Fix get_matching_ents (#10451)

* Fix get_matching_ents

Not sure what happened here - the code prior to this commit simply does
not work. It's already covered by entity linker tests, which were
succeeding in the NEL PR, but couldn't possibly succeed on master.

* Fix test

Test was indented inside another test and so doesn't seem to have been
running properly.

spacy/tests/pipeline/test_entity_linker.py

@@ -1009,65 +1009,65 @@ def test_legacy_architectures(name, config):
         losses = {}
         nlp.update(train_examples, sgd=optimizer, losses=losses)
 
-    @pytest.mark.parametrize("patterns", [
+@pytest.mark.parametrize("patterns", [
-        # perfect case
+    # perfect case
-        [{"label": "CHARACTER", "pattern": "Kirby"}],
+    [{"label": "CHARACTER", "pattern": "Kirby"}],
-        # typo for false negative
+    # typo for false negative
-        [{"label": "PERSON", "pattern": "Korby"}],
+    [{"label": "PERSON", "pattern": "Korby"}],
-        # random stuff for false positive
+    # random stuff for false positive
-        [{"label": "IS", "pattern": "is"}, {"label": "COLOR", "pattern": "pink"}],
+    [{"label": "IS", "pattern": "is"}, {"label": "COLOR", "pattern": "pink"}],
-        ]
+    ]
-    )
+)
-    def test_no_gold_ents(patterns):
+def test_no_gold_ents(patterns):
-        # test that annotating components work
+    # test that annotating components work
-        TRAIN_DATA = [
+    TRAIN_DATA = [
-            (
+        (
-                "Kirby is pink",
+            "Kirby is pink",
-                {
+            {
-                    "links": {(0, 5): {"Q613241": 1.0}},
+                "links": {(0, 5): {"Q613241": 1.0}},
-                    "entities": [(0, 5, "CHARACTER")],
+                "entities": [(0, 5, "CHARACTER")],
-                    "sent_starts": [1, 0, 0],
+                "sent_starts": [1, 0, 0],
-                },
+            },
-            )
+        )
-        ]
+    ]
-        nlp = English()
+    nlp = English()
-        vector_length = 3
+    vector_length = 3
-        train_examples = []
+    train_examples = []
-        for text, annotation in TRAIN_DATA:
+    for text, annotation in TRAIN_DATA:
-            doc = nlp(text)
+        doc = nlp(text)
-            train_examples.append(Example.from_dict(doc, annotation))
+        train_examples.append(Example.from_dict(doc, annotation))
 
-        # Create a ruler to mark entities
+    # Create a ruler to mark entities
-        ruler = nlp.add_pipe("entity_ruler")
+    ruler = nlp.add_pipe("entity_ruler")
-        ruler.add_patterns(patterns)
+    ruler.add_patterns(patterns)
 
-        # Apply ruler to examples. In a real pipeline this would be an annotating component.
+    # Apply ruler to examples. In a real pipeline this would be an annotating component.
-        for eg in train_examples:
+    for eg in train_examples:
-            eg.predicted = ruler(eg.predicted)
+        eg.predicted = ruler(eg.predicted)
 
-        def create_kb(vocab):
+    def create_kb(vocab):
-            # create artificial KB
+        # create artificial KB
-            mykb = KnowledgeBase(vocab, entity_vector_length=vector_length)
+        mykb = KnowledgeBase(vocab, entity_vector_length=vector_length)
-            mykb.add_entity(entity="Q613241", freq=12, entity_vector=[6, -4, 3])
+        mykb.add_entity(entity="Q613241", freq=12, entity_vector=[6, -4, 3])
-            mykb.add_alias("Kirby", ["Q613241"], [0.9])
+        mykb.add_alias("Kirby", ["Q613241"], [0.9])
-            # Placeholder
+        # Placeholder
-            mykb.add_entity(entity="pink", freq=12, entity_vector=[7, 2, -5])
+        mykb.add_entity(entity="pink", freq=12, entity_vector=[7, 2, -5])
-            mykb.add_alias("pink", ["pink"], [0.9])
+        mykb.add_alias("pink", ["pink"], [0.9])
-            return mykb
+        return mykb
 
 
-        # Create and train the Entity Linker
+    # Create and train the Entity Linker
-        entity_linker = nlp.add_pipe("entity_linker", config={"use_gold_ents": False}, last=True)
+    entity_linker = nlp.add_pipe("entity_linker", config={"use_gold_ents": False}, last=True)
-        entity_linker.set_kb(create_kb)
+    entity_linker.set_kb(create_kb)
-        assert entity_linker.use_gold_ents == False
+    assert entity_linker.use_gold_ents == False
 
-        optimizer = nlp.initialize(get_examples=lambda: train_examples)
+    optimizer = nlp.initialize(get_examples=lambda: train_examples)
-        for i in range(2):
+    for i in range(2):
-            losses = {}
+        losses = {}
-            nlp.update(train_examples, sgd=optimizer, losses=losses)
+        nlp.update(train_examples, sgd=optimizer, losses=losses)
 
-        # adding additional components that are required for the entity_linker
+    # adding additional components that are required for the entity_linker
-        nlp.add_pipe("sentencizer", first=True)
+    nlp.add_pipe("sentencizer", first=True)
 
-        # this will run the pipeline on the examples and shouldn't crash
+    # this will run the pipeline on the examples and shouldn't crash
-        results = nlp.evaluate(train_examples)
+    results = nlp.evaluate(train_examples)

spacy/training/example.pyx

@@ -263,11 +263,11 @@ cdef class Example:
         kept. Otherwise only the character indices need to match.
         """
         gold = {}
-        for ent in self.reference:
+        for ent in self.reference.ents:
             gold[(ent.start_char, ent.end_char)] = ent.label
 
         keep = []
-        for ent in self.predicted:
+        for ent in self.predicted.ents:
             key = (ent.start_char, ent.end_char)
             if key not in gold:
                 continue