Update spaCy pipeline
Browse files- README.md +27 -27
- config.cfg +4 -4
- grc_perseus_lg-any-py3-none-any.whl +2 -2
- lemmatizer/cfg +0 -0
- lemmatizer/model +2 -2
- lemmatizer/trees +2 -2
- meta.json +129 -154
- morphologizer/model +0 -0
- ner/model +0 -0
- ner/moves +1 -1
- parser/model +2 -2
- parser/moves +1 -1
- tagger/model +0 -0
- tok2vec/model +1 -1
- vocab/strings.json +2 -2
README.md
CHANGED
@@ -13,70 +13,70 @@ 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 |
- task:
|
24 |
name: TAG
|
25 |
type: token-classification
|
26 |
metrics:
|
27 |
- name: TAG (XPOS) Accuracy
|
28 |
type: accuracy
|
29 |
-
value: 0.
|
30 |
- task:
|
31 |
name: POS
|
32 |
type: token-classification
|
33 |
metrics:
|
34 |
- name: POS (UPOS) Accuracy
|
35 |
type: accuracy
|
36 |
-
value: 0.
|
37 |
- task:
|
38 |
name: MORPH
|
39 |
type: token-classification
|
40 |
metrics:
|
41 |
- name: Morph (UFeats) Accuracy
|
42 |
type: accuracy
|
43 |
-
value: 0.
|
44 |
- task:
|
45 |
name: LEMMA
|
46 |
type: token-classification
|
47 |
metrics:
|
48 |
- name: Lemma Accuracy
|
49 |
type: accuracy
|
50 |
-
value: 0.
|
51 |
- task:
|
52 |
name: UNLABELED_DEPENDENCIES
|
53 |
type: token-classification
|
54 |
metrics:
|
55 |
- name: Unlabeled Attachment Score (UAS)
|
56 |
type: f_score
|
57 |
-
value: 0.
|
58 |
- task:
|
59 |
name: LABELED_DEPENDENCIES
|
60 |
type: token-classification
|
61 |
metrics:
|
62 |
- name: Labeled Attachment Score (LAS)
|
63 |
type: f_score
|
64 |
-
value: 0.
|
65 |
- task:
|
66 |
name: SENTS
|
67 |
type: token-classification
|
68 |
metrics:
|
69 |
- name: Sentences F-Score
|
70 |
type: f_score
|
71 |
-
value: 0.
|
72 |
---
|
73 |
| Feature | Description |
|
74 |
| --- | --- |
|
75 |
| **Name** | `grc_perseus_lg` |
|
76 |
-
| **Version** | `3.7` |
|
77 |
-
| **spaCy** | `>=3.7.
|
78 |
-
| **Default Pipeline** | `tok2vec`, `morphologizer`, `tagger`, `parser`, `lemmatizer`, `
|
79 |
-
| **Components** | `tok2vec`, `morphologizer`, `tagger`, `parser`, `lemmatizer`, `
|
80 |
| **Vectors** | -1 keys, 200000 unique vectors (300 dimensions) |
|
81 |
| **Sources** | n/a |
|
82 |
| **License** | n/a |
|
@@ -100,21 +100,21 @@ model-index:
|
|
100 |
|
101 |
| Type | Score |
|
102 |
| --- | --- |
|
103 |
-
| `POS_ACC` |
|
104 |
-
| `MORPH_ACC` | 73.
|
105 |
-
| `TAG_ACC` | 77.
|
106 |
-
| `DEP_UAS` | 57.
|
107 |
-
| `DEP_LAS` | 48.
|
108 |
-
| `SENTS_P` |
|
109 |
-
| `SENTS_R` |
|
110 |
-
| `SENTS_F` | 94.
|
111 |
-
| `LEMMA_ACC` | 97.
|
112 |
| `ENTS_F` | 0.00 |
|
113 |
| `ENTS_P` | 0.00 |
|
114 |
| `ENTS_R` | 0.00 |
|
115 |
| `ENTS_PER_TYPE` | 0.00 |
|
116 |
-
| `TOK2VEC_LOSS` |
|
117 |
-
| `MORPHOLOGIZER_LOSS` |
|
118 |
-
| `TAGGER_LOSS` |
|
119 |
-
| `PARSER_LOSS` |
|
120 |
| `NER_LOSS` | 0.00 |
|
|
|
13 |
metrics:
|
14 |
- name: NER Precision
|
15 |
type: precision
|
16 |
+
value: 0.0
|
17 |
- name: NER Recall
|
18 |
type: recall
|
19 |
+
value: 0.0
|
20 |
- name: NER F Score
|
21 |
type: f_score
|
22 |
+
value: 0.0
|
23 |
- task:
|
24 |
name: TAG
|
25 |
type: token-classification
|
26 |
metrics:
|
27 |
- name: TAG (XPOS) Accuracy
|
28 |
type: accuracy
|
29 |
+
value: 0.7722642575
|
30 |
- task:
|
31 |
name: POS
|
32 |
type: token-classification
|
33 |
metrics:
|
34 |
- name: POS (UPOS) Accuracy
|
35 |
type: accuracy
|
36 |
+
value: 0.7983014862
|
37 |
- task:
|
38 |
name: MORPH
|
39 |
type: token-classification
|
40 |
metrics:
|
41 |
- name: Morph (UFeats) Accuracy
|
42 |
type: accuracy
|
43 |
+
value: 0.7394741597
|
44 |
- task:
|
45 |
name: LEMMA
|
46 |
type: token-classification
|
47 |
metrics:
|
48 |
- name: Lemma Accuracy
|
49 |
type: accuracy
|
50 |
+
value: 0.9766685488
|
51 |
- task:
|
52 |
name: UNLABELED_DEPENDENCIES
|
53 |
type: token-classification
|
54 |
metrics:
|
55 |
- name: Unlabeled Attachment Score (UAS)
|
56 |
type: f_score
|
57 |
+
value: 0.5785607915
|
58 |
- task:
|
59 |
name: LABELED_DEPENDENCIES
|
60 |
type: token-classification
|
61 |
metrics:
|
62 |
- name: Labeled Attachment Score (LAS)
|
63 |
type: f_score
|
64 |
+
value: 0.4840101971
|
65 |
- task:
|
66 |
name: SENTS
|
67 |
type: token-classification
|
68 |
metrics:
|
69 |
- name: Sentences F-Score
|
70 |
type: f_score
|
71 |
+
value: 0.941991342
|
72 |
---
|
73 |
| Feature | Description |
|
74 |
| --- | --- |
|
75 |
| **Name** | `grc_perseus_lg` |
|
76 |
+
| **Version** | `3.7.5` |
|
77 |
+
| **spaCy** | `>=3.7.5,<3.8.0` |
|
78 |
+
| **Default Pipeline** | `tok2vec`, `morphologizer`, `tagger`, `parser`, `lemmatizer`, `ner`, `attribute_ruler` |
|
79 |
+
| **Components** | `tok2vec`, `morphologizer`, `tagger`, `parser`, `lemmatizer`, `ner`, `attribute_ruler` |
|
80 |
| **Vectors** | -1 keys, 200000 unique vectors (300 dimensions) |
|
81 |
| **Sources** | n/a |
|
82 |
| **License** | n/a |
|
|
|
100 |
|
101 |
| Type | Score |
|
102 |
| --- | --- |
|
103 |
+
| `POS_ACC` | 79.83 |
|
104 |
+
| `MORPH_ACC` | 73.95 |
|
105 |
+
| `TAG_ACC` | 77.23 |
|
106 |
+
| `DEP_UAS` | 57.86 |
|
107 |
+
| `DEP_LAS` | 48.40 |
|
108 |
+
| `SENTS_P` | 92.75 |
|
109 |
+
| `SENTS_R` | 95.69 |
|
110 |
+
| `SENTS_F` | 94.20 |
|
111 |
+
| `LEMMA_ACC` | 97.67 |
|
112 |
| `ENTS_F` | 0.00 |
|
113 |
| `ENTS_P` | 0.00 |
|
114 |
| `ENTS_R` | 0.00 |
|
115 |
| `ENTS_PER_TYPE` | 0.00 |
|
116 |
+
| `TOK2VEC_LOSS` | 474361054.54 |
|
117 |
+
| `MORPHOLOGIZER_LOSS` | 41731347.69 |
|
118 |
+
| `TAGGER_LOSS` | 35952390.56 |
|
119 |
+
| `PARSER_LOSS` | 59028447.37 |
|
120 |
| `NER_LOSS` | 0.00 |
|
config.cfg
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
[paths]
|
2 |
-
train = "corpus/ud
|
3 |
-
dev = "corpus/ud
|
4 |
vectors = "vectors/large"
|
5 |
init_tok2vec = "data/pretrained_weights/model32.bin"
|
6 |
raw_text = "raw_text"
|
@@ -11,7 +11,7 @@ seed = 0
|
|
11 |
|
12 |
[nlp]
|
13 |
lang = "grc"
|
14 |
-
pipeline = ["tok2vec","morphologizer","tagger","parser","lemmatizer","
|
15 |
batch_size = 128
|
16 |
disabled = []
|
17 |
before_creation = null
|
@@ -180,7 +180,7 @@ accumulate_gradient = 1
|
|
180 |
patience = 5000
|
181 |
max_epochs = 0
|
182 |
max_steps = 20000
|
183 |
-
eval_frequency =
|
184 |
frozen_components = ["lemmatizer"]
|
185 |
annotating_components = []
|
186 |
before_to_disk = null
|
|
|
1 |
[paths]
|
2 |
+
train = "corpus/train/grc_perseus-ud-train.spacy"
|
3 |
+
dev = "corpus/dev/grc_perseus-ud-dev.spacy"
|
4 |
vectors = "vectors/large"
|
5 |
init_tok2vec = "data/pretrained_weights/model32.bin"
|
6 |
raw_text = "raw_text"
|
|
|
11 |
|
12 |
[nlp]
|
13 |
lang = "grc"
|
14 |
+
pipeline = ["tok2vec","morphologizer","tagger","parser","lemmatizer","ner","attribute_ruler"]
|
15 |
batch_size = 128
|
16 |
disabled = []
|
17 |
before_creation = null
|
|
|
180 |
patience = 5000
|
181 |
max_epochs = 0
|
182 |
max_steps = 20000
|
183 |
+
eval_frequency = 1000
|
184 |
frozen_components = ["lemmatizer"]
|
185 |
annotating_components = []
|
186 |
before_to_disk = null
|
grc_perseus_lg-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:b792480ead949154fb99dda98ac883923d97476c5e6ec6b6685aaefaa70356e5
|
3 |
+
size 284594384
|
lemmatizer/cfg
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
lemmatizer/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 sha256:4d5013a0dc1727b911c7f243338801fdc212f29d54ddfdb88a7abbec84448a54
|
3 |
+
size 29442044
|
lemmatizer/trees
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 sha256:86606a185ea3cbd4c6f071029121d17265dfe9d5a468c6dbeb071a5808cf49f9
|
3 |
+
size 6516433
|
meta.json
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
{
|
2 |
"lang":"grc",
|
3 |
"name":"perseus_lg",
|
4 |
-
"version":"3.7",
|
5 |
"description":"",
|
6 |
"author":"",
|
7 |
"email":"",
|
8 |
"url":"",
|
9 |
"license":"",
|
10 |
-
"spacy_version":">=3.7.
|
11 |
-
"spacy_git_version":"
|
12 |
"vectors":{
|
13 |
"width":300,
|
14 |
"vectors":200000,
|
@@ -937,15 +937,11 @@
|
|
937 |
"vocative",
|
938 |
"xcomp"
|
939 |
],
|
940 |
-
"
|
941 |
|
942 |
],
|
943 |
-
"
|
944 |
-
|
945 |
-
"LANGUAGE",
|
946 |
-
"LOC",
|
947 |
-
"NORP",
|
948 |
-
"PERSON"
|
949 |
]
|
950 |
},
|
951 |
"pipeline":[
|
@@ -954,8 +950,8 @@
|
|
954 |
"tagger",
|
955 |
"parser",
|
956 |
"lemmatizer",
|
957 |
-
"
|
958 |
-
"
|
959 |
],
|
960 |
"components":[
|
961 |
"tok2vec",
|
@@ -963,160 +959,160 @@
|
|
963 |
"tagger",
|
964 |
"parser",
|
965 |
"lemmatizer",
|
966 |
-
"
|
967 |
-
"
|
968 |
],
|
969 |
"disabled":[
|
970 |
|
971 |
],
|
972 |
"performance":{
|
973 |
-
"pos_acc":0.
|
974 |
-
"morph_acc":0.
|
975 |
"morph_per_feat":{
|
976 |
"Case":{
|
977 |
-
"p":0.
|
978 |
-
"r":0.
|
979 |
-
"f":0.
|
980 |
},
|
981 |
"Gender":{
|
982 |
-
"p":0.
|
983 |
-
"r":0.
|
984 |
-
"f":0.
|
985 |
},
|
986 |
"Number":{
|
987 |
-
"p":0.
|
988 |
-
"r":0.
|
989 |
-
"f":0.
|
990 |
},
|
991 |
"Degree":{
|
992 |
-
"p":0.
|
993 |
-
"r":0.
|
994 |
-
"f":0.
|
995 |
},
|
996 |
"Tense":{
|
997 |
-
"p":0.
|
998 |
-
"r":0.
|
999 |
-
"f":0.
|
1000 |
},
|
1001 |
"VerbForm":{
|
1002 |
-
"p":0.
|
1003 |
-
"r":0.
|
1004 |
-
"f":0.
|
1005 |
},
|
1006 |
"Voice":{
|
1007 |
-
"p":0.
|
1008 |
-
"r":0.
|
1009 |
-
"f":0.
|
1010 |
},
|
1011 |
"Aspect":{
|
1012 |
-
"p":0.
|
1013 |
-
"r":0.
|
1014 |
-
"f":0.
|
1015 |
},
|
1016 |
"Mood":{
|
1017 |
-
"p":0.
|
1018 |
-
"r":0.
|
1019 |
-
"f":0.
|
1020 |
},
|
1021 |
"Person":{
|
1022 |
-
"p":0.
|
1023 |
-
"r":0.
|
1024 |
-
"f":0.
|
1025 |
}
|
1026 |
},
|
1027 |
-
"tag_acc":0.
|
1028 |
-
"dep_uas":0.
|
1029 |
-
"dep_las":0.
|
1030 |
"dep_las_per_type":{
|
1031 |
"det":{
|
1032 |
-
"p":0.
|
1033 |
-
"r":0.
|
1034 |
-
"f":0.
|
1035 |
},
|
1036 |
"advmod":{
|
1037 |
-
"p":0.
|
1038 |
-
"r":0.
|
1039 |
-
"f":0.
|
1040 |
},
|
1041 |
"case":{
|
1042 |
-
"p":0.
|
1043 |
-
"r":0.
|
1044 |
-
"f":0.
|
1045 |
},
|
1046 |
"nmod":{
|
1047 |
-
"p":0.
|
1048 |
-
"r":0.
|
1049 |
-
"f":0.
|
1050 |
},
|
1051 |
"cc":{
|
1052 |
-
"p":0.
|
1053 |
-
"r":0.
|
1054 |
-
"f":0.
|
1055 |
},
|
1056 |
"conj":{
|
1057 |
-
"p":0.
|
1058 |
-
"r":0.
|
1059 |
-
"f":0.
|
1060 |
},
|
1061 |
"csubj":{
|
1062 |
-
"p":0.
|
1063 |
-
"r":0.
|
1064 |
-
"f":0.
|
1065 |
},
|
1066 |
"obl":{
|
1067 |
-
"p":0.
|
1068 |
-
"r":0.
|
1069 |
-
"f":0.
|
1070 |
},
|
1071 |
"root":{
|
1072 |
-
"p":0.
|
1073 |
-
"r":0.
|
1074 |
-
"f":0.
|
1075 |
},
|
1076 |
"cop":{
|
1077 |
-
"p":0.
|
1078 |
-
"r":0.
|
1079 |
-
"f":0.
|
1080 |
},
|
1081 |
"obj":{
|
1082 |
-
"p":0.
|
1083 |
-
"r":0.
|
1084 |
-
"f":0.
|
1085 |
},
|
1086 |
"acl":{
|
1087 |
-
"p":0.
|
1088 |
-
"r":0.
|
1089 |
-
"f":0.
|
1090 |
},
|
1091 |
"xcomp":{
|
1092 |
-
"p":0.
|
1093 |
-
"r":0.
|
1094 |
-
"f":0.
|
1095 |
},
|
1096 |
"nsubj":{
|
1097 |
-
"p":0.
|
1098 |
-
"r":0.
|
1099 |
-
"f":0.
|
1100 |
},
|
1101 |
"amod":{
|
1102 |
-
"p":0.
|
1103 |
-
"r":0.
|
1104 |
-
"f":0.
|
1105 |
},
|
1106 |
"advcl":{
|
1107 |
-
"p":0.
|
1108 |
-
"r":0.
|
1109 |
-
"f":0.
|
1110 |
},
|
1111 |
"mark":{
|
1112 |
-
"p":0.
|
1113 |
-
"r":0.
|
1114 |
-
"f":0.
|
1115 |
},
|
1116 |
"iobj":{
|
1117 |
-
"p":0.
|
1118 |
-
"r":0.
|
1119 |
-
"f":0.
|
1120 |
},
|
1121 |
"dep":{
|
1122 |
"p":0.0,
|
@@ -1124,29 +1120,29 @@
|
|
1124 |
"f":0.0
|
1125 |
},
|
1126 |
"ccomp":{
|
1127 |
-
"p":0.
|
1128 |
-
"r":0.
|
1129 |
-
"f":0.
|
1130 |
},
|
1131 |
"appos":{
|
1132 |
-
"p":0.
|
1133 |
-
"r":0.
|
1134 |
-
"f":0.
|
1135 |
},
|
1136 |
"nummod":{
|
1137 |
-
"p":0.
|
1138 |
-
"r":0.
|
1139 |
-
"f":0.
|
1140 |
-
},
|
1141 |
-
"vocative":{
|
1142 |
-
"p":0.4761904762,
|
1143 |
-
"r":0.4347826087,
|
1144 |
-
"f":0.4545454545
|
1145 |
},
|
1146 |
"discourse":{
|
1147 |
-
"p":0.
|
1148 |
-
"r":0.
|
1149 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
1150 |
},
|
1151 |
"parataxis":{
|
1152 |
"p":0.0,
|
@@ -1154,40 +1150,19 @@
|
|
1154 |
"f":0.0
|
1155 |
}
|
1156 |
},
|
1157 |
-
"sents_p":0.
|
1158 |
-
"sents_r":0.
|
1159 |
-
"sents_f":0.
|
1160 |
-
"lemma_acc":0.
|
1161 |
-
"ents_f":0.
|
1162 |
-
"ents_p":0.
|
1163 |
-
"ents_r":0.
|
1164 |
-
"ents_per_type":
|
1165 |
-
|
1166 |
-
|
1167 |
-
|
1168 |
-
|
1169 |
-
|
1170 |
-
"LOC":{
|
1171 |
-
"p":0.8363636364,
|
1172 |
-
"r":0.7419354839,
|
1173 |
-
"f":0.7863247863
|
1174 |
-
},
|
1175 |
-
"NORP":{
|
1176 |
-
"p":0.9204545455,
|
1177 |
-
"r":0.9418604651,
|
1178 |
-
"f":0.9310344828
|
1179 |
-
},
|
1180 |
-
"GOD":{
|
1181 |
-
"p":0.75,
|
1182 |
-
"r":0.4285714286,
|
1183 |
-
"f":0.5454545455
|
1184 |
-
}
|
1185 |
-
},
|
1186 |
-
"tok2vec_loss":81450.2292109041,
|
1187 |
-
"morphologizer_loss":2295.7859585285,
|
1188 |
-
"tagger_loss":789.4396882355,
|
1189 |
-
"parser_loss":16182.8428171727,
|
1190 |
-
"ner_loss":42.9922887249
|
1191 |
},
|
1192 |
"requirements":[
|
1193 |
|
|
|
1 |
{
|
2 |
"lang":"grc",
|
3 |
"name":"perseus_lg",
|
4 |
+
"version":"3.7.5",
|
5 |
"description":"",
|
6 |
"author":"",
|
7 |
"email":"",
|
8 |
"url":"",
|
9 |
"license":"",
|
10 |
+
"spacy_version":">=3.7.5,<3.8.0",
|
11 |
+
"spacy_git_version":"a6d0fc360",
|
12 |
"vectors":{
|
13 |
"width":300,
|
14 |
"vectors":200000,
|
|
|
937 |
"vocative",
|
938 |
"xcomp"
|
939 |
],
|
940 |
+
"ner":[
|
941 |
|
942 |
],
|
943 |
+
"attribute_ruler":[
|
944 |
+
|
|
|
|
|
|
|
|
|
945 |
]
|
946 |
},
|
947 |
"pipeline":[
|
|
|
950 |
"tagger",
|
951 |
"parser",
|
952 |
"lemmatizer",
|
953 |
+
"ner",
|
954 |
+
"attribute_ruler"
|
955 |
],
|
956 |
"components":[
|
957 |
"tok2vec",
|
|
|
959 |
"tagger",
|
960 |
"parser",
|
961 |
"lemmatizer",
|
962 |
+
"ner",
|
963 |
+
"attribute_ruler"
|
964 |
],
|
965 |
"disabled":[
|
966 |
|
967 |
],
|
968 |
"performance":{
|
969 |
+
"pos_acc":0.7983014862,
|
970 |
+
"morph_acc":0.7394741597,
|
971 |
"morph_per_feat":{
|
972 |
"Case":{
|
973 |
+
"p":0.8711741792,
|
974 |
+
"r":0.8283799277,
|
975 |
+
"f":0.8492382804
|
976 |
},
|
977 |
"Gender":{
|
978 |
+
"p":0.8067390699,
|
979 |
+
"r":0.7677561837,
|
980 |
+
"f":0.7867650387
|
981 |
},
|
982 |
"Number":{
|
983 |
+
"p":0.9222107684,
|
984 |
+
"r":0.8707696915,
|
985 |
+
"f":0.895752301
|
986 |
},
|
987 |
"Degree":{
|
988 |
+
"p":0.358490566,
|
989 |
+
"r":0.1117647059,
|
990 |
+
"f":0.1704035874
|
991 |
},
|
992 |
"Tense":{
|
993 |
+
"p":0.7315310493,
|
994 |
+
"r":0.6622243761,
|
995 |
+
"f":0.6951545212
|
996 |
},
|
997 |
"VerbForm":{
|
998 |
+
"p":0.8988222698,
|
999 |
+
"r":0.8136661013,
|
1000 |
+
"f":0.8541269236
|
1001 |
},
|
1002 |
"Voice":{
|
1003 |
+
"p":0.8364123159,
|
1004 |
+
"r":0.7575169738,
|
1005 |
+
"f":0.7950120881
|
1006 |
},
|
1007 |
"Aspect":{
|
1008 |
+
"p":0.6011673152,
|
1009 |
+
"r":0.3763702801,
|
1010 |
+
"f":0.4629213483
|
1011 |
},
|
1012 |
"Mood":{
|
1013 |
+
"p":0.8558164937,
|
1014 |
+
"r":0.7768963808,
|
1015 |
+
"f":0.8144490644
|
1016 |
},
|
1017 |
"Person":{
|
1018 |
+
"p":0.8639825898,
|
1019 |
+
"r":0.7576335878,
|
1020 |
+
"f":0.8073207931
|
1021 |
}
|
1022 |
},
|
1023 |
+
"tag_acc":0.7722642575,
|
1024 |
+
"dep_uas":0.5785607915,
|
1025 |
+
"dep_las":0.4840101971,
|
1026 |
"dep_las_per_type":{
|
1027 |
"det":{
|
1028 |
+
"p":0.8079906905,
|
1029 |
+
"r":0.7740616871,
|
1030 |
+
"f":0.7906623648
|
1031 |
},
|
1032 |
"advmod":{
|
1033 |
+
"p":0.4696218227,
|
1034 |
+
"r":0.4883945841,
|
1035 |
+
"f":0.4788242731
|
1036 |
},
|
1037 |
"case":{
|
1038 |
+
"p":0.7707567965,
|
1039 |
+
"r":0.779346211,
|
1040 |
+
"f":0.7750277059
|
1041 |
},
|
1042 |
"nmod":{
|
1043 |
+
"p":0.3324634656,
|
1044 |
+
"r":0.3432112069,
|
1045 |
+
"f":0.3377518558
|
1046 |
},
|
1047 |
"cc":{
|
1048 |
+
"p":0.4661246612,
|
1049 |
+
"r":0.5009708738,
|
1050 |
+
"f":0.4829199813
|
1051 |
},
|
1052 |
"conj":{
|
1053 |
+
"p":0.3918406072,
|
1054 |
+
"r":0.3720720721,
|
1055 |
+
"f":0.3817005545
|
1056 |
},
|
1057 |
"csubj":{
|
1058 |
+
"p":0.2380952381,
|
1059 |
+
"r":0.0485436893,
|
1060 |
+
"f":0.0806451613
|
1061 |
},
|
1062 |
"obl":{
|
1063 |
+
"p":0.380627558,
|
1064 |
+
"r":0.3940677966,
|
1065 |
+
"f":0.3872310895
|
1066 |
},
|
1067 |
"root":{
|
1068 |
+
"p":0.6692242114,
|
1069 |
+
"r":0.6904133685,
|
1070 |
+
"f":0.6796536797
|
1071 |
},
|
1072 |
"cop":{
|
1073 |
+
"p":0.4238683128,
|
1074 |
+
"r":0.3639575972,
|
1075 |
+
"f":0.391634981
|
1076 |
},
|
1077 |
"obj":{
|
1078 |
+
"p":0.3256262042,
|
1079 |
+
"r":0.4344473008,
|
1080 |
+
"f":0.372246696
|
1081 |
},
|
1082 |
"acl":{
|
1083 |
+
"p":0.1935483871,
|
1084 |
+
"r":0.0740740741,
|
1085 |
+
"f":0.1071428571
|
1086 |
},
|
1087 |
"xcomp":{
|
1088 |
+
"p":0.2528180354,
|
1089 |
+
"r":0.2302052786,
|
1090 |
+
"f":0.2409823484
|
1091 |
},
|
1092 |
"nsubj":{
|
1093 |
+
"p":0.3990825688,
|
1094 |
+
"r":0.3419811321,
|
1095 |
+
"f":0.3683319221
|
1096 |
},
|
1097 |
"amod":{
|
1098 |
+
"p":0.0555555556,
|
1099 |
+
"r":0.0147058824,
|
1100 |
+
"f":0.023255814
|
1101 |
},
|
1102 |
"advcl":{
|
1103 |
+
"p":0.3493449782,
|
1104 |
+
"r":0.3484320557,
|
1105 |
+
"f":0.3488879198
|
1106 |
},
|
1107 |
"mark":{
|
1108 |
+
"p":0.6066666667,
|
1109 |
+
"r":0.5069637883,
|
1110 |
+
"f":0.5523520486
|
1111 |
},
|
1112 |
"iobj":{
|
1113 |
+
"p":0.1940298507,
|
1114 |
+
"r":0.0955882353,
|
1115 |
+
"f":0.1280788177
|
1116 |
},
|
1117 |
"dep":{
|
1118 |
"p":0.0,
|
|
|
1120 |
"f":0.0
|
1121 |
},
|
1122 |
"ccomp":{
|
1123 |
+
"p":0.2166666667,
|
1124 |
+
"r":0.125,
|
1125 |
+
"f":0.1585365854
|
1126 |
},
|
1127 |
"appos":{
|
1128 |
+
"p":0.0,
|
1129 |
+
"r":0.0,
|
1130 |
+
"f":0.0
|
1131 |
},
|
1132 |
"nummod":{
|
1133 |
+
"p":0.1666666667,
|
1134 |
+
"r":0.125,
|
1135 |
+
"f":0.1428571429
|
|
|
|
|
|
|
|
|
|
|
1136 |
},
|
1137 |
"discourse":{
|
1138 |
+
"p":0.7647058824,
|
1139 |
+
"r":0.7647058824,
|
1140 |
+
"f":0.7647058824
|
1141 |
+
},
|
1142 |
+
"vocative":{
|
1143 |
+
"p":0.375,
|
1144 |
+
"r":0.2608695652,
|
1145 |
+
"f":0.3076923077
|
1146 |
},
|
1147 |
"parataxis":{
|
1148 |
"p":0.0,
|
|
|
1150 |
"f":0.0
|
1151 |
}
|
1152 |
},
|
1153 |
+
"sents_p":0.9275362319,
|
1154 |
+
"sents_r":0.9569041337,
|
1155 |
+
"sents_f":0.941991342,
|
1156 |
+
"lemma_acc":0.9766685488,
|
1157 |
+
"ents_f":0.0,
|
1158 |
+
"ents_p":0.0,
|
1159 |
+
"ents_r":0.0,
|
1160 |
+
"ents_per_type":0.0,
|
1161 |
+
"tok2vec_loss":4743610.5453529358,
|
1162 |
+
"morphologizer_loss":417313.4768981934,
|
1163 |
+
"tagger_loss":359523.9055938721,
|
1164 |
+
"parser_loss":590284.4736542682,
|
1165 |
+
"ner_loss":0.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1166 |
},
|
1167 |
"requirements":[
|
1168 |
|
morphologizer/model
CHANGED
Binary files a/morphologizer/model and b/morphologizer/model differ
|
|
ner/model
CHANGED
Binary files a/ner/model and b/ner/model differ
|
|
ner/moves
CHANGED
@@ -1 +1 @@
|
|
1 |
-
��moves
|
|
|
1 |
+
��moves�3{"0":{},"1":{},"2":{},"3":{},"4":{"":1},"5":{"":1}}�cfg��neg_key�
|
parser/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 sha256:8cfd923e1990a378215e64d15366517cfdde6127f0cc86989f08f9f3ed365c7d
|
3 |
+
size 1787174
|
parser/moves
CHANGED
@@ -1 +1 @@
|
|
1 |
-
��moves��{"0":{"":82576},"1":{"":65845},"2":{"advmod":17575,"obj":8400,"nmod":7356,"nsubj":6738,"punct":6644,"case":6527,"det":5417,"obl":5072,"advcl":3697,"cc":2351,"mark":1841,"xcomp":1304,"nmod||obj":1036,"nmod||nsubj":847,"iobj":777,"vocative":652,"case||obl":458,"det||nsubj":420,"cop":405,"discourse":320,"amod":276,"xcomp||nsubj":272,"nmod||obl":257,"obj||advcl":249,"mark||advcl":224,"nsubj||ccomp":177,"obj||xcomp":175,"det||obj":154,"advmod||advcl":151,"obl||advcl":144,"xcomp||obj":135,"nmod||nmod":116,"advmod||advmod":109,"ccomp":107,"nsubj||advcl":99,"nummod":90,"csubj":82,"nmod||xcomp":78,"acl":76,"advmod||xcomp":73,"obl||xcomp":69,"amod||obj":61,"advmod||nsubj":55,"det||nmod":54,"amod||nsubj":52,"advmod||obj":52,"advmod||nmod":45,"nmod||iobj":44,"obj||csubj":40,"conj||advcl":40,"advmod||ccomp":40,"cc||advcl":39,"nsubj||csubj":35,"det||obl":34,"det||advmod":34,"obj||ccomp":31,"conj||nsubj":31,"xcomp||advcl":30,"conj||obj":30,"advmod||obl":30,"dep":0},"3":{"punct":13626,"conj":6422,"nmod":6002,"cc":5646,"obj":4846,"advmod":4730,"obl":3808,"advcl":3519,"nsubj":2916,"xcomp":2055,"cop":834,"ccomp":760,"nmod||obj":710,"advmod||conj":654,"acl":556,"nsubj||conj":550,"obj||conj":541,"case":504,"nmod||nsubj":408,"iobj":337,"det":329,"amod":320,"vocative":284,"obl||conj":274,"nmod||conj":255,"acl||obj":248,"conj||obj":228,"csubj":223,"case||conj":210,"xcomp||obj":205,"advcl||conj":174,"cc||obj":166,"nmod||obl":165,"case||obl":152,"xcomp||nsubj":148,"appos":145,"nmod||nmod":135,"acl||nsubj":135,"xcomp||conj":124,"conj||nsubj":105,"amod||obj":95,"det||nsubj":92,"parataxis":91,"appos||obj":81,"cc||nsubj":76,"obl||xcomp":68,"amod||nsubj":68,"advmod||obj":66,"conj||obl":65,"det||obj":63,"obj||xcomp":61,"appos||nsubj":58,"iobj||conj":57,"cc||obl":57,"conj||xcomp":49,"acl||nmod":46,"det||conj":43,"nummod":42,"conj||nmod":42,"nmod||xcomp":39,"cc||xcomp":39,"obj||advcl":38,"cc||nmod":36,"advmod||xcomp":33,"advmod||nsubj":33,"acl||obl":32,"cop||obj":30,"dep":0},"4":{"
|
|
|
1 |
+
��moves��{"0":{"":82576},"1":{"":65845},"2":{"advmod":17575,"obj":8400,"nmod":7356,"nsubj":6738,"punct":6644,"case":6527,"det":5417,"obl":5072,"advcl":3697,"cc":2351,"mark":1841,"xcomp":1304,"nmod||obj":1036,"nmod||nsubj":847,"iobj":777,"vocative":652,"case||obl":458,"det||nsubj":420,"cop":405,"discourse":320,"amod":276,"xcomp||nsubj":272,"nmod||obl":257,"obj||advcl":249,"mark||advcl":224,"nsubj||ccomp":177,"obj||xcomp":175,"det||obj":154,"advmod||advcl":151,"obl||advcl":144,"xcomp||obj":135,"nmod||nmod":116,"advmod||advmod":109,"ccomp":107,"nsubj||advcl":99,"nummod":90,"csubj":82,"nmod||xcomp":78,"acl":76,"advmod||xcomp":73,"obl||xcomp":69,"amod||obj":61,"advmod||nsubj":55,"det||nmod":54,"amod||nsubj":52,"advmod||obj":52,"advmod||nmod":45,"nmod||iobj":44,"obj||csubj":40,"conj||advcl":40,"advmod||ccomp":40,"cc||advcl":39,"nsubj||csubj":35,"det||obl":34,"det||advmod":34,"obj||ccomp":31,"conj||nsubj":31,"xcomp||advcl":30,"conj||obj":30,"advmod||obl":30,"dep":0},"3":{"punct":13626,"conj":6422,"nmod":6002,"cc":5646,"obj":4846,"advmod":4730,"obl":3808,"advcl":3519,"nsubj":2916,"xcomp":2055,"cop":834,"ccomp":760,"nmod||obj":710,"advmod||conj":654,"acl":556,"nsubj||conj":550,"obj||conj":541,"case":504,"nmod||nsubj":408,"iobj":337,"det":329,"amod":320,"vocative":284,"obl||conj":274,"nmod||conj":255,"acl||obj":248,"conj||obj":228,"csubj":223,"case||conj":210,"xcomp||obj":205,"advcl||conj":174,"cc||obj":166,"nmod||obl":165,"case||obl":152,"xcomp||nsubj":148,"appos":145,"nmod||nmod":135,"acl||nsubj":135,"xcomp||conj":124,"conj||nsubj":105,"amod||obj":95,"det||nsubj":92,"parataxis":91,"appos||obj":81,"cc||nsubj":76,"obl||xcomp":68,"amod||nsubj":68,"advmod||obj":66,"conj||obl":65,"det||obj":63,"obj||xcomp":61,"appos||nsubj":58,"iobj||conj":57,"cc||obl":57,"conj||xcomp":49,"acl||nmod":46,"det||conj":43,"nummod":42,"conj||nmod":42,"nmod||xcomp":39,"cc||xcomp":39,"obj||advcl":38,"cc||nmod":36,"advmod||xcomp":33,"advmod||nsubj":33,"acl||obl":32,"cop||obj":30,"dep":0},"4":{"ROOT":11476}}�cfg��neg_key�
|
tagger/model
CHANGED
Binary files a/tagger/model and b/tagger/model differ
|
|
tok2vec/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 35970008
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47d74be09eb8da098d00ffc1b1cf82fdbae11c54720fafd2ce887bc4f5317f31
|
3 |
size 35970008
|
vocab/strings.json
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:d3fb51a5450d8d456a10b6bfe2b06d23f92a7fb8a91b87c926543dcde66a5154
|
3 |
+
size 21610853
|