Upload 7 files

bg_news_lg-3.5.4-py3-none-any.whl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:555c38f3b370f7da93a3996266068acd8533047f0ec79ff283a1eb308b12760a
-size 260096785
+oid sha256:563d8c7a14474321598d9057c7d3013be744a0d5153bd5c284a4fdb22d0e17d6
+size 260096880

config.cfg

@@ -12,7 +12,7 @@ gpu_allocator = null
 
 [nlp]
 lang = "bg"
-pipeline = ["tok2vec","tagger","morphologizer","parser","ner"]
+pipeline = ["tok2vec","tagger","morphologizer","trainable_lemmatizer","parser","ner"]
 tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
 disabled = []
 before_creation = null
@@ -129,6 +129,24 @@ depth = 8
 window_size = 1
 maxout_pieces = 3
 
+[components.trainable_lemmatizer]
+factory = "trainable_lemmatizer"
+backoff = "orth"
+min_tree_freq = 3
+overwrite = false
+scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
+top_k = 1
+
+[components.trainable_lemmatizer.model]
+@architectures = "spacy.Tagger.v2"
+nO = null
+normalize = false
+
+[components.trainable_lemmatizer.model.tok2vec]
+@architectures = "spacy.Tok2VecListener.v1"
+width = 256
+upstream = "tok2vec"
+
 [corpora]
 
 [corpora.dev]
@@ -192,17 +210,18 @@ eps = 0.00000001
 learn_rate = 0.001
 
 [training.score_weights]
-tag_acc = 0.26
-pos_acc = 0.12
-morph_acc = 0.12
+tag_acc = 0.2
+pos_acc = 0.1
+morph_acc = 0.1
 morph_per_feat = null
-dep_uas = 0.12
-dep_las = 0.12
+lemma_acc = 0.2
+dep_uas = 0.1
+dep_las = 0.1
 dep_las_per_type = null
 sents_p = null
 sents_r = null
 sents_f = 0.0
-ents_f = 0.26
+ents_f = 0.2
 ents_p = 0.0
 ents_r = 0.0
 ents_per_type = null

meta.json

@@ -1031,6 +1031,7 @@
     "tok2vec",
     "tagger",
     "morphologizer",
+    "trainable_lemmatizer",
     "parser",
     "ner"
   ],
@@ -1038,6 +1039,7 @@
     "tok2vec",
     "tagger",
     "morphologizer",
+    "trainable_lemmatizer",
     "parser",
     "ner"
   ],