Update spaCy pipeline
Browse files- README.md +33 -33
- config.cfg +24 -4
- functions.py +1 -4
- la_core_web_trf-any-py3-none-any.whl +2 -2
- meta.json +216 -211
- morphologizer/model +1 -1
- ner/model +1 -1
- ner/moves +1 -1
- parser/model +1 -1
- senter/cfg +3 -0
- senter/model +0 -0
- tagger/model +0 -0
- trainable_lemmatizer/cfg +0 -0
- trainable_lemmatizer/model +2 -2
- trainable_lemmatizer/trees +2 -2
- transformer/model +1 -1
- vocab/strings.json +0 -0
README.md
CHANGED
|
@@ -14,72 +14,72 @@ 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 |
- task:
|
| 32 |
name: POS
|
| 33 |
type: token-classification
|
| 34 |
metrics:
|
| 35 |
- name: POS (UPOS) Accuracy
|
| 36 |
type: accuracy
|
| 37 |
-
value: 0.
|
| 38 |
- task:
|
| 39 |
name: MORPH
|
| 40 |
type: token-classification
|
| 41 |
metrics:
|
| 42 |
- name: Morph (UFeats) Accuracy
|
| 43 |
type: accuracy
|
| 44 |
-
value: 0.
|
| 45 |
- task:
|
| 46 |
name: LEMMA
|
| 47 |
type: token-classification
|
| 48 |
metrics:
|
| 49 |
- name: Lemma Accuracy
|
| 50 |
type: accuracy
|
| 51 |
-
value: 0.
|
| 52 |
- task:
|
| 53 |
name: UNLABELED_DEPENDENCIES
|
| 54 |
type: token-classification
|
| 55 |
metrics:
|
| 56 |
- name: Unlabeled Attachment Score (UAS)
|
| 57 |
type: f_score
|
| 58 |
-
value: 0.
|
| 59 |
- task:
|
| 60 |
name: LABELED_DEPENDENCIES
|
| 61 |
type: token-classification
|
| 62 |
metrics:
|
| 63 |
- name: Labeled Attachment Score (LAS)
|
| 64 |
type: f_score
|
| 65 |
-
value: 0.
|
| 66 |
- task:
|
| 67 |
name: SENTS
|
| 68 |
type: token-classification
|
| 69 |
metrics:
|
| 70 |
- name: Sentences F-Score
|
| 71 |
type: f_score
|
| 72 |
-
value: 0.
|
| 73 |
---
|
| 74 |
| Feature | Description |
|
| 75 |
| --- | --- |
|
| 76 |
| **Name** | `la_core_web_trf` |
|
| 77 |
-
| **Version** | `3.7.
|
| 78 |
-
| **spaCy** | `>=3.7.
|
| 79 |
-
| **Default Pipeline** | `transformer`, `normer`, `tagger`, `morphologizer`, `trainable_lemmatizer`, `parser`, `lookup_lemmatizer`, `ner` |
|
| 80 |
-
| **Components** | `transformer`, `normer`, `tagger`, `morphologizer`, `trainable_lemmatizer`, `parser`, `lookup_lemmatizer`, `ner` |
|
| 81 |
| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
|
| 82 |
-
| **Sources** | UD_Latin-Perseus<br>UD_Latin-PROIEL<br>UD_Latin-ITTB<br>UD_Latin-LLCT<br>UD_Latin-UDante |
|
| 83 |
| **License** | `MIT` |
|
| 84 |
| **Author** | [Patrick J. Burns; with Nora Bernhardt [ner], Tim Geelhaar [tagger, morphologizer, parser, ner], Vincent Koch [ner]](https://diyclassics.github.io/) |
|
| 85 |
|
|
@@ -102,21 +102,21 @@ model-index:
|
|
| 102 |
|
| 103 |
| Type | Score |
|
| 104 |
| --- | --- |
|
| 105 |
-
| `ENTS_F` |
|
| 106 |
-
| `ENTS_P` | 94.
|
| 107 |
-
| `ENTS_R` | 95.
|
| 108 |
-
| `TRANSFORMER_LOSS` |
|
| 109 |
-
| `NER_LOSS` |
|
| 110 |
-
| `TAG_ACC` | 96.
|
| 111 |
-
| `POS_ACC` | 98.
|
| 112 |
-
| `MORPH_ACC` | 95.
|
| 113 |
-
| `LEMMA_ACC` | 95.
|
| 114 |
-
| `DEP_UAS` | 88.
|
| 115 |
-
| `DEP_LAS` | 84.
|
| 116 |
-
| `SENTS_P` | 94.
|
| 117 |
-
| `SENTS_R` | 94.
|
| 118 |
-
| `SENTS_F` | 94.
|
| 119 |
-
| `TAGGER_LOSS` |
|
| 120 |
-
| `MORPHOLOGIZER_LOSS` |
|
| 121 |
-
| `TRAINABLE_LEMMATIZER_LOSS` |
|
| 122 |
-
| `PARSER_LOSS` |
|
|
|
|
| 14 |
metrics:
|
| 15 |
- name: NER Precision
|
| 16 |
type: precision
|
| 17 |
+
value: 0.9631931948
|
| 18 |
- name: NER Recall
|
| 19 |
type: recall
|
| 20 |
+
value: 0.9570871261
|
| 21 |
- name: NER F Score
|
| 22 |
type: f_score
|
| 23 |
+
value: 0.9601304525
|
| 24 |
- task:
|
| 25 |
name: TAG
|
| 26 |
type: token-classification
|
| 27 |
metrics:
|
| 28 |
- name: TAG (XPOS) Accuracy
|
| 29 |
type: accuracy
|
| 30 |
+
value: 0.9640958514
|
| 31 |
- task:
|
| 32 |
name: POS
|
| 33 |
type: token-classification
|
| 34 |
metrics:
|
| 35 |
- name: POS (UPOS) Accuracy
|
| 36 |
type: accuracy
|
| 37 |
+
value: 0.9831838987
|
| 38 |
- task:
|
| 39 |
name: MORPH
|
| 40 |
type: token-classification
|
| 41 |
metrics:
|
| 42 |
- name: Morph (UFeats) Accuracy
|
| 43 |
type: accuracy
|
| 44 |
+
value: 0.9581374663
|
| 45 |
- task:
|
| 46 |
name: LEMMA
|
| 47 |
type: token-classification
|
| 48 |
metrics:
|
| 49 |
- name: Lemma Accuracy
|
| 50 |
type: accuracy
|
| 51 |
+
value: 0.9531809911
|
| 52 |
- task:
|
| 53 |
name: UNLABELED_DEPENDENCIES
|
| 54 |
type: token-classification
|
| 55 |
metrics:
|
| 56 |
- name: Unlabeled Attachment Score (UAS)
|
| 57 |
type: f_score
|
| 58 |
+
value: 0.8882308136
|
| 59 |
- task:
|
| 60 |
name: LABELED_DEPENDENCIES
|
| 61 |
type: token-classification
|
| 62 |
metrics:
|
| 63 |
- name: Labeled Attachment Score (LAS)
|
| 64 |
type: f_score
|
| 65 |
+
value: 0.8492401865
|
| 66 |
- task:
|
| 67 |
name: SENTS
|
| 68 |
type: token-classification
|
| 69 |
metrics:
|
| 70 |
- name: Sentences F-Score
|
| 71 |
type: f_score
|
| 72 |
+
value: 0.9959496442
|
| 73 |
---
|
| 74 |
| Feature | Description |
|
| 75 |
| --- | --- |
|
| 76 |
| **Name** | `la_core_web_trf` |
|
| 77 |
+
| **Version** | `3.7.7` |
|
| 78 |
+
| **spaCy** | `>=3.7.5,<3.8.0` |
|
| 79 |
+
| **Default Pipeline** | `senter`, `transformer`, `normer`, `tagger`, `morphologizer`, `trainable_lemmatizer`, `parser`, `lookup_lemmatizer`, `ner` |
|
| 80 |
+
| **Components** | `senter`, `transformer`, `normer`, `tagger`, `morphologizer`, `trainable_lemmatizer`, `parser`, `lookup_lemmatizer`, `ner` |
|
| 81 |
| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
|
| 82 |
+
| **Sources** | UD_Latin-Perseus (via Gamba/Zeman 2023)<br>UD_Latin-PROIEL (via Gamba/Zeman 2023)<br>UD_Latin-ITTB (via Gamba/Zeman 2023)<br>UD_Latin-LLCT (via Gamba/Zeman 2023<br>UD_Latin-UDante (via Gamba/Zeman 2023)<br>CIRCSE/LASLA: LASLA Corpus |
|
| 83 |
| **License** | `MIT` |
|
| 84 |
| **Author** | [Patrick J. Burns; with Nora Bernhardt [ner], Tim Geelhaar [tagger, morphologizer, parser, ner], Vincent Koch [ner]](https://diyclassics.github.io/) |
|
| 85 |
|
|
|
|
| 102 |
|
| 103 |
| Type | Score |
|
| 104 |
| --- | --- |
|
| 105 |
+
| `ENTS_F` | 95.43 |
|
| 106 |
+
| `ENTS_P` | 94.87 |
|
| 107 |
+
| `ENTS_R` | 95.99 |
|
| 108 |
+
| `TRANSFORMER_LOSS` | 3054585.96 |
|
| 109 |
+
| `NER_LOSS` | 9051.00 |
|
| 110 |
+
| `TAG_ACC` | 96.33 |
|
| 111 |
+
| `POS_ACC` | 98.31 |
|
| 112 |
+
| `MORPH_ACC` | 95.75 |
|
| 113 |
+
| `LEMMA_ACC` | 95.27 |
|
| 114 |
+
| `DEP_UAS` | 88.61 |
|
| 115 |
+
| `DEP_LAS` | 84.72 |
|
| 116 |
+
| `SENTS_P` | 94.93 |
|
| 117 |
+
| `SENTS_R` | 94.41 |
|
| 118 |
+
| `SENTS_F` | 94.67 |
|
| 119 |
+
| `TAGGER_LOSS` | 28864.85 |
|
| 120 |
+
| `MORPHOLOGIZER_LOSS` | 246784.11 |
|
| 121 |
+
| `TRAINABLE_LEMMATIZER_LOSS` | 242230.83 |
|
| 122 |
+
| `PARSER_LOSS` | 2414158.66 |
|
config.cfg
CHANGED
|
@@ -10,7 +10,7 @@ seed = 0
|
|
| 10 |
|
| 11 |
[nlp]
|
| 12 |
lang = "la"
|
| 13 |
-
pipeline = ["transformer","normer","tagger","morphologizer","trainable_lemmatizer","parser","lookup_lemmatizer","ner"]
|
| 14 |
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
|
| 15 |
disabled = []
|
| 16 |
before_creation = null
|
|
@@ -129,6 +129,26 @@ use_fast = true
|
|
| 129 |
|
| 130 |
[components.parser.model.tok2vec.transformer_config]
|
| 131 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 132 |
[components.tagger]
|
| 133 |
factory = "tagger"
|
| 134 |
label_smoothing = 0.0
|
|
@@ -251,6 +271,9 @@ eps = 0.00000001
|
|
| 251 |
learn_rate = 0.001
|
| 252 |
|
| 253 |
[training.score_weights]
|
|
|
|
|
|
|
|
|
|
| 254 |
tag_acc = 0.2
|
| 255 |
pos_acc = 0.1
|
| 256 |
morph_acc = 0.1
|
|
@@ -259,9 +282,6 @@ lemma_acc = 0.2
|
|
| 259 |
dep_uas = 0.1
|
| 260 |
dep_las = 0.1
|
| 261 |
dep_las_per_type = null
|
| 262 |
-
sents_p = null
|
| 263 |
-
sents_r = null
|
| 264 |
-
sents_f = 0.0
|
| 265 |
ents_f = 0.2
|
| 266 |
ents_p = 0.0
|
| 267 |
ents_r = 0.0
|
|
|
|
| 10 |
|
| 11 |
[nlp]
|
| 12 |
lang = "la"
|
| 13 |
+
pipeline = ["senter","transformer","normer","tagger","morphologizer","trainable_lemmatizer","parser","lookup_lemmatizer","ner"]
|
| 14 |
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
|
| 15 |
disabled = []
|
| 16 |
before_creation = null
|
|
|
|
| 129 |
|
| 130 |
[components.parser.model.tok2vec.transformer_config]
|
| 131 |
|
| 132 |
+
[components.senter]
|
| 133 |
+
factory = "senter"
|
| 134 |
+
overwrite = false
|
| 135 |
+
scorer = {"@scorers":"spacy.senter_scorer.v1"}
|
| 136 |
+
|
| 137 |
+
[components.senter.model]
|
| 138 |
+
@architectures = "spacy.Tagger.v2"
|
| 139 |
+
nO = null
|
| 140 |
+
normalize = false
|
| 141 |
+
|
| 142 |
+
[components.senter.model.tok2vec]
|
| 143 |
+
@architectures = "spacy.HashEmbedCNN.v2"
|
| 144 |
+
pretrained_vectors = null
|
| 145 |
+
width = 12
|
| 146 |
+
depth = 1
|
| 147 |
+
embed_size = 2000
|
| 148 |
+
window_size = 1
|
| 149 |
+
maxout_pieces = 2
|
| 150 |
+
subword_features = true
|
| 151 |
+
|
| 152 |
[components.tagger]
|
| 153 |
factory = "tagger"
|
| 154 |
label_smoothing = 0.0
|
|
|
|
| 271 |
learn_rate = 0.001
|
| 272 |
|
| 273 |
[training.score_weights]
|
| 274 |
+
sents_f = 0.0
|
| 275 |
+
sents_p = null
|
| 276 |
+
sents_r = null
|
| 277 |
tag_acc = 0.2
|
| 278 |
pos_acc = 0.1
|
| 279 |
morph_acc = 0.1
|
|
|
|
| 282 |
dep_uas = 0.1
|
| 283 |
dep_las = 0.1
|
| 284 |
dep_las_per_type = null
|
|
|
|
|
|
|
|
|
|
| 285 |
ents_f = 0.2
|
| 286 |
ents_p = 0.0
|
| 287 |
ents_r = 0.0
|
functions.py
CHANGED
|
@@ -200,11 +200,8 @@ import string
|
|
| 200 |
blank_nlp = spacy.blank("la")
|
| 201 |
lookups = Lookups()
|
| 202 |
|
| 203 |
-
try:
|
| 204 |
-
lookups_data = load_lookups(lang=blank_nlp.vocab.lang, tables=["lemma_lookup"])
|
| 205 |
-
except:
|
| 206 |
-
lookups_data = lookups.from_disk("scripts/lemmatizer_lookups")
|
| 207 |
|
|
|
|
| 208 |
LOOKUPS = lookups_data.get_table("lemma_lookup")
|
| 209 |
|
| 210 |
predicted_lemma_getter = lambda token: token.lemma_
|
|
|
|
| 200 |
blank_nlp = spacy.blank("la")
|
| 201 |
lookups = Lookups()
|
| 202 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 203 |
|
| 204 |
+
lookups_data = load_lookups(lang=blank_nlp.vocab.lang, tables=["lemma_lookup"])
|
| 205 |
LOOKUPS = lookups_data.get_table("lemma_lookup")
|
| 206 |
|
| 207 |
predicted_lemma_getter = lambda token: token.lemma_
|
la_core_web_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 sha256:391c1897518a0049a9648a7ae67f931c778bec052dd7a5d98cb012cab57a9929
|
| 3 |
+
size 2509328343
|
meta.json
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
{
|
| 2 |
"lang":"la",
|
| 3 |
"name":"core_web_trf",
|
| 4 |
-
"version":"3.7.
|
| 5 |
"description":"",
|
| 6 |
"author":"Patrick J. Burns; with Nora Bernhardt [ner], Tim Geelhaar [tagger, morphologizer, parser, ner], Vincent Koch [ner]",
|
| 7 |
"email":"pjb311@nyu.edu",
|
| 8 |
"url":"https://diyclassics.github.io/",
|
| 9 |
"license":"MIT",
|
| 10 |
-
"spacy_version":">=3.7.
|
| 11 |
-
"spacy_git_version":"
|
| 12 |
"vectors":{
|
| 13 |
"width":0,
|
| 14 |
"vectors":0,
|
|
@@ -811,6 +811,7 @@
|
|
| 811 |
]
|
| 812 |
},
|
| 813 |
"pipeline":[
|
|
|
|
| 814 |
"transformer",
|
| 815 |
"normer",
|
| 816 |
"tagger",
|
|
@@ -821,6 +822,7 @@
|
|
| 821 |
"ner"
|
| 822 |
],
|
| 823 |
"components":[
|
|
|
|
| 824 |
"transformer",
|
| 825 |
"normer",
|
| 826 |
"tagger",
|
|
@@ -834,301 +836,304 @@
|
|
| 834 |
|
| 835 |
],
|
| 836 |
"performance":{
|
| 837 |
-
"ents_f":0.
|
| 838 |
-
"ents_p":0.
|
| 839 |
-
"ents_r":0.
|
| 840 |
"ents_per_type":{
|
| 841 |
"PERSON":{
|
| 842 |
-
"p":0.
|
| 843 |
-
"r":0.
|
| 844 |
-
"f":0.
|
| 845 |
},
|
| 846 |
"LOC":{
|
| 847 |
-
"p":0.
|
| 848 |
-
"r":0.
|
| 849 |
-
"f":0.
|
| 850 |
},
|
| 851 |
"NORP":{
|
| 852 |
-
"p":0
|
| 853 |
"r":0.9369369369,
|
| 854 |
-
"f":0.
|
| 855 |
}
|
| 856 |
},
|
| 857 |
-
"transformer_loss":
|
| 858 |
-
"ner_loss":
|
| 859 |
-
"
|
| 860 |
-
"
|
| 861 |
-
"
|
|
|
|
|
|
|
|
|
|
| 862 |
"morph_per_feat":{
|
| 863 |
"Case":{
|
| 864 |
-
"p":0.
|
| 865 |
-
"r":0.
|
| 866 |
-
"f":0.
|
| 867 |
},
|
| 868 |
"Gender":{
|
| 869 |
-
"p":0.
|
| 870 |
-
"r":0.
|
| 871 |
-
"f":0.
|
| 872 |
},
|
| 873 |
"Number":{
|
| 874 |
-
"p":0.
|
| 875 |
-
"r":0.
|
| 876 |
-
"f":0.
|
| 877 |
},
|
| 878 |
"Mood":{
|
| 879 |
-
"p":0.
|
| 880 |
-
"r":0.
|
| 881 |
-
"f":0.
|
| 882 |
},
|
| 883 |
"Person":{
|
| 884 |
-
"p":0.
|
| 885 |
-
"r":0.
|
| 886 |
-
"f":0.
|
| 887 |
},
|
| 888 |
"Tense":{
|
| 889 |
-
"p":0.
|
| 890 |
-
"r":0.
|
| 891 |
-
"f":0.
|
| 892 |
},
|
| 893 |
"VerbForm":{
|
| 894 |
-
"p":0.
|
| 895 |
-
"r":0.
|
| 896 |
-
"f":0.
|
| 897 |
},
|
| 898 |
"Voice":{
|
| 899 |
-
"p":0.
|
| 900 |
-
"r":0.
|
| 901 |
-
"f":0.
|
| 902 |
}
|
| 903 |
},
|
| 904 |
-
"lemma_acc":0.
|
| 905 |
-
"dep_uas":0.
|
| 906 |
-
"dep_las":0.
|
| 907 |
"dep_las_per_type":{
|
| 908 |
"root":{
|
| 909 |
-
"p":0.
|
| 910 |
-
"r":0.
|
| 911 |
-
"f":0.
|
| 912 |
},
|
| 913 |
"cop":{
|
| 914 |
-
"p":0.
|
| 915 |
-
"r":0.
|
| 916 |
-
"f":0.
|
| 917 |
},
|
| 918 |
"nsubj":{
|
| 919 |
-
"p":0.
|
| 920 |
-
"r":0.
|
| 921 |
-
"f":0.
|
| 922 |
},
|
| 923 |
"nmod":{
|
| 924 |
-
"p":0.
|
| 925 |
-
"r":0.
|
| 926 |
-
"f":0.
|
| 927 |
},
|
| 928 |
"obj":{
|
| 929 |
-
"p":0.
|
| 930 |
-
"r":0.
|
| 931 |
-
"f":0.
|
| 932 |
},
|
| 933 |
"det":{
|
| 934 |
-
"p":0.
|
| 935 |
-
"r":0.
|
| 936 |
-
"f":0.
|
| 937 |
},
|
| 938 |
"cc":{
|
| 939 |
-
"p":0.
|
| 940 |
-
"r":0.
|
| 941 |
-
"f":0.
|
| 942 |
},
|
| 943 |
"conj":{
|
| 944 |
-
"p":0.
|
| 945 |
-
"r":0.
|
| 946 |
-
"f":0.
|
| 947 |
},
|
| 948 |
"nummod":{
|
| 949 |
-
"p":0.
|
| 950 |
-
"r":0.
|
| 951 |
-
"f":0.
|
| 952 |
},
|
| 953 |
"case":{
|
| 954 |
-
"p":0.
|
| 955 |
-
"r":0.
|
| 956 |
-
"f":0.
|
| 957 |
},
|
| 958 |
"obl":{
|
| 959 |
-
"p":0.
|
| 960 |
-
"r":0.
|
| 961 |
-
"f":0.
|
| 962 |
},
|
| 963 |
"acl":{
|
| 964 |
-
"p":0.
|
| 965 |
-
"r":0.
|
| 966 |
-
"f":0.
|
| 967 |
},
|
| 968 |
"ccomp":{
|
| 969 |
-
"p":0.
|
| 970 |
-
"r":0.
|
| 971 |
-
"f":0.
|
| 972 |
},
|
| 973 |
"acl:relcl":{
|
| 974 |
-
"p":0.
|
| 975 |
-
"r":0.
|
| 976 |
-
"f":0.
|
| 977 |
},
|
| 978 |
"advmod":{
|
| 979 |
-
"p":0.
|
| 980 |
-
"r":0.
|
| 981 |
-
"f":0.
|
| 982 |
},
|
| 983 |
"mark":{
|
| 984 |
-
"p":0.
|
| 985 |
-
"r":0.
|
| 986 |
-
"f":0.
|
| 987 |
},
|
| 988 |
"xcomp":{
|
| 989 |
-
"p":0.
|
| 990 |
-
"r":0.
|
| 991 |
-
"f":0.
|
| 992 |
},
|
| 993 |
"csubj:pass":{
|
| 994 |
-
"p":0.
|
| 995 |
-
"r":0.
|
| 996 |
-
"f":0.
|
| 997 |
},
|
| 998 |
"advmod:lmod":{
|
| 999 |
-
"p":0.
|
| 1000 |
-
"r":0.
|
| 1001 |
-
"f":0.
|
| 1002 |
},
|
| 1003 |
"obl:arg":{
|
| 1004 |
-
"p":0.
|
| 1005 |
-
"r":0.
|
| 1006 |
-
"f":0.
|
| 1007 |
},
|
| 1008 |
"csubj":{
|
| 1009 |
-
"p":0.
|
| 1010 |
-
"r":0.
|
| 1011 |
-
"f":0.
|
| 1012 |
},
|
| 1013 |
"discourse":{
|
| 1014 |
-
"p":0.
|
| 1015 |
-
"r":0.
|
| 1016 |
-
"f":0.
|
| 1017 |
},
|
| 1018 |
"advcl":{
|
| 1019 |
-
"p":0.
|
| 1020 |
-
"r":0.
|
| 1021 |
-
"f":0.
|
| 1022 |
},
|
| 1023 |
"nsubj:pass":{
|
| 1024 |
-
"p":0.
|
| 1025 |
-
"r":0.
|
| 1026 |
-
"f":0.
|
| 1027 |
},
|
| 1028 |
"advmod:tmod":{
|
| 1029 |
-
"p":0.
|
| 1030 |
-
"r":0.
|
| 1031 |
-
"f":0.
|
| 1032 |
},
|
| 1033 |
"advmod:emph":{
|
| 1034 |
-
"p":0.
|
| 1035 |
-
"r":0.
|
| 1036 |
-
"f":0.
|
| 1037 |
},
|
| 1038 |
"amod":{
|
| 1039 |
-
"p":0.
|
| 1040 |
"r":0.8875675676,
|
| 1041 |
-
"f":0.
|
| 1042 |
},
|
| 1043 |
"conj:expl":{
|
| 1044 |
-
"p":0.
|
| 1045 |
-
"r":0.
|
| 1046 |
-
"f":0.
|
| 1047 |
},
|
| 1048 |
"advmod:neg":{
|
| 1049 |
-
"p":0.
|
| 1050 |
-
"r":0.
|
| 1051 |
-
"f":0.
|
| 1052 |
},
|
| 1053 |
"advcl:cmp":{
|
| 1054 |
-
"p":0.
|
| 1055 |
-
"r":0.
|
| 1056 |
-
"f":0.
|
| 1057 |
},
|
| 1058 |
"nsubj:outer":{
|
| 1059 |
-
"p":0.
|
| 1060 |
"r":0.3684210526,
|
| 1061 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1062 |
},
|
| 1063 |
"advcl:abs":{
|
| 1064 |
-
"p":0.
|
| 1065 |
-
"r":0.
|
| 1066 |
-
"f":0.
|
| 1067 |
},
|
| 1068 |
"aux:pass":{
|
| 1069 |
-
"p":0.
|
| 1070 |
"r":0.9575551783,
|
| 1071 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1072 |
},
|
| 1073 |
"dep":{
|
| 1074 |
"p":0.0,
|
| 1075 |
"r":0.0,
|
| 1076 |
"f":0.0
|
| 1077 |
},
|
| 1078 |
-
"advcl:pred":{
|
| 1079 |
-
"p":0.3203883495,
|
| 1080 |
-
"r":0.1843575419,
|
| 1081 |
-
"f":0.2340425532
|
| 1082 |
-
},
|
| 1083 |
-
"orphan":{
|
| 1084 |
-
"p":0.5263157895,
|
| 1085 |
-
"r":0.3703703704,
|
| 1086 |
-
"f":0.4347826087
|
| 1087 |
-
},
|
| 1088 |
"aux":{
|
| 1089 |
-
"p":0.
|
| 1090 |
-
"r":0.
|
| 1091 |
-
"f":0.
|
| 1092 |
},
|
| 1093 |
"appos":{
|
| 1094 |
-
"p":0.
|
| 1095 |
-
"r":0.
|
| 1096 |
-
"f":0.
|
| 1097 |
-
},
|
| 1098 |
-
"fixed":{
|
| 1099 |
-
"p":0.955,
|
| 1100 |
-
"r":0.8842592593,
|
| 1101 |
-
"f":0.9182692308
|
| 1102 |
},
|
| 1103 |
"parataxis":{
|
| 1104 |
-
"p":0.
|
| 1105 |
-
"r":0.
|
| 1106 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1107 |
},
|
| 1108 |
"flat":{
|
| 1109 |
-
"p":0.
|
| 1110 |
-
"r":0.
|
| 1111 |
-
"f":0.
|
| 1112 |
},
|
| 1113 |
"vocative":{
|
| 1114 |
-
"p":0.
|
| 1115 |
"r":0.5737704918,
|
| 1116 |
-
"f":0.
|
| 1117 |
-
},
|
| 1118 |
-
"dislocated":{
|
| 1119 |
-
"p":0.3333333333,
|
| 1120 |
-
"r":0.0967741935,
|
| 1121 |
-
"f":0.15
|
| 1122 |
},
|
| 1123 |
-
"
|
| 1124 |
-
"p":0.
|
| 1125 |
-
"r":0.
|
| 1126 |
-
"f":0.
|
| 1127 |
},
|
| 1128 |
"reparandum":{
|
| 1129 |
-
"p":0.
|
| 1130 |
"r":0.0833333333,
|
| 1131 |
-
"f":0.
|
| 1132 |
},
|
| 1133 |
"dislocated:nsubj":{
|
| 1134 |
"p":0.0,
|
|
@@ -1140,35 +1145,35 @@
|
|
| 1140 |
"r":0.0,
|
| 1141 |
"f":0.0
|
| 1142 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1143 |
"obl:agent":{
|
| 1144 |
-
"p":0.
|
| 1145 |
-
"r":0.
|
| 1146 |
-
"f":0.
|
| 1147 |
},
|
| 1148 |
"flat:name":{
|
| 1149 |
-
"p":0.
|
| 1150 |
"r":0.8965517241,
|
| 1151 |
-
"f":0.
|
| 1152 |
-
},
|
| 1153 |
-
"flat:foreign":{
|
| 1154 |
-
"p":0.375,
|
| 1155 |
-
"r":1.0,
|
| 1156 |
-
"f":0.5454545455
|
| 1157 |
},
|
| 1158 |
"obl:tmod":{
|
| 1159 |
-
"p":0.
|
| 1160 |
"r":0.125,
|
| 1161 |
-
"f":0.
|
| 1162 |
},
|
| 1163 |
-
"
|
| 1164 |
"p":0.0,
|
| 1165 |
"r":0.0,
|
| 1166 |
"f":0.0
|
| 1167 |
},
|
| 1168 |
-
"
|
| 1169 |
-
"p":0.
|
| 1170 |
-
"r":0.
|
| 1171 |
-
"f":0.
|
| 1172 |
},
|
| 1173 |
"parataxis:reporting":{
|
| 1174 |
"p":0.0,
|
|
@@ -1206,20 +1211,20 @@
|
|
| 1206 |
"f":0.0
|
| 1207 |
}
|
| 1208 |
},
|
| 1209 |
-
"
|
| 1210 |
-
"
|
| 1211 |
-
"
|
| 1212 |
-
"
|
| 1213 |
-
"
|
| 1214 |
-
"trainable_lemmatizer_loss":3499.3652743734,
|
| 1215 |
-
"parser_loss":27590.0109430107
|
| 1216 |
},
|
| 1217 |
"sources":[
|
| 1218 |
-
"UD_Latin-Perseus",
|
| 1219 |
-
"UD_Latin-PROIEL",
|
| 1220 |
-
"UD_Latin-ITTB",
|
| 1221 |
-
"UD_Latin-LLCT",
|
| 1222 |
-
"UD_Latin-UDante"
|
|
|
|
|
|
|
| 1223 |
],
|
| 1224 |
"requirements":[
|
| 1225 |
"spacy_lookups_data @ git+https://github.com/diyclassics/spacy-lookups-data.git#egg=spacy-lookups-data",
|
|
|
|
| 1 |
{
|
| 2 |
"lang":"la",
|
| 3 |
"name":"core_web_trf",
|
| 4 |
+
"version":"3.7.7",
|
| 5 |
"description":"",
|
| 6 |
"author":"Patrick J. Burns; with Nora Bernhardt [ner], Tim Geelhaar [tagger, morphologizer, parser, ner], Vincent Koch [ner]",
|
| 7 |
"email":"pjb311@nyu.edu",
|
| 8 |
"url":"https://diyclassics.github.io/",
|
| 9 |
"license":"MIT",
|
| 10 |
+
"spacy_version":">=3.7.5,<3.8.0",
|
| 11 |
+
"spacy_git_version":"a6d0fc360",
|
| 12 |
"vectors":{
|
| 13 |
"width":0,
|
| 14 |
"vectors":0,
|
|
|
|
| 811 |
]
|
| 812 |
},
|
| 813 |
"pipeline":[
|
| 814 |
+
"senter",
|
| 815 |
"transformer",
|
| 816 |
"normer",
|
| 817 |
"tagger",
|
|
|
|
| 822 |
"ner"
|
| 823 |
],
|
| 824 |
"components":[
|
| 825 |
+
"senter",
|
| 826 |
"transformer",
|
| 827 |
"normer",
|
| 828 |
"tagger",
|
|
|
|
| 836 |
|
| 837 |
],
|
| 838 |
"performance":{
|
| 839 |
+
"ents_f":0.9601304525,
|
| 840 |
+
"ents_p":0.9631931948,
|
| 841 |
+
"ents_r":0.9570871261,
|
| 842 |
"ents_per_type":{
|
| 843 |
"PERSON":{
|
| 844 |
+
"p":0.966012543,
|
| 845 |
+
"r":0.9727031982,
|
| 846 |
+
"f":0.9693463256
|
| 847 |
},
|
| 848 |
"LOC":{
|
| 849 |
+
"p":0.9465290807,
|
| 850 |
+
"r":0.8913427562,
|
| 851 |
+
"f":0.9181073703
|
| 852 |
},
|
| 853 |
"NORP":{
|
| 854 |
+
"p":1.0,
|
| 855 |
"r":0.9369369369,
|
| 856 |
+
"f":0.9674418605
|
| 857 |
}
|
| 858 |
},
|
| 859 |
+
"transformer_loss":11904.1139860171,
|
| 860 |
+
"ner_loss":56.6517711698,
|
| 861 |
+
"sents_f":0.9959496442,
|
| 862 |
+
"sents_p":0.9945343244,
|
| 863 |
+
"sents_r":0.997368998,
|
| 864 |
+
"tag_acc":0.9640958514,
|
| 865 |
+
"pos_acc":0.9831838987,
|
| 866 |
+
"morph_acc":0.9581374663,
|
| 867 |
"morph_per_feat":{
|
| 868 |
"Case":{
|
| 869 |
+
"p":0.9639107612,
|
| 870 |
+
"r":0.9600554205,
|
| 871 |
+
"f":0.9619792281
|
| 872 |
},
|
| 873 |
"Gender":{
|
| 874 |
+
"p":0.9704207442,
|
| 875 |
+
"r":0.9668658936,
|
| 876 |
+
"f":0.9686400574
|
| 877 |
},
|
| 878 |
"Number":{
|
| 879 |
+
"p":0.9882738621,
|
| 880 |
+
"r":0.985457441,
|
| 881 |
+
"f":0.9868636421
|
| 882 |
},
|
| 883 |
"Mood":{
|
| 884 |
+
"p":0.9832762836,
|
| 885 |
+
"r":0.9826035966,
|
| 886 |
+
"f":0.982939825
|
| 887 |
},
|
| 888 |
"Person":{
|
| 889 |
+
"p":0.9932344122,
|
| 890 |
+
"r":0.9924713836,
|
| 891 |
+
"f":0.9928527513
|
| 892 |
},
|
| 893 |
"Tense":{
|
| 894 |
+
"p":0.976521164,
|
| 895 |
+
"r":0.9763597289,
|
| 896 |
+
"f":0.9764404398
|
| 897 |
},
|
| 898 |
"VerbForm":{
|
| 899 |
+
"p":0.9860205033,
|
| 900 |
+
"r":0.9809271523,
|
| 901 |
+
"f":0.9834672333
|
| 902 |
},
|
| 903 |
"Voice":{
|
| 904 |
+
"p":0.9829952525,
|
| 905 |
+
"r":0.9858886676,
|
| 906 |
+
"f":0.984439834
|
| 907 |
}
|
| 908 |
},
|
| 909 |
+
"lemma_acc":0.9531809911,
|
| 910 |
+
"dep_uas":0.8882308136,
|
| 911 |
+
"dep_las":0.8492401865,
|
| 912 |
"dep_las_per_type":{
|
| 913 |
"root":{
|
| 914 |
+
"p":0.931788369,
|
| 915 |
+
"r":0.9344442008,
|
| 916 |
+
"f":0.9331143952
|
| 917 |
},
|
| 918 |
"cop":{
|
| 919 |
+
"p":0.8331784387,
|
| 920 |
+
"r":0.8542162935,
|
| 921 |
+
"f":0.8435662197
|
| 922 |
},
|
| 923 |
"nsubj":{
|
| 924 |
+
"p":0.8516872095,
|
| 925 |
+
"r":0.8516872095,
|
| 926 |
+
"f":0.8516872095
|
| 927 |
},
|
| 928 |
"nmod":{
|
| 929 |
+
"p":0.8462984724,
|
| 930 |
+
"r":0.8320240296,
|
| 931 |
+
"f":0.8391005476
|
| 932 |
},
|
| 933 |
"obj":{
|
| 934 |
+
"p":0.8521505376,
|
| 935 |
+
"r":0.8643490116,
|
| 936 |
+
"f":0.8582064298
|
| 937 |
},
|
| 938 |
"det":{
|
| 939 |
+
"p":0.9342518733,
|
| 940 |
+
"r":0.9319990354,
|
| 941 |
+
"f":0.9331240946
|
| 942 |
},
|
| 943 |
"cc":{
|
| 944 |
+
"p":0.9080487222,
|
| 945 |
+
"r":0.9205811138,
|
| 946 |
+
"f":0.9142719731
|
| 947 |
},
|
| 948 |
"conj":{
|
| 949 |
+
"p":0.7781139687,
|
| 950 |
+
"r":0.7745983936,
|
| 951 |
+
"f":0.7763522013
|
| 952 |
},
|
| 953 |
"nummod":{
|
| 954 |
+
"p":0.9216101695,
|
| 955 |
+
"r":0.935483871,
|
| 956 |
+
"f":0.9284951974
|
| 957 |
},
|
| 958 |
"case":{
|
| 959 |
+
"p":0.9727039178,
|
| 960 |
+
"r":0.9832819348,
|
| 961 |
+
"f":0.9779643232
|
| 962 |
},
|
| 963 |
"obl":{
|
| 964 |
+
"p":0.8034008407,
|
| 965 |
+
"r":0.8227352769,
|
| 966 |
+
"f":0.8129531174
|
| 967 |
},
|
| 968 |
"acl":{
|
| 969 |
+
"p":0.7437788018,
|
| 970 |
+
"r":0.6879795396,
|
| 971 |
+
"f":0.7147918512
|
| 972 |
},
|
| 973 |
"ccomp":{
|
| 974 |
+
"p":0.6428571429,
|
| 975 |
+
"r":0.6331658291,
|
| 976 |
+
"f":0.6379746835
|
| 977 |
},
|
| 978 |
"acl:relcl":{
|
| 979 |
+
"p":0.7105263158,
|
| 980 |
+
"r":0.700843608,
|
| 981 |
+
"f":0.7056517478
|
| 982 |
},
|
| 983 |
"advmod":{
|
| 984 |
+
"p":0.7999080037,
|
| 985 |
+
"r":0.8080855019,
|
| 986 |
+
"f":0.8039759593
|
| 987 |
},
|
| 988 |
"mark":{
|
| 989 |
+
"p":0.8895979579,
|
| 990 |
+
"r":0.8704339682,
|
| 991 |
+
"f":0.8799116301
|
| 992 |
},
|
| 993 |
"xcomp":{
|
| 994 |
+
"p":0.795045045,
|
| 995 |
+
"r":0.7998489426,
|
| 996 |
+
"f":0.797439759
|
| 997 |
},
|
| 998 |
"csubj:pass":{
|
| 999 |
+
"p":0.7127659574,
|
| 1000 |
+
"r":0.6380952381,
|
| 1001 |
+
"f":0.6733668342
|
| 1002 |
},
|
| 1003 |
"advmod:lmod":{
|
| 1004 |
+
"p":0.9055944056,
|
| 1005 |
+
"r":0.8839590444,
|
| 1006 |
+
"f":0.8946459413
|
| 1007 |
},
|
| 1008 |
"obl:arg":{
|
| 1009 |
+
"p":0.8297546012,
|
| 1010 |
+
"r":0.8098802395,
|
| 1011 |
+
"f":0.8196969697
|
| 1012 |
},
|
| 1013 |
"csubj":{
|
| 1014 |
+
"p":0.7437106918,
|
| 1015 |
+
"r":0.7413793103,
|
| 1016 |
+
"f":0.7425431711
|
| 1017 |
},
|
| 1018 |
"discourse":{
|
| 1019 |
+
"p":0.8915662651,
|
| 1020 |
+
"r":0.8921319797,
|
| 1021 |
+
"f":0.8918490327
|
| 1022 |
},
|
| 1023 |
"advcl":{
|
| 1024 |
+
"p":0.6983372922,
|
| 1025 |
+
"r":0.7191780822,
|
| 1026 |
+
"f":0.708604483
|
| 1027 |
},
|
| 1028 |
"nsubj:pass":{
|
| 1029 |
+
"p":0.8316205534,
|
| 1030 |
+
"r":0.8449799197,
|
| 1031 |
+
"f":0.838247012
|
| 1032 |
},
|
| 1033 |
"advmod:tmod":{
|
| 1034 |
+
"p":0.7633928571,
|
| 1035 |
+
"r":0.7844036697,
|
| 1036 |
+
"f":0.7737556561
|
| 1037 |
},
|
| 1038 |
"advmod:emph":{
|
| 1039 |
+
"p":0.72,
|
| 1040 |
+
"r":0.69,
|
| 1041 |
+
"f":0.7046808511
|
| 1042 |
},
|
| 1043 |
"amod":{
|
| 1044 |
+
"p":0.8834289813,
|
| 1045 |
"r":0.8875675676,
|
| 1046 |
+
"f":0.8854934388
|
| 1047 |
},
|
| 1048 |
"conj:expl":{
|
| 1049 |
+
"p":0.4909090909,
|
| 1050 |
+
"r":0.2903225806,
|
| 1051 |
+
"f":0.3648648649
|
| 1052 |
},
|
| 1053 |
"advmod:neg":{
|
| 1054 |
+
"p":0.8902554399,
|
| 1055 |
+
"r":0.8961904762,
|
| 1056 |
+
"f":0.8932130992
|
| 1057 |
},
|
| 1058 |
"advcl:cmp":{
|
| 1059 |
+
"p":0.6553191489,
|
| 1060 |
+
"r":0.6184738956,
|
| 1061 |
+
"f":0.6363636364
|
| 1062 |
},
|
| 1063 |
"nsubj:outer":{
|
| 1064 |
+
"p":0.35,
|
| 1065 |
"r":0.3684210526,
|
| 1066 |
+
"f":0.358974359
|
| 1067 |
+
},
|
| 1068 |
+
"advcl:pred":{
|
| 1069 |
+
"p":0.329787234,
|
| 1070 |
+
"r":0.1731843575,
|
| 1071 |
+
"f":0.2271062271
|
| 1072 |
},
|
| 1073 |
"advcl:abs":{
|
| 1074 |
+
"p":0.8535911602,
|
| 1075 |
+
"r":0.860724234,
|
| 1076 |
+
"f":0.8571428571
|
| 1077 |
},
|
| 1078 |
"aux:pass":{
|
| 1079 |
+
"p":0.94,
|
| 1080 |
"r":0.9575551783,
|
| 1081 |
+
"f":0.9486963835
|
| 1082 |
+
},
|
| 1083 |
+
"fixed":{
|
| 1084 |
+
"p":0.9532019704,
|
| 1085 |
+
"r":0.8958333333,
|
| 1086 |
+
"f":0.923627685
|
| 1087 |
+
},
|
| 1088 |
+
"orphan":{
|
| 1089 |
+
"p":0.5299145299,
|
| 1090 |
+
"r":0.3827160494,
|
| 1091 |
+
"f":0.4444444444
|
| 1092 |
},
|
| 1093 |
"dep":{
|
| 1094 |
"p":0.0,
|
| 1095 |
"r":0.0,
|
| 1096 |
"f":0.0
|
| 1097 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1098 |
"aux":{
|
| 1099 |
+
"p":0.8827586207,
|
| 1100 |
+
"r":0.9208633094,
|
| 1101 |
+
"f":0.9014084507
|
| 1102 |
},
|
| 1103 |
"appos":{
|
| 1104 |
+
"p":0.9301242236,
|
| 1105 |
+
"r":0.8946975355,
|
| 1106 |
+
"f":0.9120669966
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1107 |
},
|
| 1108 |
"parataxis":{
|
| 1109 |
+
"p":0.5,
|
| 1110 |
+
"r":0.3541666667,
|
| 1111 |
+
"f":0.4146341463
|
| 1112 |
+
},
|
| 1113 |
+
"dislocated:obj":{
|
| 1114 |
+
"p":0.7676767677,
|
| 1115 |
+
"r":0.7835051546,
|
| 1116 |
+
"f":0.7755102041
|
| 1117 |
},
|
| 1118 |
"flat":{
|
| 1119 |
+
"p":0.8504273504,
|
| 1120 |
+
"r":0.7713178295,
|
| 1121 |
+
"f":0.8089430894
|
| 1122 |
},
|
| 1123 |
"vocative":{
|
| 1124 |
+
"p":0.625,
|
| 1125 |
"r":0.5737704918,
|
| 1126 |
+
"f":0.5982905983
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1127 |
},
|
| 1128 |
+
"ccomp:reported":{
|
| 1129 |
+
"p":0.2857142857,
|
| 1130 |
+
"r":0.4347826087,
|
| 1131 |
+
"f":0.3448275862
|
| 1132 |
},
|
| 1133 |
"reparandum":{
|
| 1134 |
+
"p":0.3333333333,
|
| 1135 |
"r":0.0833333333,
|
| 1136 |
+
"f":0.1333333333
|
| 1137 |
},
|
| 1138 |
"dislocated:nsubj":{
|
| 1139 |
"p":0.0,
|
|
|
|
| 1145 |
"r":0.0,
|
| 1146 |
"f":0.0
|
| 1147 |
},
|
| 1148 |
+
"dislocated":{
|
| 1149 |
+
"p":0.4444444444,
|
| 1150 |
+
"r":0.1290322581,
|
| 1151 |
+
"f":0.2
|
| 1152 |
+
},
|
| 1153 |
"obl:agent":{
|
| 1154 |
+
"p":0.52,
|
| 1155 |
+
"r":0.2574257426,
|
| 1156 |
+
"f":0.3443708609
|
| 1157 |
},
|
| 1158 |
"flat:name":{
|
| 1159 |
+
"p":0.6842105263,
|
| 1160 |
"r":0.8965517241,
|
| 1161 |
+
"f":0.776119403
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1162 |
},
|
| 1163 |
"obl:tmod":{
|
| 1164 |
+
"p":0.25,
|
| 1165 |
"r":0.125,
|
| 1166 |
+
"f":0.1666666667
|
| 1167 |
},
|
| 1168 |
+
"flat:foreign":{
|
| 1169 |
"p":0.0,
|
| 1170 |
"r":0.0,
|
| 1171 |
"f":0.0
|
| 1172 |
},
|
| 1173 |
+
"obl:lmod":{
|
| 1174 |
+
"p":0.0,
|
| 1175 |
+
"r":0.0,
|
| 1176 |
+
"f":0.0
|
| 1177 |
},
|
| 1178 |
"parataxis:reporting":{
|
| 1179 |
"p":0.0,
|
|
|
|
| 1211 |
"f":0.0
|
| 1212 |
}
|
| 1213 |
},
|
| 1214 |
+
"senter_loss":149.3224464637,
|
| 1215 |
+
"tagger_loss":103.7340285726,
|
| 1216 |
+
"morphologizer_loss":1120.5138759464,
|
| 1217 |
+
"trainable_lemmatizer_loss":1068.4113499675,
|
| 1218 |
+
"parser_loss":19163.8495826822
|
|
|
|
|
|
|
| 1219 |
},
|
| 1220 |
"sources":[
|
| 1221 |
+
"UD_Latin-Perseus (via Gamba/Zeman 2023)",
|
| 1222 |
+
"UD_Latin-PROIEL (via Gamba/Zeman 2023)",
|
| 1223 |
+
"UD_Latin-ITTB (via Gamba/Zeman 2023)",
|
| 1224 |
+
"UD_Latin-LLCT (via Gamba/Zeman 2023",
|
| 1225 |
+
"UD_Latin-UDante (via Gamba/Zeman 2023)",
|
| 1226 |
+
"CIRCSE/LASLA: LASLA Corpus",
|
| 1227 |
+
"UD_Latin-CIRCSE"
|
| 1228 |
],
|
| 1229 |
"requirements":[
|
| 1230 |
"spacy_lookups_data @ git+https://github.com/diyclassics/spacy-lookups-data.git#egg=spacy-lookups-data",
|
morphologizer/model
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 675109300
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4314e207681175f24999911fb6021e49163510932e816af12cb1ce5db54901d4
|
| 3 |
size 675109300
|
ner/model
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 673159757
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:418d4628460fe4adac04843c2da156ebbe59eee6624b18e20c32ebd9231704c8
|
| 3 |
size 673159757
|
ner/moves
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
��moves��{"0":{},"1":{"PERSON":
|
|
|
|
| 1 |
+
��moves��{"0":{},"1":{"PERSON":16680,"LOC":2845,"NORP":119},"2":{"PERSON":16680,"LOC":2845,"NORP":119},"3":{"PERSON":16680,"LOC":2845,"NORP":119},"4":{"PERSON":16680,"LOC":2845,"NORP":119,"":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 676235346
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:603d1ed7d520cc49dd6dbda77f5734ebdaa1af716137d8b4413e2dd0a9f38ad6
|
| 3 |
size 676235346
|
senter/cfg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"overwrite":false
|
| 3 |
+
}
|
senter/model
ADDED
|
Binary file (255 kB). View file
|
|
|
tagger/model
CHANGED
|
Binary files a/tagger/model and b/tagger/model differ
|
|
|
trainable_lemmatizer/cfg
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
trainable_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:af6dfb059ad18026fdc3e92c427c082c551aef965740e70b9988b18722e750f3
|
| 3 |
+
size 14131797
|
trainable_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:a15aefb70d9da8a30f7072f6609d8523a253cf54394eade11c4868ee7a09010b
|
| 3 |
+
size 949814
|
transformer/model
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 672940068
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b631c9775406d20af454f70054c364541d2ea0f5dccd1cc390296008d1ea6c0f
|
| 3 |
size 672940068
|
vocab/strings.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|