gistfile1.txt

--- training/pt_core_news_lg_rule/model-best/config.cfg	2021-11-22 10:28:51.610899763 +0100
+++ training-edit-tree-bench/pt_core_news_lg/model-best/config.cfg	2021-11-21 17:40:53.559460807 +0100
@@ -12,7 +12,7 @@
 
 [nlp]
 lang = "pt"
-pipeline = ["tok2vec","morphologizer","parser","senter","attribute_ruler","lemmatizer","ner"]
+pipeline = ["tok2vec","morphologizer","parser","senter","attribute_ruler","edit_tree_lemmatizer","ner"]
 disabled = ["parser","senter","attribute_ruler","ner"]
 before_creation = null
 after_creation = null
@@ -27,12 +27,21 @@
 scorer = {"@scorers":"spacy.attribute_ruler_scorer.v1"}
 validate = false
 
-[components.lemmatizer]
-factory = "lemmatizer"
-mode = "lookup"
-model = null
+[components.edit_tree_lemmatizer]
+factory = "edit_tree_lemmatizer"
+backoff = "form"
+min_tree_freq = 3
 overwrite = false
-scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
+top_k = 1
+
+[components.edit_tree_lemmatizer.model]
+@architectures = "spacy.Tagger.v1"
+nO = null
+
+[components.edit_tree_lemmatizer.model.tok2vec]
+@architectures = "spacy.Tok2VecListener.v1"
+width = ${components.tok2vec.model.encode.width}
+upstream = "tok2vec"
 
 [components.morphologizer]
 factory = "morphologizer"