Merge branch 'develop' of https://github.com/explosion/spaCy into develop

spacy/lang/nl/tag_map.py

@@ -2,7 +2,7 @@
 from __future__ import unicode_literals
 
 from ...symbols import POS, PUNCT, ADJ, NUM, DET, ADV, ADP, X, VERB
-from ...symbols import NOUN, PROPN, SPACE, PRON, CONJ, PREP
+from ...symbols import NOUN, PROPN, SPACE, PRON, CONJ
 
 
 TAG_MAP = {

website/usage/_adding-languages/_language-data.jade

@@ -287,6 +287,7 @@ p
     |  all personal pronouns.
 
 +h(3, "norm-exceptions") Norm exceptions
+    +tag-new(2)
 
 p
     |  In addition to #[code ORTH] or #[code LEMMA], tokenizer exceptions can
@@ -351,6 +352,7 @@ p
     |  always have priority over the atrribute getters.
 
 +h(3, "lex-attrs") Lexical attributes
+    +tag-new(2)
 
 p
     |  spaCy provides a range of #[+api("token#attributes") #[code Token] attributes]
@@ -435,6 +437,7 @@ p
                     code lang/#{lang}/syntax_iterators.py
 
 +h(3, "lemmatizer") Lemmatizer
+    +tag-new(2)
 
 p
     |  As of v2.0, spaCy supports simple lookup-based lemmatization. This is

website/usage/_v2/_migrating.jade

@@ -105,7 +105,7 @@ p
 
 p
     |  All built-in pipeline components are now subclasses of
-    |  #[+api("pipe") #[code Pipe]] are fully trainable and serializable,
+    |  #[+api("pipe") #[code Pipe]], fully trainable and serializable,
     |  and follow the same API. Instead of updating the model and telling
     |  spaCy when to #[em stop], you can now explicitly call
     |  #[+api("language#begin_training") #[code begin_taining]], which