Update spaCy pipeline

config.cfg

@@ -15,7 +15,7 @@ seed = 0
 
 [nlp]
 lang = "en"
-pipeline = ["tok2vec","ner","textcat_classify"]
+pipeline = ["tok2vec_small","tagger","parser","attribute_ruler","lemmatizer","tok2vec","ner","textcat_classify"]
 batch_size = 1000
 disabled = []
 before_creation = null
@@ -26,6 +26,18 @@ vectors = {"@vectors":"spacy.Vectors.v1"}
 
 [components]
 
+[components.attribute_ruler]
+factory = "attribute_ruler"
+scorer = {"@scorers":"spacy.attribute_ruler_scorer.v1"}
+validate = false
+
+[components.lemmatizer]
+factory = "lemmatizer"
+mode = "rule"
+model = null
+overwrite = false
+scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
+
 [components.ner]
 factory = "ner"
 incorrect_spans_key = null
@@ -47,6 +59,45 @@ nO = null
 width = 256
 upstream = "*"
 
+[components.parser]
+factory = "parser"
+learn_tokens = false
+min_action_freq = 30
+moves = null
+scorer = {"@scorers":"spacy.parser_scorer.v1"}
+update_with_oracle_cut_size = 100
+
+[components.parser.model]
+@architectures = "spacy.TransitionBasedParser.v2"
+state_type = "parser"
+extra_state_tokens = false
+hidden_width = 64
+maxout_pieces = 2
+use_upper = true
+nO = null
+
+[components.parser.model.tok2vec]
+@architectures = "spacy.Tok2VecListener.v1"
+width = 96
+upstream = "tok2vec"
+
+[components.tagger]
+factory = "tagger"
+label_smoothing = 0.0
+neg_prefix = "!"
+overwrite = false
+scorer = {"@scorers":"spacy.tagger_scorer.v1"}
+
+[components.tagger.model]
+@architectures = "spacy.Tagger.v2"
+nO = null
+normalize = false
+
+[components.tagger.model.tok2vec]
+@architectures = "spacy.Tok2VecListener.v1"
+width = 96
+upstream = "tok2vec"
+
 [components.textcat_classify]
 factory = "weighted_textcat"
 class_weights = [0.67,0.33]
@@ -102,6 +153,26 @@ window_size = 1
 maxout_pieces = 3
 depth = 8
 
+[components.tok2vec_small]
+factory = "tok2vec"
+
+[components.tok2vec_small.model]
+@architectures = "spacy.Tok2Vec.v2"
+
+[components.tok2vec_small.model.embed]
+@architectures = "spacy.MultiHashEmbed.v2"
+width = 96
+attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY","IS_SPACE"]
+rows = [5000,1000,2500,2500,50,50]
+include_static_vectors = false
+
+[components.tok2vec_small.model.encode]
+@architectures = "spacy.MaxoutWindowEncoder.v2"
+width = 96
+depth = 4
+window_size = 1
+maxout_pieces = 3
+
 [corpora]
 
 [corpora.dev]
@@ -189,14 +260,22 @@ eps = 0.00000001
 learn_rate = 0.001
 
 [training.score_weights]
-ents_f = 0.5
+tag_acc = 0.25
+dep_uas = 0.12
+dep_las = 0.12
+dep_las_per_type = null
+sents_p = null
+sents_r = null
+sents_f = 0.0
+lemma_acc = 0.25
+ents_f = 0.12
 ents_p = 0.0
 ents_r = 0.0
 ents_per_type = null
-cats_score = 0.25
+cats_score = 0.06
 cats_score_desc = null
 cats_micro_p = null
-cats_micro_r = 0.25
+cats_micro_r = 0.06
 cats_micro_f = null
 cats_macro_p = null
 cats_macro_r = null

en_tako_query_analyzer-any-py3-none-any.whl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:758f2f483a1f44bf0ff426f5c5e2abf5867e859261672a51f8759e97ca667a31
-size 619535137
+oid sha256:d276080166d535d192f52fef9138c4678a32445a14b0c27f9a43c974be5c3aca
+size 619963181

lemmatizer/lookups/lookups.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb64f40c0f8396d1762730c0ddf4dad2a52d138f5a389f71a1a1d088173b7737
+size 972893

meta.json

@@ -120,6 +120,9 @@
     ],
     "attribute_ruler":[
 
+    ],
+    "lemmatizer":[
+
     ],
     "tok2vec":[
 
@@ -155,6 +158,7 @@
     "tagger",
     "parser",
     "attribute_ruler",
+    "lemmatizer",
     "tok2vec",
     "ner",
     "textcat_classify"
@@ -164,6 +168,7 @@
     "tagger",
     "parser",
     "attribute_ruler",
+    "lemmatizer",
     "tok2vec",
     "ner",
     "textcat_classify"