Commit
•
f0c4f9a
1
Parent(s):
3b99e24
xx_cop_sigtyp_trf-0.1.0: Update SIGTYP pipeline
Browse files- README.md +45 -5
- meta.json +44 -44
- parser/model +0 -0
- tagger/model +0 -0
- trainable_lemmatizer/model +0 -0
- trainable_lemmatizer/trees +0 -0
- transformer/model +2 -2
- vocab/strings.json +37 -0
- xx_cop_sigtyp_trf-any-py3-none-any.whl +2 -2
README.md
CHANGED
@@ -13,33 +13,73 @@ model-index:
|
|
13 |
metrics:
|
14 |
- name: TAG (XPOS) Accuracy
|
15 |
type: accuracy
|
16 |
-
value: 0.
|
17 |
- task:
|
18 |
name: LEMMA
|
19 |
type: token-classification
|
20 |
metrics:
|
21 |
- name: Lemma Accuracy
|
22 |
type: accuracy
|
23 |
-
value: 0.
|
24 |
- task:
|
25 |
name: UNLABELED_DEPENDENCIES
|
26 |
type: token-classification
|
27 |
metrics:
|
28 |
- name: Unlabeled Attachment Score (UAS)
|
29 |
type: f_score
|
30 |
-
value: 0.
|
31 |
- task:
|
32 |
name: LABELED_DEPENDENCIES
|
33 |
type: token-classification
|
34 |
metrics:
|
35 |
- name: Labeled Attachment Score (LAS)
|
36 |
type: f_score
|
37 |
-
value: 0.
|
38 |
- task:
|
39 |
name: SENTS
|
40 |
type: token-classification
|
41 |
metrics:
|
42 |
- name: Sentences F-Score
|
43 |
type: f_score
|
44 |
-
value: 0.
|
45 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
metrics:
|
14 |
- name: TAG (XPOS) Accuracy
|
15 |
type: accuracy
|
16 |
+
value: 0.2801932367
|
17 |
- task:
|
18 |
name: LEMMA
|
19 |
type: token-classification
|
20 |
metrics:
|
21 |
- name: Lemma Accuracy
|
22 |
type: accuracy
|
23 |
+
value: 0.2942952007
|
24 |
- task:
|
25 |
name: UNLABELED_DEPENDENCIES
|
26 |
type: token-classification
|
27 |
metrics:
|
28 |
- name: Unlabeled Attachment Score (UAS)
|
29 |
type: f_score
|
30 |
+
value: 0.0226315789
|
31 |
- task:
|
32 |
name: LABELED_DEPENDENCIES
|
33 |
type: token-classification
|
34 |
metrics:
|
35 |
- name: Labeled Attachment Score (LAS)
|
36 |
type: f_score
|
37 |
+
value: 0.0202631579
|
38 |
- task:
|
39 |
name: SENTS
|
40 |
type: token-classification
|
41 |
metrics:
|
42 |
- name: Sentences F-Score
|
43 |
type: f_score
|
44 |
+
value: 0.8864142539
|
45 |
---
|
46 |
+
| Feature | Description |
|
47 |
+
| --- | --- |
|
48 |
+
| **Name** | `xx_cop_sigtyp_trf` |
|
49 |
+
| **Version** | `0.1.0` |
|
50 |
+
| **spaCy** | `>=3.6.1,<3.7.0` |
|
51 |
+
| **Default Pipeline** | `transformer`, `parser`, `trainable_lemmatizer`, `tagger` |
|
52 |
+
| **Components** | `transformer`, `parser`, `trainable_lemmatizer`, `tagger` |
|
53 |
+
| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
|
54 |
+
| **Sources** | n/a |
|
55 |
+
| **License** | n/a |
|
56 |
+
| **Author** | [n/a]() |
|
57 |
+
|
58 |
+
### Label Scheme
|
59 |
+
|
60 |
+
<details>
|
61 |
+
|
62 |
+
<summary>View label scheme (196 labels for 2 components)</summary>
|
63 |
+
|
64 |
+
| Component | Labels |
|
65 |
+
| --- | --- |
|
66 |
+
| **`parser`** | `ROOT`, `acl:relcl`, `advcl`, `advmod`, `appos`, `aux`, `case`, `cc`, `ccomp`, `conj`, `cop`, `csubj`, `dep`, `det`, `discourse`, `dislocated`, `fixed`, `flat`, `iobj`, `mark`, `nmod`, `nsubj`, `nummod`, `obj`, `obl`, `obl:npmod`, `parataxis`, `punct`, `vocative`, `xcomp` |
|
67 |
+
| **`tagger`** | `AAOR`, `ACAUS`, `ACOND`, `ACOND_PPERS`, `ACOND_PPERS__Definite=Def\|Gender=Fem\|Number=Sing\|Person=2\|PronType=Prs`, `ACOND_PPERS__Definite=Def\|Gender=Fem\|Number=Sing\|Person=3\|PronType=Prs`, `ACOND_PPERS__Definite=Def\|Gender=Masc\|Number=Sing\|Person=2\|PronType=Prs`, `ACOND_PPERS__Definite=Def\|Gender=Masc\|Number=Sing\|Person=3\|PronType=Prs`, `ACOND_PPERS__Definite=Def\|Number=Plur\|Person=1\|PronType=Prs`, `ACOND_PPERS__Definite=Def\|Number=Plur\|Person=2\|PronType=Prs`, `ACOND_PPERS__Definite=Def\|Number=Plur\|Person=3\|PronType=Prs`, `ACOND_PPERS__Definite=Def\|Number=Sing\|Person=1\|PronType=Prs`, `ACONJ`, `ACONJ_PPERS`, `ACONJ_PPERS__Definite=Def\|Number=Sing\|Person=1\|PronType=Prs`, `ADV`, `ADV__Foreign=Yes`, `AFUTCONJ`, `AJUS`, `ALIM`, `ANEGAOR__Polarity=Neg`, `ANEGJUS__Polarity=Neg`, `ANEGOPT__Polarity=Neg`, `ANEGPST_PPERS__Definite=Def\|Gender=Fem\|Number=Sing\|Person=2\|Polarity=Neg\|PronType=Prs`, `ANEGPST__Polarity=Neg`, `ANY__Polarity=Neg`, `AOPT`, `AOPT_PPERS`, `AOPT_PPERS__Definite=Def\|Gender=Fem\|Number=Sing\|Person=2\|PronType=Prs`, `AOPT_PPERS__Definite=Def\|Gender=Fem\|Number=Sing\|Person=3\|PronType=Prs`, `AOPT_PPERS__Definite=Def\|Gender=Masc\|Number=Sing\|Person=2\|PronType=Prs`, `AOPT_PPERS__Definite=Def\|Gender=Masc\|Number=Sing\|Person=3\|PronType=Prs`, `AOPT_PPERS__Definite=Def\|Number=Plur\|Person=2\|PronType=Prs`, `AOPT_PPERS__Definite=Def\|Number=Plur\|Person=3\|PronType=Prs`, `AOPT_PPERS__Definite=Def\|Number=Sing\|Person=1\|PronType=Prs`, `APREC`, `APST`, `APST_PPERS__Definite=Def\|Gender=Fem\|Number=Sing\|Person=2\|PronType=Prs`, `ART`, `ART__Definite=Def\|Gender=Fem\|Number=Sing\|PronType=Art`, `ART__Definite=Def\|Gender=Masc\|Number=Sing\|PronType=Art`, `ART__Definite=Def\|Number=Plur\|PronType=Art`, `ART__Definite=Ind\|Number=Sing\|PronType=Art`, `ART__PronType=Art`, `CCIRC`, `CCIRC_PPERS__Definite=Def\|Gender=Fem\|Number=Sing\|Person=2\|PronType=Prs`, `CCIRC_PPERS__Definite=Def\|Gender=Fem\|Number=Sing\|Person=3\|PronType=Prs`, `CFOC`, `CFOC_PPERS`, `CFOC_PPERS__Definite=Def\|Gender=Fem\|Number=Sing\|Person=2\|PronType=Prs`, `CONJ`, `CONJ__Foreign=Yes`, `CONJ__Foreign=Yes\|Polarity=Neg`, `COP__Gender=Fem\|Number=Sing`, `COP__Gender=Masc\|Number=Sing`, `COP__Number=Plur`, `CPRET`, `CPRET_PPERS__Definite=Def\|Gender=Fem\|Number=Sing\|Person=2\|PronType=Prs`, `CREL`, `CREL_PPERS__Definite=Def\|Gender=Fem\|Number=Sing\|Person=2\|PronType=Prs`, `EXIST`, `EXIST__Foreign=Yes`, `EXIST__Polarity=Neg`, `FM`, `FM__Foreign=Yes`, `FM__Foreign=Yes\|Polarity=Neg`, `FM__Polarity=Neg`, `FUT`, `IMOD`, `IMOD_PPERO__Definite=Def\|Number=Sing\|Person=1\|PronType=Prs`, `IMOD__Definite=Def\|PronType=Prs\|Reflex=Yes`, `IMOD__PronType=Tot`, `N`, `NEG__Foreign=Yes\|Polarity=Neg`, `NEG__Polarity=Neg`, `NPROP`, `NPROP__Foreign=Yes`, `NUM__Foreign=Yes\|NumType=Card`, `NUM__NumType=Card`, `N_PPERO__Definite=Def\|Gender=Fem\|Number=Sing\|Person=2\|PronType=Prs`, `N_PPERO__Definite=Def\|Number=Sing\|Person=1\|PronType=Prs`, `N__Foreign=Yes`, `N__PronType=Rcp`, `PDEM`, `PDEM__Definite=Def\|Foreign=Yes\|Number=Plur\|PronType=Dem`, `PDEM__Definite=Def\|Gender=Fem\|Number=Sing\|PronType=Dem`, `PDEM__Definite=Def\|Gender=Masc\|Number=Sing\|PronType=Dem`, `PDEM__Definite=Def\|Number=Plur\|PronType=Dem`, `PINT__PronType=Ind`, `PINT__PronType=Int`, `PPERI__Definite=Def\|Gender=Fem\|Number=Sing\|Person=2\|PronType=Prs`, `PPERI__Definite=Def\|Gender=Fem\|Number=Sing\|Person=3\|PronType=Prs`, `PPERI__Definite=Def\|Gender=Masc\|Number=Sing\|Person=2\|PronType=Prs`, `PPERI__Definite=Def\|Gender=Masc\|Number=Sing\|Person=3\|PronType=Prs`, `PPERI__Definite=Def\|Number=Plur\|Person=1\|PronType=Prs`, `PPERI__Definite=Def\|Number=Plur\|Person=2\|PronType=Prs`, `PPERI__Definite=Def\|Number=Plur\|Person=3\|PronType=Prs`, `PPERI__Definite=Def\|Number=Sing\|Person=1\|PronType=Prs`, `PPERO`, `PPERO__Definite=Def\|Foreign=Yes\|Number=Plur\|Person=3\|PronType=Prs`, `PPERO__Definite=Def\|Gender=Fem\|Number=Sing\|Person=2\|PronType=Prs`, `PPERO__Definite=Def\|Gender=Fem\|Number=Sing\|Person=3\|PronType=Prs`, `PPERO__Definite=Def\|Gender=Masc\|Number=Sing\|Person=2\|PronType=Prs`, `PPERO__Definite=Def\|Gender=Masc\|Number=Sing\|Person=3\|PronType=Prs`, `PPERO__Definite=Def\|Number=Plur\|Person=1\|PronType=Prs`, `PPERO__Definite=Def\|Number=Plur\|Person=2\|PronType=Prs`, `PPERO__Definite=Def\|Number=Plur\|Person=3\|PronType=Prs`, `PPERO__Definite=Def\|Number=Sing\|Person=1\|PronType=Prs`, `PPERO__Definite=Def\|Poss=Yes\|PronType=Prs`, `PPERS`, `PPERS__Definite=Def\|Gender=Fem\|Number=Sing\|Person=2\|PronType=Prs`, `PPERS__Definite=Def\|Gender=Fem\|Number=Sing\|Person=3\|PronType=Prs`, `PPERS__Definite=Def\|Gender=Masc\|Number=Sing\|Person=2\|PronType=Prs`, `PPERS__Definite=Def\|Gender=Masc\|Number=Sing\|Person=3\|PronType=Prs`, `PPERS__Definite=Def\|Number=Plur\|Person=1\|PronType=Prs`, `PPERS__Definite=Def\|Number=Plur\|Person=2\|PronType=Prs`, `PPERS__Definite=Def\|Number=Plur\|Person=3\|PronType=Prs`, `PPERS__Definite=Def\|Number=Sing\|Person=1\|PronType=Prs`, `PPOS`, `PPOS__Definite=Def\|Gender=Fem\|Gender[psor]=Fem\|Number=Sing\|Number[psor]=Sing\|Person=2\|Poss=Yes\|PronType=Prs`, `PPOS__Definite=Def\|Gender=Fem\|Gender[psor]=Fem\|Number=Sing\|Number[psor]=Sing\|Person=3\|Poss=Yes\|PronType=Prs`, `PPOS__Definite=Def\|Gender=Fem\|Gender[psor]=Masc\|Number=Sing\|Number[psor]=Sing\|Person=2\|Poss=Yes\|PronType=Prs`, `PPOS__Definite=Def\|Gender=Fem\|Gender[psor]=Masc\|Number=Sing\|Number[psor]=Sing\|Person=3\|Poss=Yes\|PronType=Prs`, `PPOS__Definite=Def\|Gender=Fem\|Number=Sing\|Number[psor]=Plur\|Person=1\|Poss=Yes\|PronType=Prs`, `PPOS__Definite=Def\|Gender=Fem\|Number=Sing\|Number[psor]=Plur\|Person=2\|Poss=Yes\|PronType=Prs`, `PPOS__Definite=Def\|Gender=Fem\|Number=Sing\|Number[psor]=Plur\|Person=3\|Poss=Yes\|PronType=Prs`, `PPOS__Definite=Def\|Gender=Fem\|Number=Sing\|Number[psor]=Sing\|Person=1\|Poss=Yes\|PronType=Prs`, `PPOS__Definite=Def\|Gender=Fem\|Number=Sing\|Poss=Yes\|PronType=Prs`, `PPOS__Definite=Def\|Gender=Masc\|Gender[psor]=Fem\|Number=Sing\|Number[psor]=Sing\|Person=2\|Poss=Yes\|PronType=Prs`, `PPOS__Definite=Def\|Gender=Masc\|Gender[psor]=Fem\|Number=Sing\|Number[psor]=Sing\|Person=3\|Poss=Yes\|PronType=Prs`, `PPOS__Definite=Def\|Gender=Masc\|Gender[psor]=Masc\|Number=Sing\|Number[psor]=Sing\|Person=2\|Poss=Yes\|PronType=Prs`, `PPOS__Definite=Def\|Gender=Masc\|Gender[psor]=Masc\|Number=Sing\|Number[psor]=Sing\|Person=3\|Poss=Yes\|PronType=Prs`, `PPOS__Definite=Def\|Gender=Masc\|Number=Sing\|Number[psor]=Plur\|Person=1\|Poss=Yes\|PronType=Prs`, `PPOS__Definite=Def\|Gender=Masc\|Number=Sing\|Number[psor]=Plur\|Person=2\|Poss=Yes\|PronType=Prs`, `PPOS__Definite=Def\|Gender=Masc\|Number=Sing\|Number[psor]=Plur\|Person=3\|Poss=Yes\|PronType=Prs`, `PPOS__Definite=Def\|Gender=Masc\|Number=Sing\|Number[psor]=Sing\|Person=1\|Poss=Yes\|PronType=Prs`, `PPOS__Definite=Def\|Gender=Masc\|Number=Sing\|Poss=Yes\|PronType=Prs`, `PPOS__Definite=Def\|Gender[psor]=Fem\|Number=Plur\|Number[psor]=Sing\|Person=2\|Poss=Yes\|PronType=Prs`, `PPOS__Definite=Def\|Gender[psor]=Fem\|Number=Plur\|Number[psor]=Sing\|Person=3\|Poss=Yes\|PronType=Prs`, `PPOS__Definite=Def\|Gender[psor]=Masc\|Number=Plur\|Number[psor]=Sing\|Person=2\|Poss=Yes\|PronType=Prs`, `PPOS__Definite=Def\|Gender[psor]=Masc\|Number=Plur\|Number[psor]=Sing\|Person=3\|Poss=Yes\|PronType=Prs`, `PPOS__Definite=Def\|Number=Plur\|Number[psor]=Plur\|Person=1\|Poss=Yes\|PronType=Prs`, `PPOS__Definite=Def\|Number=Plur\|Number[psor]=Plur\|Person=2\|Poss=Yes\|PronType=Prs`, `PPOS__Definite=Def\|Number=Plur\|Number[psor]=Plur\|Person=3\|Poss=Yes\|PronType=Prs`, `PPOS__Definite=Def\|Number=Plur\|Number[psor]=Sing\|Person=1\|Poss=Yes\|PronType=Prs`, `PPOS__Definite=Def\|Number=Plur\|Poss=Yes\|PronType=Prs`, `PREP`, `PREP_PPERO`, `PREP_PPERO__Definite=Def\|Gender=Fem\|Number=Sing\|Person=2\|PronType=Prs`, `PREP_PPERO__Definite=Def\|Number=Sing\|Person=1\|PronType=Prs`, `PREP__Foreign=Yes`, `PTC`, `PTC__Foreign=Yes`, `PTC__Polarity=Neg`, `PUNCT`, `UNKNOWN`, `UNKNOWN__Foreign=Yes`, `VBD__VerbForm=Fin`, `VIMP__Foreign=Yes\|VerbForm=Fin`, `VIMP__VerbForm=Fin`, `VSTAT__VerbForm=Fin`, `V_PPERO__VerbForm=Fin`, `V__Foreign=Yes\|VerbForm=Fin`, `V__Foreign=Yes\|VerbForm=Inf`, `V__VerbForm=Fin`, `V__VerbForm=Inf` |
|
68 |
+
|
69 |
+
</details>
|
70 |
+
|
71 |
+
### Accuracy
|
72 |
+
|
73 |
+
| Type | Score |
|
74 |
+
| --- | --- |
|
75 |
+
| `DEP_UAS` | 2.26 |
|
76 |
+
| `DEP_LAS` | 2.03 |
|
77 |
+
| `SENTS_P` | 85.41 |
|
78 |
+
| `SENTS_R` | 92.13 |
|
79 |
+
| `SENTS_F` | 88.64 |
|
80 |
+
| `LEMMA_ACC` | 29.43 |
|
81 |
+
| `TAG_ACC` | 28.02 |
|
82 |
+
| `TRANSFORMER_LOSS` | 19921.12 |
|
83 |
+
| `PARSER_LOSS` | 5781.98 |
|
84 |
+
| `TRAINABLE_LEMMATIZER_LOSS` | 192.05 |
|
85 |
+
| `TAGGER_LOSS` | 194.77 |
|
meta.json
CHANGED
@@ -236,18 +236,18 @@
|
|
236 |
|
237 |
],
|
238 |
"performance":{
|
239 |
-
"dep_uas":0.
|
240 |
-
"dep_las":0.
|
241 |
"dep_las_per_type":{
|
242 |
"cc":{
|
243 |
-
"p":0.
|
244 |
-
"r":0.
|
245 |
-
"f":0.
|
246 |
},
|
247 |
"mark":{
|
248 |
-
"p":0.
|
249 |
-
"r":0.
|
250 |
-
"f":0.
|
251 |
},
|
252 |
"nsubj":{
|
253 |
"p":0.0,
|
@@ -255,14 +255,14 @@
|
|
255 |
"f":0.0
|
256 |
},
|
257 |
"root":{
|
258 |
-
"p":0.
|
259 |
-
"r":0.
|
260 |
-
"f":0.
|
261 |
},
|
262 |
"case":{
|
263 |
-
"p":0.
|
264 |
-
"r":0.
|
265 |
-
"f":0.
|
266 |
},
|
267 |
"obl":{
|
268 |
"p":0.0,
|
@@ -290,14 +290,14 @@
|
|
290 |
"f":0.0
|
291 |
},
|
292 |
"advmod":{
|
293 |
-
"p":0.
|
294 |
-
"r":0.
|
295 |
-
"f":0.
|
296 |
},
|
297 |
"advcl":{
|
298 |
-
"p":
|
299 |
-
"r":0.
|
300 |
-
"f":0.
|
301 |
},
|
302 |
"obj":{
|
303 |
"p":0.0,
|
@@ -310,9 +310,9 @@
|
|
310 |
"f":0.0
|
311 |
},
|
312 |
"parataxis":{
|
313 |
-
"p":0.
|
314 |
-
"r":0.
|
315 |
-
"f":0.
|
316 |
},
|
317 |
"nmod":{
|
318 |
"p":0.0,
|
@@ -320,9 +320,9 @@
|
|
320 |
"f":0.0
|
321 |
},
|
322 |
"cop":{
|
323 |
-
"p":0.
|
324 |
-
"r":0.
|
325 |
-
"f":0.
|
326 |
},
|
327 |
"appos":{
|
328 |
"p":0.0,
|
@@ -335,9 +335,9 @@
|
|
335 |
"f":0.0
|
336 |
},
|
337 |
"conj":{
|
338 |
-
"p":0.
|
339 |
-
"r":0.
|
340 |
-
"f":0.
|
341 |
},
|
342 |
"xcomp":{
|
343 |
"p":0.0,
|
@@ -365,9 +365,9 @@
|
|
365 |
"f":0.0
|
366 |
},
|
367 |
"discourse":{
|
368 |
-
"p":
|
369 |
-
"r":0.
|
370 |
-
"f":0.
|
371 |
},
|
372 |
"amod":{
|
373 |
"p":0.0,
|
@@ -385,9 +385,9 @@
|
|
385 |
"f":0.0
|
386 |
},
|
387 |
"flat":{
|
388 |
-
"p":0.
|
389 |
-
"r":0.
|
390 |
-
"f":0.
|
391 |
},
|
392 |
"obl:npmod":{
|
393 |
"p":0.0,
|
@@ -400,15 +400,15 @@
|
|
400 |
"f":0.0
|
401 |
}
|
402 |
},
|
403 |
-
"sents_p":0.
|
404 |
-
"sents_r":0.
|
405 |
-
"sents_f":0.
|
406 |
-
"lemma_acc":0.
|
407 |
-
"tag_acc":0.
|
408 |
-
"transformer_loss":
|
409 |
-
"parser_loss":
|
410 |
-
"trainable_lemmatizer_loss":
|
411 |
-
"tagger_loss":
|
412 |
},
|
413 |
"requirements":[
|
414 |
"spacy-transformers>=1.3.3,<1.4.0"
|
|
|
236 |
|
237 |
],
|
238 |
"performance":{
|
239 |
+
"dep_uas":0.0226315789,
|
240 |
+
"dep_las":0.0202631579,
|
241 |
"dep_las_per_type":{
|
242 |
"cc":{
|
243 |
+
"p":0.8333333333,
|
244 |
+
"r":0.0872093023,
|
245 |
+
"f":0.1578947368
|
246 |
},
|
247 |
"mark":{
|
248 |
+
"p":0.6666666667,
|
249 |
+
"r":0.0046296296,
|
250 |
+
"f":0.0091954023
|
251 |
},
|
252 |
"nsubj":{
|
253 |
"p":0.0,
|
|
|
255 |
"f":0.0
|
256 |
},
|
257 |
"root":{
|
258 |
+
"p":0.213592233,
|
259 |
+
"r":0.1018518519,
|
260 |
+
"f":0.1379310345
|
261 |
},
|
262 |
"case":{
|
263 |
+
"p":0.5,
|
264 |
+
"r":0.0012886598,
|
265 |
+
"f":0.0025706941
|
266 |
},
|
267 |
"obl":{
|
268 |
"p":0.0,
|
|
|
290 |
"f":0.0
|
291 |
},
|
292 |
"advmod":{
|
293 |
+
"p":0.5789473684,
|
294 |
+
"r":0.0785714286,
|
295 |
+
"f":0.1383647799
|
296 |
},
|
297 |
"advcl":{
|
298 |
+
"p":1.0,
|
299 |
+
"r":0.0064102564,
|
300 |
+
"f":0.0127388535
|
301 |
},
|
302 |
"obj":{
|
303 |
"p":0.0,
|
|
|
310 |
"f":0.0
|
311 |
},
|
312 |
"parataxis":{
|
313 |
+
"p":0.125,
|
314 |
+
"r":0.0138888889,
|
315 |
+
"f":0.025
|
316 |
},
|
317 |
"nmod":{
|
318 |
"p":0.0,
|
|
|
320 |
"f":0.0
|
321 |
},
|
322 |
"cop":{
|
323 |
+
"p":0.4117647059,
|
324 |
+
"r":0.1346153846,
|
325 |
+
"f":0.2028985507
|
326 |
},
|
327 |
"appos":{
|
328 |
"p":0.0,
|
|
|
335 |
"f":0.0
|
336 |
},
|
337 |
"conj":{
|
338 |
+
"p":0.75,
|
339 |
+
"r":0.0218978102,
|
340 |
+
"f":0.0425531915
|
341 |
},
|
342 |
"xcomp":{
|
343 |
"p":0.0,
|
|
|
365 |
"f":0.0
|
366 |
},
|
367 |
"discourse":{
|
368 |
+
"p":1.0,
|
369 |
+
"r":0.2,
|
370 |
+
"f":0.3333333333
|
371 |
},
|
372 |
"amod":{
|
373 |
"p":0.0,
|
|
|
385 |
"f":0.0
|
386 |
},
|
387 |
"flat":{
|
388 |
+
"p":0.6666666667,
|
389 |
+
"r":0.4,
|
390 |
+
"f":0.5
|
391 |
},
|
392 |
"obl:npmod":{
|
393 |
"p":0.0,
|
|
|
400 |
"f":0.0
|
401 |
}
|
402 |
},
|
403 |
+
"sents_p":0.8540772532,
|
404 |
+
"sents_r":0.9212962963,
|
405 |
+
"sents_f":0.8864142539,
|
406 |
+
"lemma_acc":0.2942952007,
|
407 |
+
"tag_acc":0.2801932367,
|
408 |
+
"transformer_loss":199.2112121448,
|
409 |
+
"parser_loss":57.8198015797,
|
410 |
+
"trainable_lemmatizer_loss":1.9204635808,
|
411 |
+
"tagger_loss":1.9476538145
|
412 |
},
|
413 |
"requirements":[
|
414 |
"spacy-transformers>=1.3.3,<1.4.0"
|
parser/model
CHANGED
Binary files a/parser/model and b/parser/model differ
|
|
tagger/model
CHANGED
Binary files a/tagger/model and b/tagger/model differ
|
|
trainable_lemmatizer/model
CHANGED
Binary files a/trainable_lemmatizer/model and b/trainable_lemmatizer/model differ
|
|
trainable_lemmatizer/trees
CHANGED
Binary files a/trainable_lemmatizer/trees and b/trainable_lemmatizer/trees differ
|
|
transformer/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 sha256:4b351f1da3b0008e772c769d09a7280b4c90fb59f3911321324d3caa049850b6
|
3 |
+
size 509231398
|
vocab/strings.json
CHANGED
@@ -64,9 +64,14 @@
|
|
64 |
"........",
|
65 |
".........",
|
66 |
"..........",
|
|
|
|
|
67 |
".....\u2c9f...",
|
68 |
"....x...",
|
|
|
69 |
"..]",
|
|
|
|
|
70 |
".]\u2ca5",
|
71 |
"._.",
|
72 |
"/",
|
@@ -583,6 +588,9 @@
|
|
583 |
"Yes",
|
584 |
"[",
|
585 |
"[-:",
|
|
|
|
|
|
|
586 |
"[.....]",
|
587 |
"[....]",
|
588 |
"[....]x",
|
@@ -630,6 +638,7 @@
|
|
630 |
"acaus",
|
631 |
"ace",
|
632 |
"acl:relcl",
|
|
|
633 |
"acond",
|
634 |
"acond_ppers",
|
635 |
"acond_ppers__definite=def|gender=fem|number=sing|person=2|prontype=prs",
|
@@ -645,6 +654,10 @@
|
|
645 |
"aconj_ppers__definite=def|number=sing|person=1|prontype=prs",
|
646 |
"adv",
|
647 |
"adv__foreign=yes",
|
|
|
|
|
|
|
|
|
648 |
"afutconj",
|
649 |
"ajus",
|
650 |
"alim",
|
@@ -663,6 +676,9 @@
|
|
663 |
"aopt_ppers__definite=def|number=plur|person=2|prontype=prs",
|
664 |
"aopt_ppers__definite=def|number=plur|person=3|prontype=prs",
|
665 |
"aopt_ppers__definite=def|number=sing|person=1|prontype=prs",
|
|
|
|
|
|
|
666 |
"aprec",
|
667 |
"apst",
|
668 |
"apst_ppers__definite=def|gender=fem|number=sing|person=2|prontype=prs",
|
@@ -675,6 +691,7 @@
|
|
675 |
"art__definite=ind|number=sing|prontype=art",
|
676 |
"art__prontype=art",
|
677 |
"ase",
|
|
|
678 |
"b",
|
679 |
"b.",
|
680 |
"c",
|
@@ -684,7 +701,9 @@
|
|
684 |
"ccirc",
|
685 |
"ccirc_ppers__definite=def|gender=fem|number=sing|person=2|prontype=prs",
|
686 |
"ccirc_ppers__definite=def|gender=fem|number=sing|person=3|prontype=prs",
|
|
|
687 |
"cc||conj",
|
|
|
688 |
"ce>",
|
689 |
"cfoc",
|
690 |
"cfoc_ppers",
|
@@ -692,6 +711,7 @@
|
|
692 |
"compound",
|
693 |
"conj__foreign=yes",
|
694 |
"conj__foreign=yes|polarity=neg",
|
|
|
695 |
"cop__gender=fem|number=sing",
|
696 |
"cop__gender=masc|number=sing",
|
697 |
"cop__number=plur",
|
@@ -759,8 +779,12 @@
|
|
759 |
"definite=def|poss=yes|prontype=prs",
|
760 |
"definite=def|prontype=prs|reflex=yes",
|
761 |
"definite=ind|number=sing|prontype=art",
|
|
|
|
|
762 |
"discourse",
|
763 |
"dislocated",
|
|
|
|
|
764 |
"dum",
|
765 |
"e",
|
766 |
"e.",
|
@@ -807,6 +831,7 @@
|
|
807 |
"lur",
|
808 |
"m",
|
809 |
"m.",
|
|
|
810 |
"mod",
|
811 |
"n",
|
812 |
"n.",
|
@@ -817,12 +842,14 @@
|
|
817 |
"nct",
|
818 |
"neg__foreign=yes|polarity=neg",
|
819 |
"neg__polarity=neg",
|
|
|
820 |
"nprop",
|
821 |
"nprop__foreign=yes",
|
822 |
"num__foreign=yes|numtype=card",
|
823 |
"num__numtype=card",
|
824 |
"number=plur",
|
825 |
"nummod",
|
|
|
826 |
"numtype=card",
|
827 |
"o",
|
828 |
"o.",
|
@@ -833,6 +860,9 @@
|
|
833 |
"o_O",
|
834 |
"o_o",
|
835 |
"obl:npmod",
|
|
|
|
|
|
|
836 |
"omp",
|
837 |
"onj",
|
838 |
"orphan",
|
@@ -4422,10 +4452,12 @@
|
|
4422 |
"\u2c87\u2cb1\u2c9b",
|
4423 |
"\u2c87\u2cb1\u2ca3\u2c9f\u2c9b",
|
4424 |
"\u2c89",
|
|
|
4425 |
"\u2c89......\u2c99....",
|
4426 |
"\u2c89[",
|
4427 |
"\u2c89[.....]",
|
4428 |
"\u2c89_",
|
|
|
4429 |
"\u2c89_\u2c9b\u2ca7\u2c9f",
|
4430 |
"\u2c89\u03e3",
|
4431 |
"\u2c89\u03e3\u03e3\u2c89",
|
@@ -7137,6 +7169,7 @@
|
|
7137 |
"\u2c97\u2cb1\u2ca1",
|
7138 |
"\u2c97\u2cb1\u2ca5",
|
7139 |
"\u2c99",
|
|
|
7140 |
"\u2c99\u03e3\u2c89",
|
7141 |
"\u2c99\u03e3\u2c93\u2ca3",
|
7142 |
"\u2c99\u03e5\u2c93",
|
@@ -8434,6 +8467,7 @@
|
|
8434 |
"\u2c99\u2cb1\u2ca5",
|
8435 |
"\u2c99\u2cb1\u2ca9\u2ca5\u2c8f\u2ca5",
|
8436 |
"\u2c9b",
|
|
|
8437 |
"\u2c9b_\u2c9b\u2ca7",
|
8438 |
"\u2c9b_\u2c9b\u2ca7\u2c9f",
|
8439 |
"\u2c9b\u03e3\u03e5\u2c89",
|
@@ -10658,6 +10692,7 @@
|
|
10658 |
"\u2c9d\u2c93\u2c81",
|
10659 |
"\u2c9d\u2c93\u2ca5",
|
10660 |
"\u2c9f",
|
|
|
10661 |
"\u2c9f\u03e3",
|
10662 |
"\u2c9f\u03e3\u03e5",
|
10663 |
"\u2c9f\u03e3\u2c89",
|
@@ -10770,6 +10805,7 @@
|
|
10770 |
"\u2c9f\u2ca5\u2c89",
|
10771 |
"\u2c9f\u2ca5\u2c95",
|
10772 |
"\u2c9f\u2ca5\u2c9b",
|
|
|
10773 |
"\u2c9f\u2ca7\u03e5",
|
10774 |
"\u2c9f\u2ca7\u03e9",
|
10775 |
"\u2c9f\u2ca7\u2c89",
|
@@ -11588,6 +11624,7 @@
|
|
11588 |
"\u2ca1\u2ca5\u2cb1\u2ca7\u2c8f\u2ca3",
|
11589 |
"\u2ca1\u2ca7\u2c81\u03eb\u2ca3\u2c9f",
|
11590 |
"\u2ca1\u2ca7\u2c81\u2c89\u2c93\u2c9f",
|
|
|
11591 |
"\u2ca1\u2ca7\u2c83\u2c83\u2c9f",
|
11592 |
"\u2ca1\u2ca7\u2c89\u2c97\u2cb1\u2c9b\u2c8f\u2ca5",
|
11593 |
"\u2ca1\u2ca7\u2c8f",
|
|
|
64 |
"........",
|
65 |
".........",
|
66 |
"..........",
|
67 |
+
"......\u2c99....",
|
68 |
+
".....]",
|
69 |
".....\u2c9f...",
|
70 |
"....x...",
|
71 |
+
"...]",
|
72 |
"..]",
|
73 |
+
"..\u2c99....",
|
74 |
+
"..\u2c9f...",
|
75 |
".]\u2ca5",
|
76 |
"._.",
|
77 |
"/",
|
|
|
588 |
"Yes",
|
589 |
"[",
|
590 |
"[-:",
|
591 |
+
"[..",
|
592 |
+
"[...",
|
593 |
+
"[.....",
|
594 |
"[.....]",
|
595 |
"[....]",
|
596 |
"[....]x",
|
|
|
638 |
"acaus",
|
639 |
"ace",
|
640 |
"acl:relcl",
|
641 |
+
"acl:relcl||nsubj",
|
642 |
"acond",
|
643 |
"acond_ppers",
|
644 |
"acond_ppers__definite=def|gender=fem|number=sing|person=2|prontype=prs",
|
|
|
654 |
"aconj_ppers__definite=def|number=sing|person=1|prontype=prs",
|
655 |
"adv",
|
656 |
"adv__foreign=yes",
|
657 |
+
"advcl||acl:relcl",
|
658 |
+
"advmod||acl:relcl",
|
659 |
+
"advmod||advcl",
|
660 |
+
"advmod||obl",
|
661 |
"afutconj",
|
662 |
"ajus",
|
663 |
"alim",
|
|
|
676 |
"aopt_ppers__definite=def|number=plur|person=2|prontype=prs",
|
677 |
"aopt_ppers__definite=def|number=plur|person=3|prontype=prs",
|
678 |
"aopt_ppers__definite=def|number=sing|person=1|prontype=prs",
|
679 |
+
"appos||dislocated",
|
680 |
+
"appos||nmod",
|
681 |
+
"appos||nsubj",
|
682 |
"aprec",
|
683 |
"apst",
|
684 |
"apst_ppers__definite=def|gender=fem|number=sing|person=2|prontype=prs",
|
|
|
691 |
"art__definite=ind|number=sing|prontype=art",
|
692 |
"art__prontype=art",
|
693 |
"ase",
|
694 |
+
"aux||nsubj",
|
695 |
"b",
|
696 |
"b.",
|
697 |
"c",
|
|
|
701 |
"ccirc",
|
702 |
"ccirc_ppers__definite=def|gender=fem|number=sing|person=2|prontype=prs",
|
703 |
"ccirc_ppers__definite=def|gender=fem|number=sing|person=3|prontype=prs",
|
704 |
+
"ccomp||advcl",
|
705 |
"cc||conj",
|
706 |
+
"cc||nsubj",
|
707 |
"ce>",
|
708 |
"cfoc",
|
709 |
"cfoc_ppers",
|
|
|
711 |
"compound",
|
712 |
"conj__foreign=yes",
|
713 |
"conj__foreign=yes|polarity=neg",
|
714 |
+
"conj||nsubj",
|
715 |
"cop__gender=fem|number=sing",
|
716 |
"cop__gender=masc|number=sing",
|
717 |
"cop__number=plur",
|
|
|
779 |
"definite=def|poss=yes|prontype=prs",
|
780 |
"definite=def|prontype=prs|reflex=yes",
|
781 |
"definite=ind|number=sing|prontype=art",
|
782 |
+
"det||dislocated",
|
783 |
+
"det||nsubj",
|
784 |
"discourse",
|
785 |
"dislocated",
|
786 |
+
"dislocated||advcl",
|
787 |
+
"dislocated||xcomp",
|
788 |
"dum",
|
789 |
"e",
|
790 |
"e.",
|
|
|
831 |
"lur",
|
832 |
"m",
|
833 |
"m.",
|
834 |
+
"mark||advcl",
|
835 |
"mod",
|
836 |
"n",
|
837 |
"n.",
|
|
|
842 |
"nct",
|
843 |
"neg__foreign=yes|polarity=neg",
|
844 |
"neg__polarity=neg",
|
845 |
+
"nmod||obl",
|
846 |
"nprop",
|
847 |
"nprop__foreign=yes",
|
848 |
"num__foreign=yes|numtype=card",
|
849 |
"num__numtype=card",
|
850 |
"number=plur",
|
851 |
"nummod",
|
852 |
+
"nummod||obl",
|
853 |
"numtype=card",
|
854 |
"o",
|
855 |
"o.",
|
|
|
860 |
"o_O",
|
861 |
"o_o",
|
862 |
"obl:npmod",
|
863 |
+
"obl:npmod||dislocated",
|
864 |
+
"obl||acl:relcl",
|
865 |
+
"obl||advcl",
|
866 |
"omp",
|
867 |
"onj",
|
868 |
"orphan",
|
|
|
4452 |
"\u2c87\u2cb1\u2c9b",
|
4453 |
"\u2c87\u2cb1\u2ca3\u2c9f\u2c9b",
|
4454 |
"\u2c89",
|
4455 |
+
"\u2c89......",
|
4456 |
"\u2c89......\u2c99....",
|
4457 |
"\u2c89[",
|
4458 |
"\u2c89[.....]",
|
4459 |
"\u2c89_",
|
4460 |
+
"\u2c89_\u2c81\u2c9b\u2c9f\u2c95",
|
4461 |
"\u2c89_\u2c9b\u2ca7\u2c9f",
|
4462 |
"\u2c89\u03e3",
|
4463 |
"\u2c89\u03e3\u03e3\u2c89",
|
|
|
7169 |
"\u2c97\u2cb1\u2ca1",
|
7170 |
"\u2c97\u2cb1\u2ca5",
|
7171 |
"\u2c99",
|
7172 |
+
"\u2c99....",
|
7173 |
"\u2c99\u03e3\u2c89",
|
7174 |
"\u2c99\u03e3\u2c93\u2ca3",
|
7175 |
"\u2c99\u03e5\u2c93",
|
|
|
8467 |
"\u2c99\u2cb1\u2ca5",
|
8468 |
"\u2c99\u2cb1\u2ca9\u2ca5\u2c8f\u2ca5",
|
8469 |
"\u2c9b",
|
8470 |
+
"\u2c9b_\u2c81\u2c9b",
|
8471 |
"\u2c9b_\u2c9b\u2ca7",
|
8472 |
"\u2c9b_\u2c9b\u2ca7\u2c9f",
|
8473 |
"\u2c9b\u03e3\u03e5\u2c89",
|
|
|
10692 |
"\u2c9d\u2c93\u2c81",
|
10693 |
"\u2c9d\u2c93\u2ca5",
|
10694 |
"\u2c9f",
|
10695 |
+
"\u2c9f...",
|
10696 |
"\u2c9f\u03e3",
|
10697 |
"\u2c9f\u03e3\u03e5",
|
10698 |
"\u2c9f\u03e3\u2c89",
|
|
|
10805 |
"\u2c9f\u2ca5\u2c89",
|
10806 |
"\u2c9f\u2ca5\u2c95",
|
10807 |
"\u2c9f\u2ca5\u2c9b",
|
10808 |
+
"\u2c9f\u2ca7",
|
10809 |
"\u2c9f\u2ca7\u03e5",
|
10810 |
"\u2c9f\u2ca7\u03e9",
|
10811 |
"\u2c9f\u2ca7\u2c89",
|
|
|
11624 |
"\u2ca1\u2ca5\u2cb1\u2ca7\u2c8f\u2ca3",
|
11625 |
"\u2ca1\u2ca7\u2c81\u03eb\u2ca3\u2c9f",
|
11626 |
"\u2ca1\u2ca7\u2c81\u2c89\u2c93\u2c9f",
|
11627 |
+
"\u2ca1\u2ca7\u2c81\u2c99\u2c9f\u2c9f\u2ca9",
|
11628 |
"\u2ca1\u2ca7\u2c83\u2c83\u2c9f",
|
11629 |
"\u2ca1\u2ca7\u2c89\u2c97\u2cb1\u2c9b\u2c8f\u2ca5",
|
11630 |
"\u2ca1\u2ca7\u2c8f",
|
xx_cop_sigtyp_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 sha256:7c0cba75d805c86273e251b52838962141fb1da7f9db96642e975aae6218a6e9
|
3 |
+
size 467235628
|