Update spaCy pipeline

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 textcat/model filter=lfs diff=lfs merge=lfs -text
+da_spacy_sentiment-any-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+tok2vec/model filter=lfs diff=lfs merge=lfs -text
+vocab/key2row filter=lfs diff=lfs merge=lfs -text
+vocab/vectors filter=lfs diff=lfs merge=lfs -text

config.cfg

@@ -1,7 +1,7 @@
 [paths]
 train = "./corpus/train.sentiment.spacy"
 dev = "./corpus/dev.sentiment.spacy"
-vectors = null
+vectors = "da_core_news_md"
 init_tok2vec = null
 
 [system]
@@ -10,7 +10,7 @@ seed = 0
 
 [nlp]
 lang = "da"
-pipeline = ["textcat"]
+pipeline = ["tok2vec","textcat"]
 batch_size = 1000
 disabled = []
 before_creation = null
@@ -26,12 +26,41 @@ scorer = {"@scorers":"spacy.textcat_scorer.v2"}
 threshold = 0.0
 
 [components.textcat.model]
+@architectures = "spacy.TextCatEnsemble.v2"
+nO = null
+
+[components.textcat.model.linear_model]
 @architectures = "spacy.TextCatBOW.v2"
 exclusive_classes = true
 ngram_size = 1
 no_output_layer = false
 nO = null
 
+[components.textcat.model.tok2vec]
+@architectures = "spacy.Tok2VecListener.v1"
+width = ${components.tok2vec.model.encode.width}
+upstream = "*"
+
+[components.tok2vec]
+factory = "tok2vec"
+
+[components.tok2vec.model]
+@architectures = "spacy.Tok2Vec.v2"
+
+[components.tok2vec.model.embed]
+@architectures = "spacy.MultiHashEmbed.v2"
+width = ${components.tok2vec.model.encode.width}
+attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
+rows = [5000,1000,2500,2500]
+include_static_vectors = true
+
+[components.tok2vec.model.encode]
+@architectures = "spacy.MaxoutWindowEncoder.v2"
+width = 256
+depth = 8
+window_size = 1
+maxout_pieces = 3
+
 [corpora]
 
 [corpora.dev]

meta.json

@@ -10,12 +10,15 @@
   "spacy_version":">=3.5.1,<3.6.0",
   "spacy_git_version":"Unknown",
   "vectors":{
-    "width":0,
-    "vectors":0,
-    "keys":0,
-    "name":null
+    "width":300,
+    "vectors":20000,
+    "keys":500000,
+    "name":"da_vectors"
   },
   "labels":{
+    "tok2vec":[
+
+    ],
     "textcat":[
       "neutral",
       "negative",
@@ -23,42 +26,45 @@
     ]
   },
   "pipeline":[
+    "tok2vec",
     "textcat"
   ],
   "components":[
+    "tok2vec",
     "textcat"
   ],
   "disabled":[
 
   ],
   "performance":{
-    "cats_score":0.4644417144,
+    "cats_score":0.4935672515,
     "cats_score_desc":"macro F",
-    "cats_micro_p":0.7301587302,
-    "cats_micro_r":0.7301587302,
-    "cats_micro_f":0.7301587302,
-    "cats_macro_p":0.5166357238,
-    "cats_macro_r":0.4431664354,
-    "cats_macro_f":0.4644417144,
-    "cats_macro_auc":0.6167244706,
+    "cats_micro_p":0.6904761905,
+    "cats_micro_r":0.6904761905,
+    "cats_micro_f":0.6904761905,
+    "cats_macro_p":0.4864024864,
+    "cats_macro_r":0.502577943,
+    "cats_macro_f":0.4935672515,
+    "cats_macro_auc":0.6640492205,
     "cats_f_per_type":{
       "neutral":{
-        "p":0.7990654206,
-        "r":0.8860103627,
-        "f":0.8402948403
+        "p":0.8181818182,
+        "r":0.792746114,
+        "f":0.8052631579
       },
       "negative":{
-        "p":0.4545454545,
-        "r":0.2272727273,
-        "f":0.303030303
+        "p":0.3076923077,
+        "r":0.3636363636,
+        "f":0.3333333333
       },
       "positive":{
-        "p":0.2962962963,
-        "r":0.2162162162,
-        "f":0.25
+        "p":0.3333333333,
+        "r":0.3513513514,
+        "f":0.3421052632
       }
     },
-    "textcat_loss":7.6585407546
+    "tok2vec_loss":51.8325935973,
+    "textcat_loss":16.7191163995
   },
   "requirements":[
 

textcat/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f757344345aaa840842e42feb51d88d09743dbd845898f861c7269037720bfae
-size 3146475
+oid sha256:751028d05294d492933266f6e518ed982b7051a96b4f63820ddf58d7d196d0c1
+size 3944012

tok2vec/cfg

@@ -0,0 +1,3 @@
+{
+
+}

tok2vec/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e4285eced09bf237b2cf427339a9b2dc379b0963bba52b6256d458e076eb0dc
+size 34434008

vocab/key2row

@@ -1 +1,3 @@
-�
+version https://git-lfs.github.com/spec/v1
+oid sha256:29b9f9abc60252769aa9a64072337af1f81f0f15d568dd09c8bdad03789ce961
+size 5996984