ljvmiranda921
commited on
Commit
•
444c4a1
1
Parent(s):
69b67e3
xx_grc_sigtyp_trf-0.1.0: Update SIGTYP pipeline
Browse files- .gitattributes +1 -0
- README.md +0 -0
- config.cfg +26 -5
- meta.json +0 -0
- morphologizer/cfg +0 -0
- morphologizer/model +3 -0
- parser/model +1 -1
- tagger/model +1 -1
- trainable_lemmatizer/model +1 -1
- transformer/model +1 -1
- vocab/strings.json +0 -0
- xx_grc_sigtyp_trf-any-py3-none-any.whl +2 -2
.gitattributes
CHANGED
@@ -39,3 +39,4 @@ trainable_lemmatizer/model filter=lfs diff=lfs merge=lfs -text
|
|
39 |
trainable_lemmatizer/trees filter=lfs diff=lfs merge=lfs -text
|
40 |
transformer/model filter=lfs diff=lfs merge=lfs -text
|
41 |
xx_grc_sigtyp_trf-any-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
|
|
|
|
39 |
trainable_lemmatizer/trees filter=lfs diff=lfs merge=lfs -text
|
40 |
transformer/model filter=lfs diff=lfs merge=lfs -text
|
41 |
xx_grc_sigtyp_trf-any-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
|
42 |
+
morphologizer/model filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
config.cfg
CHANGED
@@ -10,7 +10,7 @@ seed = 42
|
|
10 |
|
11 |
[nlp]
|
12 |
lang = "xx"
|
13 |
-
pipeline = ["transformer","parser","trainable_lemmatizer","tagger"]
|
14 |
batch_size = 128
|
15 |
disabled = []
|
16 |
before_creation = null
|
@@ -20,6 +20,24 @@ tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
|
|
20 |
|
21 |
[components]
|
22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
[components.parser]
|
24 |
factory = "parser"
|
25 |
learn_tokens = false
|
@@ -166,14 +184,17 @@ total_steps = 20000
|
|
166 |
initial_rate = 0.00005
|
167 |
|
168 |
[training.score_weights]
|
169 |
-
dep_uas = 0.
|
170 |
-
dep_las = 0.
|
171 |
dep_las_per_type = null
|
172 |
sents_p = null
|
173 |
sents_r = null
|
174 |
sents_f = 0.0
|
175 |
-
lemma_acc = 0.
|
176 |
-
tag_acc = 0.
|
|
|
|
|
|
|
177 |
|
178 |
[pretraining]
|
179 |
|
|
|
10 |
|
11 |
[nlp]
|
12 |
lang = "xx"
|
13 |
+
pipeline = ["transformer","parser","trainable_lemmatizer","tagger","morphologizer"]
|
14 |
batch_size = 128
|
15 |
disabled = []
|
16 |
before_creation = null
|
|
|
20 |
|
21 |
[components]
|
22 |
|
23 |
+
[components.morphologizer]
|
24 |
+
factory = "morphologizer"
|
25 |
+
extend = false
|
26 |
+
label_smoothing = 0.0
|
27 |
+
overwrite = true
|
28 |
+
scorer = {"@scorers":"spacy.morphologizer_scorer.v1"}
|
29 |
+
|
30 |
+
[components.morphologizer.model]
|
31 |
+
@architectures = "spacy.Tagger.v2"
|
32 |
+
nO = null
|
33 |
+
normalize = false
|
34 |
+
|
35 |
+
[components.morphologizer.model.tok2vec]
|
36 |
+
@architectures = "spacy-transformers.TransformerListener.v1"
|
37 |
+
grad_factor = 1.0
|
38 |
+
pooling = {"@layers":"reduce_mean.v1"}
|
39 |
+
upstream = "*"
|
40 |
+
|
41 |
[components.parser]
|
42 |
factory = "parser"
|
43 |
learn_tokens = false
|
|
|
184 |
initial_rate = 0.00005
|
185 |
|
186 |
[training.score_weights]
|
187 |
+
dep_uas = 0.09
|
188 |
+
dep_las = 0.09
|
189 |
dep_las_per_type = null
|
190 |
sents_p = null
|
191 |
sents_r = null
|
192 |
sents_f = 0.0
|
193 |
+
lemma_acc = 0.17
|
194 |
+
tag_acc = 0.17
|
195 |
+
pos_acc = 0.25
|
196 |
+
morph_acc = 0.25
|
197 |
+
morph_per_feat = null
|
198 |
|
199 |
[pretraining]
|
200 |
|
meta.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
morphologizer/cfg
ADDED
The diff for this file is too large to render.
See raw diff
|
|
morphologizer/model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c24b855640bb04e977e50c789a09fa301c8921a5811324a9a0fb10c0060bad0
|
3 |
+
size 4543905
|
parser/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2700271
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28e380fb48559ec73335aaac43e65f105da904c9ae1f434be16ad1b8f1301486
|
3 |
size 2700271
|
tagger/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5549757
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27cd948c2c905bd982f9350bb01edb07eefe2f81102f2b8d789417af11abff54
|
3 |
size 5549757
|
trainable_lemmatizer/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 22120169
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3cf8a691ff1bd47a9b04ad111e4fb9edf0a36b3f6d79d00701f324e3b8ee8843
|
3 |
size 22120169
|
transformer/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 509231398
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0605f671749f4ad8e319f5db7c5a4b6fc2b238eca319e237b0e88e0f9cdd6e21
|
3 |
size 509231398
|
vocab/strings.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
xx_grc_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 sha256:47d0ffe937a98a6dd4fe4addca4901fca2242c86a178db146488ad6494af4122
|
3 |
+
size 499447084
|