Update Russian and Ukrainian lemmatizers (#11811)

* pymorph2 issues #11620, #11626, #11625:
- #11620: pymorphy2_lookup
- #11626: handle multiple forms pointing to the same normal form + handling empty POS tag
- #11625: matching DET that are labelled as PRON by pymorhp2

* Move lemmatizer algorithm changes back into RussianLemmatizer

* Fix uk pymorphy3_lookup mode init

* Move and update tests for ru/uk lookup lemmatizer modes

* Fix typo

* Remove traces of previous behavior for uninflected POS

* Refactor to private generic-looking pymorphy methods

* Remove xfailed uk lemmatizer cases

* Update spacy/lang/ru/lemmatizer.py

Co-authored-by: Richard Hudson <richard@explosion.ai>

Co-authored-by: Dmytro S Lituiev <d.lituiev@gmail.com>
Co-authored-by: Richard Hudson <richard@explosion.ai>

spacy/lang/ru/lemmatizer.py

@@ -28,34 +28,39 @@ class RussianLemmatizer(Lemmatizer):
                 from pymorphy2 import MorphAnalyzer
             except ImportError:
                 raise ImportError(
-                    "The Russian lemmatizer mode 'pymorphy2' requires the "
-                    "pymorphy2 library. Install it with: pip install pymorphy2"
+                    "The lemmatizer mode 'pymorphy2' requires the "
+                    "pymorphy2 library and dictionaries. Install them with: "
+                    "pip install pymorphy2"
+                    "# for Ukrainian dictionaries:"
+                    "pip install pymorphy2-dicts-uk"
                 ) from None
             if getattr(self, "_morph", None) is None:
-                self._morph = MorphAnalyzer()
-        elif mode == "pymorphy3":
+                self._morph = MorphAnalyzer(lang="ru")
+        elif mode in {"pymorphy3", "pymorphy3_lookup"}:
             try:
                 from pymorphy3 import MorphAnalyzer
             except ImportError:
                 raise ImportError(
-                    "The Russian lemmatizer mode 'pymorphy3' requires the "
-                    "pymorphy3 library. Install it with: pip install pymorphy3"
+                    "The lemmatizer mode 'pymorphy3' requires the "
+                    "pymorphy3 library and dictionaries. Install them with: "
+                    "pip install pymorphy3"
+                    "# for Ukrainian dictionaries:"
+                    "pip install pymorphy3-dicts-uk"
                 ) from None
             if getattr(self, "_morph", None) is None:
-                self._morph = MorphAnalyzer()
+                self._morph = MorphAnalyzer(lang="ru")
         super().__init__(
             vocab, model, name, mode=mode, overwrite=overwrite, scorer=scorer
         )
 
-    def pymorphy2_lemmatize(self, token: Token) -> List[str]:
+    def _pymorphy_lemmatize(self, token: Token) -> List[str]:
         string = token.text
         univ_pos = token.pos_
         morphology = token.morph.to_dict()
         if univ_pos == "PUNCT":
             return [PUNCT_RULES.get(string, string)]
         if univ_pos not in ("ADJ", "DET", "NOUN", "NUM", "PRON", "PROPN", "VERB"):
-            # Skip unchangeable pos
-            return [string.lower()]
+            return self._pymorphy_lookup_lemmatize(token)
         analyses = self._morph.parse(string)
         filtered_analyses = []
         for analysis in analyses:
@@ -63,8 +68,10 @@ class RussianLemmatizer(Lemmatizer):
                 # Skip suggested parse variant for unknown word for pymorphy
                 continue
             analysis_pos, _ = oc2ud(str(analysis.tag))
-            if analysis_pos == univ_pos or (
-                analysis_pos in ("NOUN", "PROPN") and univ_pos in ("NOUN", "PROPN")
+            if (
+                analysis_pos == univ_pos
+                or (analysis_pos in ("NOUN", "PROPN") and univ_pos in ("NOUN", "PROPN"))
+                or ((analysis_pos == "PRON") and (univ_pos == "DET"))
             ):
                 filtered_analyses.append(analysis)
         if not len(filtered_analyses):
@@ -107,15 +114,27 @@ class RussianLemmatizer(Lemmatizer):
             dict.fromkeys([analysis.normal_form for analysis in filtered_analyses])
         )
 
-    def pymorphy2_lookup_lemmatize(self, token: Token) -> List[str]:
+    def _pymorphy_lookup_lemmatize(self, token: Token) -> List[str]:
         string = token.text
         analyses = self._morph.parse(string)
-        if len(analyses) == 1:
-            return [analyses[0].normal_form]
+        # often multiple forms would derive from the same normal form
+        # thus check _unique_ normal forms
+        normal_forms = set([an.normal_form for an in analyses])
+        if len(normal_forms) == 1:
+            return [next(iter(normal_forms))]
         return [string]
 
+    def pymorphy2_lemmatize(self, token: Token) -> List[str]:
+        return self._pymorphy_lemmatize(token)
+
+    def pymorphy2_lookup_lemmatize(self, token: Token) -> List[str]:
+        return self._pymorphy_lookup_lemmatize(token)
+
     def pymorphy3_lemmatize(self, token: Token) -> List[str]:
-        return self.pymorphy2_lemmatize(token)
+        return self._pymorphy_lemmatize(token)
+
+    def pymorphy3_lookup_lemmatize(self, token: Token) -> List[str]:
+        return self._pymorphy_lookup_lemmatize(token)
 
 
 def oc2ud(oc_tag: str) -> Tuple[str, Dict[str, str]]:

spacy/lang/uk/lemmatizer.py

@@ -29,7 +29,7 @@ class UkrainianLemmatizer(RussianLemmatizer):
                 ) from None
             if getattr(self, "_morph", None) is None:
                 self._morph = MorphAnalyzer(lang="uk")
-        elif mode == "pymorphy3":
+        elif mode in {"pymorphy3", "pymorphy3_lookup"}:
             try:
                 from pymorphy3 import MorphAnalyzer
             except ImportError:

spacy/tests/conftest.py

@@ -337,17 +337,17 @@ def ru_tokenizer():
     return get_lang_class("ru")().tokenizer
 
 
-@pytest.fixture
+@pytest.fixture(scope="session")
 def ru_lemmatizer():
     pytest.importorskip("pymorphy3")
     return get_lang_class("ru")().add_pipe("lemmatizer")
 
 
-@pytest.fixture
+@pytest.fixture(scope="session")
 def ru_lookup_lemmatizer():
-    pytest.importorskip("pymorphy2")
+    pytest.importorskip("pymorphy3")
     return get_lang_class("ru")().add_pipe(
-        "lemmatizer", config={"mode": "pymorphy2_lookup"}
+        "lemmatizer", config={"mode": "pymorphy3_lookup"}
     )
 
 
@@ -423,19 +423,19 @@ def uk_tokenizer():
     return get_lang_class("uk")().tokenizer
 
 
-@pytest.fixture
+@pytest.fixture(scope="session")
 def uk_lemmatizer():
     pytest.importorskip("pymorphy3")
     pytest.importorskip("pymorphy3_dicts_uk")
     return get_lang_class("uk")().add_pipe("lemmatizer")
 
 
-@pytest.fixture
+@pytest.fixture(scope="session")
 def uk_lookup_lemmatizer():
-    pytest.importorskip("pymorphy2")
-    pytest.importorskip("pymorphy2_dicts_uk")
+    pytest.importorskip("pymorphy3")
+    pytest.importorskip("pymorphy3_dicts_uk")
     return get_lang_class("uk")().add_pipe(
-        "lemmatizer", config={"mode": "pymorphy2_lookup"}
+        "lemmatizer", config={"mode": "pymorphy3_lookup"}
     )
 
 

spacy/tests/lang/ru/test_lemmatizer.py

@@ -81,6 +81,7 @@ def test_ru_lemmatizer_punct(ru_lemmatizer):
 
 
 def test_ru_doc_lookup_lemmatization(ru_lookup_lemmatizer):
+    assert ru_lookup_lemmatizer.mode == "pymorphy3_lookup"
     words = ["мама", "мыла", "раму"]
     pos = ["NOUN", "VERB", "NOUN"]
     morphs = [
@@ -92,3 +93,17 @@ def test_ru_doc_lookup_lemmatization(ru_lookup_lemmatizer):
     doc = ru_lookup_lemmatizer(doc)
     lemmas = [token.lemma_ for token in doc]
     assert lemmas == ["мама", "мыла", "раму"]
+
+
+@pytest.mark.parametrize(
+    "word,lemma",
+    (
+        ("бременем", "бремя"),
+        ("будешь", "быть"),
+        ("какая-то", "какой-то"),
+    ),
+)
+def test_ru_lookup_lemmatizer(ru_lookup_lemmatizer, word, lemma):
+    assert ru_lookup_lemmatizer.mode == "pymorphy3_lookup"
+    doc = Doc(ru_lookup_lemmatizer.vocab, words=[word])
+    assert ru_lookup_lemmatizer(doc)[0].lemma_ == lemma

spacy/tests/lang/uk/test_lemmatizer.py

@@ -8,12 +8,20 @@ pytestmark = pytest.mark.filterwarnings("ignore::DeprecationWarning")
 def test_uk_lemmatizer(uk_lemmatizer):
     """Check that the default uk lemmatizer runs."""
     doc = Doc(uk_lemmatizer.vocab, words=["a", "b", "c"])
+    assert uk_lemmatizer.mode == "pymorphy3"
     uk_lemmatizer(doc)
     assert [token.lemma for token in doc]
 
 
-def test_uk_lookup_lemmatizer(uk_lookup_lemmatizer):
-    """Check that the lookup uk lemmatizer runs."""
-    doc = Doc(uk_lookup_lemmatizer.vocab, words=["a", "b", "c"])
-    uk_lookup_lemmatizer(doc)
-    assert [token.lemma for token in doc]
+@pytest.mark.parametrize(
+    "word,lemma",
+    (
+        ("якийсь", "якийсь"),
+        ("розповідають", "розповідати"),
+        ("розповіси", "розповісти"),
+    ),
+)
+def test_uk_lookup_lemmatizer(uk_lookup_lemmatizer, word, lemma):
+    assert uk_lookup_lemmatizer.mode == "pymorphy3_lookup"
+    doc = Doc(uk_lookup_lemmatizer.vocab, words=[word])
+    assert uk_lookup_lemmatizer(doc)[0].lemma_ == lemma