Merge pull request #1913 from ohenrik/nb_syntax_iterator

Norwegian Language (nb) - Added french syntax iterator with explanation

spacy/lang/nb/__init__.py

@@ -13,6 +13,12 @@ from ...language import Language
 from ...attrs import LANG, NORM
 from ...util import update_exc, add_lookups
 
+# Borrowing french syntax parser because both languages use
+# universal dependencies for tagging/parsing.
+# Read here for more:
+# https://github.com/explosion/spaCy/pull/1882#issuecomment-361409573
+from .syntax_iterators import SYNTAX_ITERATORS
+
 
 class NorwegianDefaults(Language.Defaults):
     lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
@@ -22,6 +28,7 @@ class NorwegianDefaults(Language.Defaults):
     stop_words = STOP_WORDS
     tag_map = TAG_MAP
     lemma_lookup = LOOKUP
+    syntax_iterators = SYNTAX_ITERATORS
 
 
 class Norwegian(Language):

spacy/lang/nb/syntax_iterators.py

@@ -0,0 +1,42 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+from ...symbols import NOUN, PROPN, PRON
+
+
+def noun_chunks(obj):
+    """
+    Detect base noun phrases from a dependency parse. Works on both Doc and Span.
+    """
+    labels = ['nsubj', 'nsubj:pass', 'obj', 'iobj', 'ROOT', 'appos', 'nmod', 'nmod:poss']
+    doc = obj.doc  # Ensure works on both Doc and Span.
+    np_deps = [doc.vocab.strings[label] for label in labels]
+    conj = doc.vocab.strings.add('conj')
+    np_label = doc.vocab.strings.add('NP')
+    seen = set()
+    for i, word in enumerate(obj):
+        if word.pos not in (NOUN, PROPN, PRON):
+            continue
+        # Prevent nested chunks from being produced
+        if word.i in seen:
+            continue
+        if word.dep in np_deps:
+            if any(w.i in seen for w in word.subtree):
+                continue
+            seen.update(j for j in range(word.left_edge.i, word.right_edge.i+1))
+            yield word.left_edge.i, word.right_edge.i+1, np_label
+        elif word.dep == conj:
+            head = word.head
+            while head.dep == conj and head.head.i < head.i:
+                head = head.head
+            # If the head is an NP, and we're coordinated to it, we're an NP
+            if head.dep in np_deps:
+                if any(w.i in seen for w in word.subtree):
+                    continue
+                seen.update(j for j in range(word.left_edge.i, word.right_edge.i+1))
+                yield word.left_edge.i, word.right_edge.i+1, np_label
+
+
+SYNTAX_ITERATORS = {
+    'noun_chunks': noun_chunks
+}