Update spaCy architecture

website/docs/usage/spacy-101.jade

@@ -8,3 +8,85 @@ include ../../_includes/_mixins
     include ../../assets/img/docs/architecture.svg
     .u-text-right
         +button("/assets/img/docs/architecture.svg", false, "secondary").u-text-tag View large graphic
+
++table(["Name", "Description"])
+    +row
+        +cell #[+api("language") #[code Language]]
+        +cell
+            |  A text-processing pipeline. Usually you'll load this once per
+            |  process as #[code nlp] and pass the instance around your application.
+
+    +row
+        +cell #[+api("doc") #[code Doc]]
+        +cell A container for accessing linguistic annotations.
+
+    +row
+        +cell #[+api("span") #[code Span]]
+        +cell A slice from a #[code Doc] object.
+
+    +row
+        +cell #[+api("token") #[code Token]]
+        +cell
+            |  An individual token — i.e. a word, punctuation symbol, whitespace,
+            |  etc.
+
+    +row
+        +cell #[+api("lexeme") #[code Lexeme]]
+        +cell
+            |  An entry in the vocabulary. It's a word type with no context, as
+            |  opposed to a word token. It therefore has no part-of-speech tag,
+            |  dependency parse etc.
+
+    +row
+        +cell #[+api("vocab") #[code Vocab]]
+        +cell
+            |  A lookup table for the vocabulary that allows you to access
+            |  #[code Lexeme] objects.
+
+    +row
+        +cell #[code Morphology]
+        +cell
+
+    +row
+        +cell #[+api("stringstore") #[code StringStore]]
+        +cell Map strings to and from integer IDs.
+
+    +row
+        +row
+        +cell #[+api("tokenizer") #[code Tokenizer]]
+        +cell
+            |  Segment text, and create #[code Doc] objects with the discovered
+            |  segment boundaries.
+
+    +row
+        +cell #[+api("tagger") #[code Tagger]]
+        +cell Annotate part-of-speech tags on #[code Doc] objects.
+
+    +row
+        +cell #[+api("dependencyparser") #[code DependencyParser]]
+        +cell Annotate syntactic dependencies on #[code Doc] objects.
+
+    +row
+        +cell #[+api("entityrecognizer") #[code EntityRecognizer]]
+        +cell
+            |  Annotate named entities, e.g. persons or products, on #[code Doc]
+            |  objects.
+
+    +row
+        +cell #[+api("matcher") #[code Matcher]]
+        +cell
+            |  Match sequences of tokens, based on pattern rules, similar to
+            |  regular expressions.
+
++h(3, "architecture-other") Other
+
++table(["Name", "Description"])
+    +row
+        +cell #[+api("goldparse") #[code GoldParse]]
+        +cell Collection for training annotations.
+
+    +row
+        +cell #[+api("goldcorpus") #[code GoldCorpus]]
+        +cell
+            |  An annotated corpus, using the JSON file format. Manages
+            |  annotations for tagging, dependency parsing and NER.