368 |
-
"f":0.
|
369 |
},
|
370 |
"ConfidenceHigh":{
|
371 |
-
"p":0.
|
372 |
-
"r":0.
|
373 |
-
"f":0.
|
374 |
},
|
375 |
"PlanningFuture":{
|
376 |
-
"p":0.
|
377 |
-
"r":0.
|
378 |
-
"f":0.
|
379 |
},
|
380 |
"SignpostingAcademicWritingMoves":{
|
381 |
-
"p":0.
|
382 |
-
"r":0.
|
383 |
-
"f":0.
|
384 |
},
|
385 |
"PlanningStrategy":{
|
386 |
-
"p":0.
|
387 |
-
"r":0.
|
388 |
-
"f":0.
|
389 |
},
|
390 |
"CitationAuthority":{
|
391 |
-
"p":0.
|
392 |
-
"r":0.
|
393 |
-
"f":0.
|
394 |
},
|
395 |
"StanceModerated":{
|
396 |
-
"p":0.
|
397 |
-
"r":0.
|
398 |
-
"f":0.
|
399 |
},
|
400 |
"CitationNeutral":{
|
401 |
-
"p":0.
|
402 |
-
"r":0.
|
403 |
-
"f":0.
|
404 |
},
|
405 |
"CitationControversy":{
|
406 |
-
"p":0.
|
407 |
-
"r":0.
|
408 |
-
"f":0.
|
409 |
}
|
410 |
},
|
411 |
-
"transformer_loss":
|
412 |
-
"tagger_loss":
|
413 |
-
"ner_loss":
|
414 |
},
|
415 |
"requirements":[
|
416 |
"spacy-transformers>=1.1.8,<1.2.0"
|
|
|
1 |
{
|
2 |
"lang":"en",
|
3 |
"name":"docusco_spacy_fc_trf",
|
4 |
+
"version":"1.1",
|
5 |
"description":"English pipeline for part-of-speech and rhetorical tagging.",
|
6 |
"author":"David Brown",
|
7 |
"email":"[email protected]",
|
|
|
307 |
|
308 |
],
|
309 |
"performance":{
|
310 |
+
"tag_acc":0.9838746739,
|
311 |
+
"ents_f":0.886203716,
|
312 |
+
"ents_p":0.889028963,
|
313 |
+
"ents_r":0.8833963688,
|
314 |
"ents_per_type":{
|
315 |
"ActorsFirstPerson":{
|
316 |
+
"p":0.9048672566,
|
317 |
+
"r":0.9176833544,
|
318 |
+
"f":0.9112302444
|
319 |
},
|
320 |
"ActorsAbstractions":{
|
321 |
+
"p":0.8884982639,
|
322 |
+
"r":0.8868047132,
|
323 |
+
"f":0.8876506808
|
324 |
},
|
325 |
"SentimentPositive":{
|
326 |
+
"p":0.8560008306,
|
327 |
+
"r":0.827811245,
|
328 |
+
"f":0.8416700694
|
329 |
},
|
330 |
"ActorsPeople":{
|
331 |
+
"p":0.9271072667,
|
332 |
+
"r":0.9305028034,
|
333 |
+
"f":0.9288019317
|
334 |
},
|
335 |
"SignpostingMetadiscourse":{
|
336 |
+
"p":0.9420750336,
|
337 |
+
"r":0.9215780036,
|
338 |
+
"f":0.9317138023
|
339 |
},
|
340 |
"OrganizationReasoning":{
|
341 |
+
"p":0.9138317376,
|
342 |
+
"r":0.8952304929,
|
343 |
+
"f":0.9044354839
|
344 |
},
|
345 |
"SentimentNegative":{
|
346 |
+
"p":0.8280952381,
|
347 |
+
"r":0.8157206996,
|
348 |
+
"f":0.8218613915
|
349 |
},
|
350 |
"OrganizationNarrative":{
|
351 |
+
"p":0.8888659154,
|
352 |
+
"r":0.8726276261,
|
353 |
+
"f":0.8806719246
|
354 |
},
|
355 |
"ActorsPublicEntities":{
|
356 |
+
"p":0.913087316,
|
357 |
+
"r":0.8978782471,
|
358 |
+
"f":0.9054189162
|
359 |
},
|
360 |
"ConfidenceHedged":{
|
361 |
+
"p":0.9044895625,
|
362 |
+
"r":0.9052661706,
|
363 |
+
"f":0.9048776999
|
364 |
},
|
365 |
"StanceEmphatic":{
|
366 |
+
"p":0.864783265,
|
367 |
+
"r":0.9101225601,
|
368 |
+
"f":0.8868738251
|
369 |
},
|
370 |
"ConfidenceHigh":{
|
371 |
+
"p":0.8696095076,
|
372 |
+
"r":0.8573819886,
|
373 |
+
"f":0.8634524612
|
374 |
},
|
375 |
"PlanningFuture":{
|
376 |
+
"p":0.8828828829,
|
377 |
+
"r":0.8994576554,
|
378 |
+
"f":0.8910932011
|
379 |
},
|
380 |
"SignpostingAcademicWritingMoves":{
|
381 |
+
"p":0.7609090909,
|
382 |
+
"r":0.7678899083,
|
383 |
+
"f":0.7643835616
|
384 |
},
|
385 |
"PlanningStrategy":{
|
386 |
+
"p":0.8513819665,
|
387 |
+
"r":0.8205240175,
|
388 |
+
"f":0.8356682233
|
389 |
},
|
390 |
"CitationAuthority":{
|
391 |
+
"p":0.8544839255,
|
392 |
+
"r":0.8265139116,
|
393 |
+
"f":0.840266223
|
394 |
},
|
395 |
"StanceModerated":{
|
396 |
+
"p":0.8590852905,
|
397 |
+
"r":0.8853503185,
|
398 |
+
"f":0.8720200753
|
399 |
},
|
400 |
"CitationNeutral":{
|
401 |
+
"p":0.8832214765,
|
402 |
+
"r":0.8832214765,
|
403 |
+
"f":0.8832214765
|
404 |
},
|
405 |
"CitationControversy":{
|
406 |
+
"p":0.8739837398,
|
407 |
+
"r":0.8884297521,
|
408 |
+
"f":0.881147541
|
409 |
}
|
410 |
},
|
411 |
+
"transformer_loss":23198.0035903843,
|
412 |
+
"tagger_loss":6697.7777622218,
|
413 |
+
"ner_loss":20484.2334804777
|
414 |
},
|
415 |
"requirements":[
|
416 |
"spacy-transformers>=1.1.8,<1.2.0"
|
ner/model
CHANGED
Binary files a/ner/model and b/ner/model differ
|
|
ner/moves
CHANGED
@@ -1 +1 @@
|
|
1 |
-
��moves�P{"0":{},"1":{"ActorsAbstractions":
|
|
|
1 |
+
��moves�P{"0":{},"1":{"ActorsAbstractions":574627,"SentimentNegative":505726,"ActorsPeople":489704,"SentimentPositive":329499,"OrganizationNarrative":327796,"SignpostingMetadiscourse":285541,"ActorsFirstPerson":242622,"OrganizationReasoning":182971,"StanceEmphatic":148905,"ActorsPublicEntities":141386,"ConfidenceHedged":130515,"ConfidenceHigh":119696,"PlanningFuture":91199,"PlanningStrategy":77436,"SignpostingAcademicWritingMoves":45355,"CitationNeutral":28827,"StanceModerated":24981,"CitationAuthority":24697,"CitationControversy":7780},"2":{"ActorsAbstractions":574627,"SentimentNegative":505726,"ActorsPeople":489704,"SentimentPositive":329499,"OrganizationNarrative":327796,"SignpostingMetadiscourse":285541,"ActorsFirstPerson":242622,"OrganizationReasoning":182971,"StanceEmphatic":148905,"ActorsPublicEntities":141386,"ConfidenceHedged":130515,"ConfidenceHigh":119696,"PlanningFuture":91199,"PlanningStrategy":77436,"SignpostingAcademicWritingMoves":45355,"CitationNeutral":28827,"StanceModerated":24981,"CitationAuthority":24697,"CitationControversy":7780},"3":{"ActorsAbstractions":574627,"SentimentNegative":505726,"ActorsPeople":489704,"SentimentPositive":329499,"OrganizationNarrative":327796,"SignpostingMetadiscourse":285541,"ActorsFirstPerson":242622,"OrganizationReasoning":182971,"StanceEmphatic":148905,"ActorsPublicEntities":141386,"ConfidenceHedged":130515,"ConfidenceHigh":119696,"PlanningFuture":91199,"PlanningStrategy":77436,"SignpostingAcademicWritingMoves":45355,"CitationNeutral":28827,"StanceModerated":24981,"CitationAuthority":24697,"CitationControversy":7780},"4":{"ActorsAbstractions":574627,"SentimentNegative":505726,"ActorsPeople":489704,"SentimentPositive":329499,"OrganizationNarrative":327796,"SignpostingMetadiscourse":285541,"ActorsFirstPerson":242622,"OrganizationReasoning":182971,"StanceEmphatic":148905,"ActorsPublicEntities":141386,"ConfidenceHedged":130515,"ConfidenceHigh":119696,"PlanningFuture":91199,"PlanningStrategy":77436,"SignpostingAcademicWritingMoves":45355,"CitationNeutral":28827,"StanceModerated":24981,"CitationAuthority":24697,"CitationControversy":7780,"":1},"5":{"":1}}�cfg��neg_key�
|
tagger/model
CHANGED
Binary files a/tagger/model and b/tagger/model differ
|
|
transformer/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 502030632
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22576948b84086ef0634f91f089cb600a12dcf97e5c37e27caf9ddf1d2cebfb8
|
3 |
size 502030632
|