Merge remote-tracking branch 'origin/fix/types' into fix/types

.github/FUNDING.yml

@@ -0,0 +1 @@
+custom: https://explosion.ai/merch

README.md

@@ -46,6 +46,7 @@ open-source software, released under the
 | 📺 **[Videos]**                                                                                                                                                                                                           | Our YouTube channel with video tutorials, talks and more.                                                                                                                                                                                                                                                                                    |
 | 🛠 **[Changelog]**                                                                                                                                                                                                         | Changes and version history.                                                                                                                                                                                                                                                                                                                 |
 | 💝 **[Contribute]**                                                                                                                                                                                                       | How to contribute to the spaCy project and code base.                                                                                                                                                                                                                                                                                        |
+| 👕 **[Swag]**                                                                                                                                                                                                             | Support us and our work with unique, custom-designed swag!                                                                                                                                                                                                                                                                                   |
 | <a href="https://explosion.ai/spacy-tailored-pipelines"><img src="https://user-images.githubusercontent.com/13643239/152853098-1c761611-ccb0-4ec6-9066-b234552831fe.png" width="125" alt="spaCy Tailored Pipelines"/></a> | Get a custom spaCy pipeline, tailor-made for your NLP problem by spaCy's core developers. Streamlined, production-ready, predictable and maintainable. Start by completing our 5-minute questionnaire to tell us what you need and we'll be in touch! **[Learn more &rarr;](https://explosion.ai/spacy-tailored-pipelines)**                 |
 | <a href="https://explosion.ai/spacy-tailored-analysis"><img src="https://user-images.githubusercontent.com/1019791/206151300-b00cd189-e503-4797-aa1e-1bb6344062c5.png" width="125" alt="spaCy Tailored Pipelines"/></a>   | Bespoke advice for problem solving, strategy and analysis for applied NLP projects. Services include data strategy, code reviews, pipeline design and annotation coaching. Curious? Fill in our 5-minute questionnaire to tell us what you need and we'll be in touch! **[Learn more &rarr;](https://explosion.ai/spacy-tailored-analysis)** |
 
@@ -61,6 +62,7 @@ open-source software, released under the
 [project templates]: https://github.com/explosion/projects
 [changelog]: https://spacy.io/usage#changelog
 [contribute]: https://github.com/explosion/spaCy/blob/master/CONTRIBUTING.md
+[swag]: https://explosion.ai/merch
 
 ## 💬 Where to ask questions
 

spacy/cli/templates/quickstart_training.jinja

@@ -271,8 +271,9 @@ grad_factor = 1.0
 @layers = "reduce_mean.v1"
 
 [components.textcat.model.linear_model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatBOW.v3"
 exclusive_classes = true
+length = 262144
 ngram_size = 1
 no_output_layer = false
 
@@ -308,8 +309,9 @@ grad_factor = 1.0
 @layers = "reduce_mean.v1"
 
 [components.textcat_multilabel.model.linear_model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatBOW.v3"
 exclusive_classes = false
+length = 262144
 ngram_size = 1
 no_output_layer = false
 
@@ -542,14 +544,15 @@ nO = null
 width = ${components.tok2vec.model.encode.width}
 
 [components.textcat.model.linear_model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatBOW.v3"
 exclusive_classes = true
+length = 262144
 ngram_size = 1
 no_output_layer = false
 
 {% else -%}
 [components.textcat.model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatBOW.v3"
 exclusive_classes = true
 ngram_size = 1
 no_output_layer = false
@@ -570,15 +573,17 @@ nO = null
 width = ${components.tok2vec.model.encode.width}
 
 [components.textcat_multilabel.model.linear_model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatBOW.v3"
 exclusive_classes = false
+length = 262144
 ngram_size = 1
 no_output_layer = false
 
 {% else -%}
 [components.textcat_multilabel.model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatBOW.v3"
 exclusive_classes = false
+length = 262144
 ngram_size = 1
 no_output_layer = false
 {%- endif %}

spacy/errors.py

@@ -983,6 +983,7 @@ class Errors(metaclass=ErrorsWithCodes):
              "predicted docs when training {component}.")
     E1055 = ("The 'replace_listener' callback expects {num_params} parameters, "
              "but only callbacks with one or three parameters are supported")
+    E1056 = ("The `TextCatBOW` architecture expects a length of at least 1, was {length}.")
 
 
 # Deprecated model shortcuts, only used in errors and warnings

spacy/lang/fo/__init__.py

@@ -0,0 +1,18 @@
+from ...language import BaseDefaults, Language
+from ..punctuation import TOKENIZER_INFIXES, TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES
+from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
+
+
+class FaroeseDefaults(BaseDefaults):
+    tokenizer_exceptions = TOKENIZER_EXCEPTIONS
+    infixes = TOKENIZER_INFIXES
+    suffixes = TOKENIZER_SUFFIXES
+    prefixes = TOKENIZER_PREFIXES
+
+
+class Faroese(Language):
+    lang = "fo"
+    Defaults = FaroeseDefaults
+
+
+__all__ = ["Faroese"]

spacy/lang/fo/tokenizer_exceptions.py

@@ -0,0 +1,90 @@
+from ...symbols import ORTH
+from ...util import update_exc
+from ..tokenizer_exceptions import BASE_EXCEPTIONS
+
+_exc = {}
+
+for orth in [
+    "apr.",
+    "aug.",
+    "avgr.",
+    "árg.",
+    "ávís.",
+    "beinl.",
+    "blkv.",
+    "blaðkv.",
+    "blm.",
+    "blaðm.",
+    "bls.",
+    "blstj.",
+    "blaðstj.",
+    "des.",
+    "eint.",
+    "febr.",
+    "fyrrv.",
+    "góðk.",
+    "h.m.",
+    "innt.",
+    "jan.",
+    "kl.",
+    "m.a.",
+    "mðr.",
+    "mió.",
+    "nr.",
+    "nto.",
+    "nov.",
+    "nút.",
+    "o.a.",
+    "o.a.m.",
+    "o.a.tíl.",
+    "o.fl.",
+    "ff.",
+    "o.m.a.",
+    "o.o.",
+    "o.s.fr.",
+    "o.tíl.",
+    "o.ø.",
+    "okt.",
+    "omf.",
+    "pst.",
+    "ritstj.",
+    "sbr.",
+    "sms.",
+    "smst.",
+    "smb.",
+    "sb.",
+    "sbrt.",
+    "sp.",
+    "sept.",
+    "spf.",
+    "spsk.",
+    "t.e.",
+    "t.s.",
+    "t.s.s.",
+    "tlf.",
+    "tel.",
+    "tsk.",
+    "t.o.v.",
+    "t.d.",
+    "uml.",
+    "ums.",
+    "uppl.",
+    "upprfr.",
+    "uppr.",
+    "útg.",
+    "útl.",
+    "útr.",
+    "vanl.",
+    "v.",
+    "v.h.",
+    "v.ø.o.",
+    "viðm.",
+    "viðv.",
+    "vm.",
+    "v.m.",
+]:
+    _exc[orth] = [{ORTH: orth}]
+    capitalized = orth.capitalize()
+    _exc[capitalized] = [{ORTH: capitalized}]
+
+TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)

spacy/lang/nn/__init__.py

@@ -0,0 +1,20 @@
+from ...language import BaseDefaults, Language
+from ..nb import SYNTAX_ITERATORS
+from .punctuation import TOKENIZER_INFIXES, TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES
+from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
+
+
+class NorwegianNynorskDefaults(BaseDefaults):
+    tokenizer_exceptions = TOKENIZER_EXCEPTIONS
+    prefixes = TOKENIZER_PREFIXES
+    infixes = TOKENIZER_INFIXES
+    suffixes = TOKENIZER_SUFFIXES
+    syntax_iterators = SYNTAX_ITERATORS
+
+
+class NorwegianNynorsk(Language):
+    lang = "nn"
+    Defaults = NorwegianNynorskDefaults
+
+
+__all__ = ["NorwegianNynorsk"]

spacy/lang/nn/examples.py

@@ -0,0 +1,15 @@
+"""
+Example sentences to test spaCy and its language models.
+
+>>> from spacy.lang.nn.examples import sentences
+>>> docs = nlp.pipe(sentences)
+"""
+
+
+# sentences taken from Omsetjingsminne frå Nynorsk pressekontor 2022 (https://www.nb.no/sprakbanken/en/resource-catalogue/oai-nb-no-sbr-80/)
+sentences = [
+    "Konseptet går ut på at alle tre omgangar tel, alle hopparar må stille i kvalifiseringa og poengsummen skal telje.",
+    "Det er ein meir enn i same periode i fjor.",
+    "Det har lava ned enorme snømengder i store delar av Europa den siste tida.",
+    "Akhtar Chaudhry er ikkje innstilt på Oslo-lista til SV, men utfordrar Heikki Holmås om førsteplassen.",
+]

spacy/lang/nn/punctuation.py

@@ -0,0 +1,74 @@
+from ..char_classes import (
+    ALPHA,
+    ALPHA_LOWER,
+    ALPHA_UPPER,
+    CONCAT_QUOTES,
+    CURRENCY,
+    LIST_CURRENCY,
+    LIST_ELLIPSES,
+    LIST_ICONS,
+    LIST_PUNCT,
+    LIST_QUOTES,
+    PUNCT,
+    UNITS,
+)
+from ..punctuation import TOKENIZER_SUFFIXES
+
+_quotes = CONCAT_QUOTES.replace("'", "")
+_list_punct = [x for x in LIST_PUNCT if x != "#"]
+_list_icons = [x for x in LIST_ICONS if x != "°"]
+_list_icons = [x.replace("\\u00B0", "") for x in _list_icons]
+_list_quotes = [x for x in LIST_QUOTES if x != "\\'"]
+
+
+_prefixes = (
+    ["§", "%", "=", "—", "–", r"\+(?![0-9])"]
+    + _list_punct
+    + LIST_ELLIPSES
+    + LIST_QUOTES
+    + LIST_CURRENCY
+    + LIST_ICONS
+)
+
+
+_infixes = (
+    LIST_ELLIPSES
+    + _list_icons
+    + [
+        r"(?<=[{al}])\.(?=[{au}])".format(al=ALPHA_LOWER, au=ALPHA_UPPER),
+        r"(?<=[{a}])[,!?](?=[{a}])".format(a=ALPHA),
+        r"(?<=[{a}])[:<>=/](?=[{a}])".format(a=ALPHA),
+        r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
+        r"(?<=[{a}])([{q}\)\]\(\[])(?=[{a}])".format(a=ALPHA, q=_quotes),
+        r"(?<=[{a}])--(?=[{a}])".format(a=ALPHA),
+    ]
+)
+
+_suffixes = (
+    LIST_PUNCT
+    + LIST_ELLIPSES
+    + _list_quotes
+    + _list_icons
+    + ["—", "–"]
+    + [
+        r"(?<=[0-9])\+",
+        r"(?<=°[FfCcKk])\.",
+        r"(?<=[0-9])(?:{c})".format(c=CURRENCY),
+        r"(?<=[0-9])(?:{u})".format(u=UNITS),
+        r"(?<=[{al}{e}{p}(?:{q})])\.".format(
+            al=ALPHA_LOWER, e=r"%²\-\+", q=_quotes, p=PUNCT
+        ),
+        r"(?<=[{au}][{au}])\.".format(au=ALPHA_UPPER),
+    ]
+    + [r"(?<=[^sSxXzZ])'"]
+)
+_suffixes += [
+    suffix
+    for suffix in TOKENIZER_SUFFIXES
+    if suffix not in ["'s", "'S", "’s", "’S", r"\'"]
+]
+
+
+TOKENIZER_PREFIXES = _prefixes
+TOKENIZER_INFIXES = _infixes
+TOKENIZER_SUFFIXES = _suffixes

spacy/lang/nn/tokenizer_exceptions.py

@@ -0,0 +1,228 @@
+from ...symbols import NORM, ORTH
+from ...util import update_exc
+from ..tokenizer_exceptions import BASE_EXCEPTIONS
+
+_exc = {}
+
+
+for exc_data in [
+    {ORTH: "jan.", NORM: "januar"},
+    {ORTH: "feb.", NORM: "februar"},
+    {ORTH: "mar.", NORM: "mars"},
+    {ORTH: "apr.", NORM: "april"},
+    {ORTH: "jun.", NORM: "juni"},
+    # note: "jul." is in the simple list below without a NORM exception
+    {ORTH: "aug.", NORM: "august"},
+    {ORTH: "sep.", NORM: "september"},
+    {ORTH: "okt.", NORM: "oktober"},
+    {ORTH: "nov.", NORM: "november"},
+    {ORTH: "des.", NORM: "desember"},
+]:
+    _exc[exc_data[ORTH]] = [exc_data]
+
+
+for orth in [
+    "Ap.",
+    "Aq.",
+    "Ca.",
+    "Chr.",
+    "Co.",
+    "Dr.",
+    "F.eks.",
+    "Fr.p.",
+    "Frp.",
+    "Grl.",
+    "Kr.",
+    "Kr.F.",
+    "Kr.F.s",
+    "Mr.",
+    "Mrs.",
+    "Pb.",
+    "Pr.",
+    "Sp.",
+    "St.",
+    "a.m.",
+    "ad.",
+    "adm.dir.",
+    "adr.",
+    "b.c.",
+    "bl.a.",
+    "bla.",
+    "bm.",
+    "bnr.",
+    "bto.",
+    "c.c.",
+    "ca.",
+    "cand.mag.",
+    "co.",
+    "d.d.",
+    "d.m.",
+    "d.y.",
+    "dept.",
+    "dr.",
+    "dr.med.",
+    "dr.philos.",
+    "dr.psychol.",
+    "dss.",
+    "dvs.",
+    "e.Kr.",
+    "e.l.",
+    "eg.",
+    "eig.",
+    "ekskl.",
+    "el.",
+    "et.",
+    "etc.",
+    "etg.",
+    "ev.",
+    "evt.",
+    "f.",
+    "f.Kr.",
+    "f.eks.",
+    "f.o.m.",
+    "fhv.",
+    "fk.",
+    "foreg.",
+    "fork.",
+    "fv.",
+    "fvt.",
+    "g.",
+    "gl.",
+    "gno.",
+    "gnr.",
+    "grl.",
+    "gt.",
+    "h.r.adv.",
+    "hhv.",
+    "hoh.",
+    "hr.",
+    "ifb.",
+    "ifm.",
+    "iht.",
+    "inkl.",
+    "istf.",
+    "jf.",
+    "jr.",
+    "jul.",
+    "juris.",
+    "kfr.",
+    "kgl.",
+    "kgl.res.",
+    "kl.",
+    "komm.",
+    "kr.",
+    "kst.",
+    "lat.",
+    "lø.",
+    "m.a.",
+    "m.a.o.",
+    "m.fl.",
+    "m.m.",
+    "m.v.",
+    "ma.",
+    "mag.art.",
+    "md.",
+    "mfl.",
+    "mht.",
+    "mill.",
+    "min.",
+    "mnd.",
+    "moh.",
+    "mrd.",
+    "muh.",
+    "mv.",
+    "mva.",
+    "n.å.",
+    "ndf.",
+    "nr.",
+    "nto.",
+    "nyno.",
+    "o.a.",
+    "o.l.",
+    "obl.",
+    "off.",
+    "ofl.",
+    "on.",
+    "op.",
+    "org.",
+    "osv.",
+    "ovf.",
+    "p.",
+    "p.a.",
+    "p.g.a.",
+    "p.m.",
+    "p.t.",
+    "pga.",
+    "ph.d.",
+    "pkt.",
+    "pr.",
+    "pst.",
+    "pt.",
+    "red.anm.",
+    "ref.",
+    "res.",
+    "res.kap.",
+    "resp.",
+    "rv.",
+    "s.",
+    "s.d.",
+    "s.k.",
+    "s.u.",
+    "s.å.",
+    "sen.",
+    "sep.",
+    "siviling.",
+    "sms.",
+    "snr.",
+    "spm.",
+    "sr.",
+    "sst.",
+    "st.",
+    "st.meld.",
+    "st.prp.",
+    "stip.",
+    "stk.",
+    "stud.",
+    "sv.",
+    "såk.",
+    "sø.",
+    "t.d.",
+    "t.h.",
+    "t.o.m.",
+    "t.v.",
+    "temp.",
+    "ti.",
+    "tils.",
+    "tilsv.",
+    "tl;dr",
+    "tlf.",
+    "to.",
+    "ult.",
+    "utg.",
+    "v.",
+    "vedk.",
+    "vedr.",
+    "vg.",
+    "vgs.",
+    "vha.",
+    "vit.ass.",
+    "vn.",
+    "vol.",
+    "vs.",
+    "vsa.",
+    "§§",
+    "©NTB",
+    "årg.",
+    "årh.",
+]:
+    _exc[orth] = [{ORTH: orth}]
+
+# Dates
+for h in range(1, 31 + 1):
+    for period in ["."]:
+        _exc[f"{h}{period}"] = [{ORTH: f"{h}."}]
+
+_custom_base_exc = {"i.": [{ORTH: "i", NORM: "i"}, {ORTH: "."}]}
+_exc.update(_custom_base_exc)
+
+TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)

spacy/ml/models/textcat.py

@@ -1,5 +1,5 @@
 from functools import partial
-from typing import List, Optional, cast
+from typing import List, Optional, Tuple, cast
 
 from thinc.api import (
     Dropout,
@@ -12,6 +12,7 @@ from thinc.api import (
     Relu,
     Softmax,
     SparseLinear,
+    SparseLinear_v2,
     chain,
     clone,
     concatenate,
@@ -25,9 +26,10 @@ from thinc.api import (
 )
 from thinc.layers.chain import init as init_chain
 from thinc.layers.resizable import resize_linear_weighted, resize_model
-from thinc.types import Floats2d
+from thinc.types import ArrayXd, Floats2d
 
 from ...attrs import ORTH
+from ...errors import Errors
 from ...tokens import Doc
 from ...util import registry
 from ..extract_ngrams import extract_ngrams
@@ -95,10 +97,48 @@ def build_bow_text_classifier(
     ngram_size: int,
     no_output_layer: bool,
     nO: Optional[int] = None,
+) -> Model[List[Doc], Floats2d]:
+    return _build_bow_text_classifier(
+        exclusive_classes=exclusive_classes,
+        ngram_size=ngram_size,
+        no_output_layer=no_output_layer,
+        nO=nO,
+        sparse_linear=SparseLinear(nO=nO),
+    )
+
+
+@registry.architectures("spacy.TextCatBOW.v3")
+def build_bow_text_classifier_v3(
+    exclusive_classes: bool,
+    ngram_size: int,
+    no_output_layer: bool,
+    length: int = 262144,
+    nO: Optional[int] = None,
+) -> Model[List[Doc], Floats2d]:
+    if length < 1:
+        raise ValueError(Errors.E1056.format(length=length))
+
+    # Find k such that 2**(k-1) < length <= 2**k.
+    length = 2 ** (length - 1).bit_length()
+
+    return _build_bow_text_classifier(
+        exclusive_classes=exclusive_classes,
+        ngram_size=ngram_size,
+        no_output_layer=no_output_layer,
+        nO=nO,
+        sparse_linear=SparseLinear_v2(nO=nO, length=length),
+    )
+
+
+def _build_bow_text_classifier(
+    exclusive_classes: bool,
+    ngram_size: int,
+    no_output_layer: bool,
+    sparse_linear: Model[Tuple[ArrayXd, ArrayXd, ArrayXd], ArrayXd],
+    nO: Optional[int] = None,
 ) -> Model[List[Doc], Floats2d]:
     fill_defaults = {"b": 0, "W": 0}
     with Model.define_operators({">>": chain}):
-        sparse_linear = SparseLinear(nO=nO)
         output_layer = None
         if not no_output_layer:
             fill_defaults["b"] = NEG_VALUE

spacy/pipeline/textcat.py

@@ -36,8 +36,9 @@ maxout_pieces = 3
 depth = 2
 
 [model.linear_model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatBOW.v3"
 exclusive_classes = true
+length = 262144
 ngram_size = 1
 no_output_layer = false
 """
@@ -45,8 +46,9 @@ DEFAULT_SINGLE_TEXTCAT_MODEL = Config().from_str(single_label_default_config)["m
 
 single_label_bow_config = """
 [model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatBOW.v3"
 exclusive_classes = true
+length = 262144
 ngram_size = 1
 no_output_layer = false
 """

spacy/pipeline/textcat_multilabel.py

@@ -35,8 +35,9 @@ maxout_pieces = 3
 depth = 2
 
 [model.linear_model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatBOW.v3"
 exclusive_classes = false
+length = 262144
 ngram_size = 1
 no_output_layer = false
 """
@@ -44,7 +45,7 @@ DEFAULT_MULTI_TEXTCAT_MODEL = Config().from_str(multi_label_default_config)["mod
 
 multi_label_bow_config = """
 [model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatBOW.v3"
 exclusive_classes = false
 ngram_size = 1
 no_output_layer = false

spacy/tests/conftest.py

@@ -162,6 +162,11 @@ def fi_tokenizer():
     return get_lang_class("fi")().tokenizer
 
 
+@pytest.fixture(scope="session")
+def fo_tokenizer():
+    return get_lang_class("fo")().tokenizer
+
+
 @pytest.fixture(scope="session")
 def fr_tokenizer():
     return get_lang_class("fr")().tokenizer
@@ -317,6 +322,11 @@ def nl_tokenizer():
     return get_lang_class("nl")().tokenizer
 
 
+@pytest.fixture(scope="session")
+def nn_tokenizer():
+    return get_lang_class("nn")().tokenizer
+
+
 @pytest.fixture(scope="session")
 def pl_tokenizer():
     return get_lang_class("pl")().tokenizer

spacy/tests/lang/fo/test_tokenizer.py

@@ -0,0 +1,26 @@
+import pytest
+
+# examples taken from Basic LAnguage Resource Kit 1.0 for Faroese (https://maltokni.fo/en/resources) licensed with CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)
+# fmt: off
+FO_TOKEN_EXCEPTION_TESTS = [
+    (
+        "Eftir løgtingslóg um samsýning og eftirløn landsstýrismanna v.m., skulu løgmaður og landsstýrismenn vanliga siga frá sær størv í almennari tænastu ella privatum virkjum, samtøkum ella stovnum. ",
+        [
+            "Eftir", "løgtingslóg", "um", "samsýning", "og", "eftirløn", "landsstýrismanna", "v.m.", ",", "skulu", "løgmaður", "og", "landsstýrismenn", "vanliga", "siga", "frá", "sær", "størv", "í", "almennari", "tænastu", "ella", "privatum", "virkjum", ",", "samtøkum", "ella", "stovnum", ".",
+        ],
+    ),
+    (
+        "Sambandsflokkurin gongur aftur við 2,7 prosentum í mun til valið í 1994, tá flokkurin fekk undirtøku frá 23,4 prosent av veljarunum.",
+        [
+            "Sambandsflokkurin", "gongur", "aftur", "við", "2,7", "prosentum", "í", "mun", "til", "valið", "í", "1994", ",", "tá", "flokkurin", "fekk", "undirtøku", "frá", "23,4", "prosent", "av", "veljarunum", ".",
+        ],
+    ),
+]
+# fmt: on
+
+
+@pytest.mark.parametrize("text,expected_tokens", FO_TOKEN_EXCEPTION_TESTS)
+def test_fo_tokenizer_handles_exception_cases(fo_tokenizer, text, expected_tokens):
+    tokens = fo_tokenizer(text)
+    token_list = [token.text for token in tokens if not token.is_space]
+    assert expected_tokens == token_list

spacy/tests/lang/nn/test_tokenizer.py

@@ -0,0 +1,38 @@
+import pytest
+
+# examples taken from Omsetjingsminne frå Nynorsk pressekontor 2022 (https://www.nb.no/sprakbanken/en/resource-catalogue/oai-nb-no-sbr-80/)
+# fmt: off
+NN_TOKEN_EXCEPTION_TESTS = [
+    (
+        "Målet til direktoratet er at alle skal bli tilbydd jobb i politiet så raskt som mogleg i 2014.",
+        [
+            "Målet", "til", "direktoratet", "er", "at", "alle", "skal", "bli", "tilbydd", "jobb", "i", "politiet", "så", "raskt", "som", "mogleg", "i", "2014", ".",
+        ],
+    ),
+    (
+        "Han ønskjer ikkje at staten skal vere med på å finansiere slik undervisning, men dette er rektor på skulen ueinig i.",
+        [
+            "Han", "ønskjer", "ikkje", "at", "staten", "skal", "vere", "med", "på", "å", "finansiere", "slik", "undervisning", ",", "men", "dette", "er", "rektor", "på", "skulen", "ueinig", "i", ".",
+        ],
+    ),
+    (
+        "Ifølgje China Daily vart det 8.848 meter høge fjellet flytta 3 centimeter sørvestover under jordskjelvet, som vart målt til 7,8.",
+        [
+            "Ifølgje", "China", "Daily", "vart", "det", "8.848", "meter", "høge", "fjellet", "flytta", "3", "centimeter", "sørvestover", "under", "jordskjelvet", ",", "som", "vart", "målt", "til", "7,8", ".",
+        ],
+    ),
+    (
+        "Brukssesongen er frå nov. til mai, med ein topp i mars.",
+        [
+            "Brukssesongen", "er", "frå", "nov.", "til", "mai", ",", "med", "ein", "topp", "i", "mars", ".",
+        ],
+    ),
+]
+# fmt: on
+
+
+@pytest.mark.parametrize("text,expected_tokens", NN_TOKEN_EXCEPTION_TESTS)
+def test_nn_tokenizer_handles_exception_cases(nn_tokenizer, text, expected_tokens):
+    tokens = nn_tokenizer(text)
+    token_list = [token.text for token in tokens if not token.is_space]
+    assert expected_tokens == token_list

spacy/tests/pipeline/test_pipe_factories.py

@@ -203,7 +203,7 @@ def test_pipe_class_component_model():
             "@architectures": "spacy.TextCatEnsemble.v2",
             "tok2vec": DEFAULT_TOK2VEC_MODEL,
             "linear_model": {
-                "@architectures": "spacy.TextCatBOW.v2",
+                "@architectures": "spacy.TextCatBOW.v3",
                 "exclusive_classes": False,
                 "ngram_size": 1,
                 "no_output_layer": False,

spacy/tests/pipeline/test_textcat.py

@@ -414,7 +414,7 @@ def test_implicit_label(name, get_examples):
 @pytest.mark.parametrize(
     "name,textcat_config",
     [
-        # BOW
+        # BOW V1
         ("textcat", {"@architectures": "spacy.TextCatBOW.v1", "exclusive_classes": True, "no_output_layer": False, "ngram_size": 3}),
         ("textcat", {"@architectures": "spacy.TextCatBOW.v1", "exclusive_classes": True, "no_output_layer": True, "ngram_size": 3}),
         ("textcat_multilabel", {"@architectures": "spacy.TextCatBOW.v1", "exclusive_classes": False, "no_output_layer": False, "ngram_size": 3}),
@@ -451,11 +451,11 @@ def test_no_resize(name, textcat_config):
 @pytest.mark.parametrize(
     "name,textcat_config",
     [
-        # BOW
+        # BOW V3
-        ("textcat", {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": True, "no_output_layer": False, "ngram_size": 3}),
+        ("textcat", {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": True, "no_output_layer": False, "ngram_size": 3}),
-        ("textcat", {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": True, "no_output_layer": True, "ngram_size": 3}),
+        ("textcat", {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": True, "no_output_layer": True, "ngram_size": 3}),
-        ("textcat_multilabel", {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": False, "no_output_layer": False, "ngram_size": 3}),
+        ("textcat_multilabel", {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": False, "no_output_layer": False, "ngram_size": 3}),
-        ("textcat_multilabel", {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": False, "no_output_layer": True, "ngram_size": 3}),
+        ("textcat_multilabel", {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": False, "no_output_layer": True, "ngram_size": 3}),
         # CNN
         ("textcat", {"@architectures": "spacy.TextCatCNN.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": True}),
         ("textcat_multilabel", {"@architectures": "spacy.TextCatCNN.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": False}),
@@ -480,11 +480,11 @@ def test_resize(name, textcat_config):
 @pytest.mark.parametrize(
     "name,textcat_config",
     [
-        # BOW
+        # BOW v3
-        ("textcat", {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": True, "no_output_layer": False, "ngram_size": 3}),
+        ("textcat", {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": True, "no_output_layer": False, "ngram_size": 3}),
-        ("textcat", {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": True, "no_output_layer": True, "ngram_size": 3}),
+        ("textcat", {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": True, "no_output_layer": True, "ngram_size": 3}),
-        ("textcat_multilabel", {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": False, "no_output_layer": False, "ngram_size": 3}),
+        ("textcat_multilabel", {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": False, "no_output_layer": False, "ngram_size": 3}),
-        ("textcat_multilabel", {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": False, "no_output_layer": True, "ngram_size": 3}),
+        ("textcat_multilabel", {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": False, "no_output_layer": True, "ngram_size": 3}),
         # CNN
         ("textcat", {"@architectures": "spacy.TextCatCNN.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": True}),
         ("textcat_multilabel", {"@architectures": "spacy.TextCatCNN.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": False}),
@@ -693,9 +693,14 @@ def test_overfitting_IO_multi():
         ("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": True, "ngram_size": 4, "no_output_layer": False}),
         ("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": False, "ngram_size": 3, "no_output_layer": True}),
         ("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": True, "ngram_size": 2, "no_output_layer": True}),
+        # BOW V3
+        ("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": False, "ngram_size": 1, "no_output_layer": False}),
+        ("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": True, "ngram_size": 4, "no_output_layer": False}),
+        ("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": False, "ngram_size": 3, "no_output_layer": True}),
+        ("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": True, "ngram_size": 2, "no_output_layer": True}),
         # ENSEMBLE V2
-        ("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatEnsemble.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "linear_model": {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": False, "ngram_size": 1, "no_output_layer": False}}),
+        ("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatEnsemble.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "linear_model": {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": False, "ngram_size": 1, "no_output_layer": False}}),
-        ("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatEnsemble.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "linear_model": {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": True, "ngram_size": 5, "no_output_layer": False}}),
+        ("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatEnsemble.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "linear_model": {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": True, "ngram_size": 5, "no_output_layer": False}}),
         # CNN V2
         ("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatCNN.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": True}),
         ("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatCNN.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": False}),

spacy/tests/test_cli_app.py

@@ -238,7 +238,7 @@ def test_project_push_pull(project_dir):
 
 def test_find_function_valid():
     # example of architecture in main code base
-    function = "spacy.TextCatBOW.v2"
+    function = "spacy.TextCatBOW.v3"
     result = CliRunner().invoke(app, ["find-function", function, "-r", "architectures"])
     assert f"Found registered function '{function}'" in result.stdout
     assert "textcat.py" in result.stdout
@@ -257,7 +257,7 @@ def test_find_function_valid():
 
 def test_find_function_invalid():
     # invalid registry
-    function = "spacy.TextCatBOW.v2"
+    function = "spacy.TextCatBOW.v3"
     registry = "foobar"
     result = CliRunner().invoke(
         app, ["find-function", function, "--registry", registry]

spacy/tests/test_misc.py

@@ -376,8 +376,9 @@ def test_util_dot_section():
     factory = "textcat"
 
     [components.textcat.model]
-    @architectures = "spacy.TextCatBOW.v2"
+    @architectures = "spacy.TextCatBOW.v3"
     exclusive_classes = true
+    length = 262144
     ngram_size = 1
     no_output_layer = false
     """

website/docs/api/architectures.mdx

@@ -79,7 +79,7 @@ subword features, and a
 consisting of a CNN and a layer-normalized maxout activation function.
 
 | Name                 | Description                                                                                                                                                                                                                                                                 |
-| -------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| -------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | `width`              | The width of the input and output. These are required to be the same, so that residual connections can be used. Recommended values are `96`, `128` or `300`. ~~int~~                                                                                                        |
 | `depth`              | The number of convolutional layers to use. Recommended values are between `2` and `8`. ~~int~~                                                                                                                                                                              |
 | `embed_size`         | The number of rows in the hash embedding tables. This can be surprisingly small, due to the use of the hash embeddings. Recommended values are between `2000` and `10000`. ~~int~~                                                                                          |
@@ -962,8 +962,9 @@ single-label use-cases where `exclusive_classes = true`, while the
 > nO = null
 >
 > [model.linear_model]
-> @architectures = "spacy.TextCatBOW.v2"
+> @architectures = "spacy.TextCatBOW.v3"
 > exclusive_classes = true
+> length = 262144
 > ngram_size = 1
 > no_output_layer = false
 >
@@ -1057,14 +1058,15 @@ after training.
 
 </Accordion>
 
-### spacy.TextCatBOW.v2 {id="TextCatBOW"}
+### spacy.TextCatBOW.v3 {id="TextCatBOW"}
 
 > #### Example Config
 >
 > ```ini
 > [model]
-> @architectures = "spacy.TextCatBOW.v2"
+> @architectures = "spacy.TextCatBOW.v3"
 > exclusive_classes = false
+> length = 262144
 > ngram_size = 1
 > no_output_layer = false
 > nO = null
@@ -1078,14 +1080,19 @@ the others, but may not be as accurate, especially if texts are short.
 | `exclusive_classes` | Whether or not categories are mutually exclusive. ~~bool~~                                                                                                                                     |
 | `ngram_size`        | Determines the maximum length of the n-grams in the BOW model. For instance, `ngram_size=3` would give unigram, trigram and bigram features. ~~int~~                                           |
 | `no_output_layer`   | Whether or not to add an output layer to the model (`Softmax` activation if `exclusive_classes` is `True`, else `Logistic`). ~~bool~~                                                          |
+| `length`            | The size of the weights vector. The length will be rounded up to the next power of two if it is not a power of two. Defaults to `262144`. ~~int~~                                              |
 | `nO`                | Output dimension, determined by the number of different labels. If not set, the [`TextCategorizer`](/api/textcategorizer) component will set it when `initialize` is called. ~~Optional[int]~~ |
 | **CREATES**         | The model using the architecture. ~~Model[List[Doc], Floats2d]~~                                                                                                                               |
 
-<Accordion title="spacy.TextCatBOW.v1 definition" spaced>
+<Accordion title="Previous versions of spacy.TextCatBOW" spaced>
 
-[TextCatBOW.v1](/api/legacy#TextCatBOW_v1) had the exact same signature, but was
+- [TextCatBOW.v1](/api/legacy#TextCatBOW_v1) was not yet resizable. Since v2,
-not yet resizable. Since v2, new labels can be added to this component, even
+  new labels can be added to this component, even after training.
-after training.
+- [TextCatBOW.v1](/api/legacy#TextCatBOW_v1) and
+  [TextCatBOW.v2](/api/legacy#TextCatBOW_v2) used an erroneous sparse linear
+  layer that only used a small number of the allocated parameters.
+- [TextCatBOW.v1](/api/legacy#TextCatBOW_v1) and
+  [TextCatBOW.v2](/api/legacy#TextCatBOW_v2) did not have the `length` argument.
 
 </Accordion>
 

website/docs/api/curatedtransformer.mdx

@@ -400,6 +400,14 @@ identifiers are grouped by token. Instances of this class are typically assigned
 to the [`Doc._.trf_data`](/api/curatedtransformer#assigned-attributes) extension
 attribute.
 
+> #### Example
+>
+> ```python
+> # Get the last hidden layer output for "is" (token index 1)
+> doc = nlp("This is a text.")
+> tensors = doc._.trf_data.last_hidden_layer_state[1]
+> ```
+
 | Name              | Description                                                                                                                                                                        |
 | ----------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | `all_outputs`     | List of `Ragged` tensors that correspends to outputs of the different transformer layers. Each tensor element corresponds to a piece identifier's representation. ~~List[Ragged]~~ |

website/docs/api/legacy.mdx

@@ -198,7 +198,9 @@ architecture is usually less accurate than the ensemble, but runs faster.
 
 Since `spacy.TextCatBOW.v2`, this architecture has become resizable, which means
 that you can add labels to a previously trained textcat. `TextCatBOW` v1 did not
-yet support that.
+yet support that. Versions of this model before `spacy.TextCatBOW.v3` used an
+erroneous sparse linear layer that only used a small number of the allocated
+parameters.
 
 > #### Example Config
 >
@@ -222,6 +224,33 @@ the others, but may not be as accurate, especially if texts are short.
 | `nO`                | Output dimension, determined by the number of different labels. If not set, the [`TextCategorizer`](/api/textcategorizer) component will set it when `initialize` is called. ~~Optional[int]~~ |
 | **CREATES**         | The model using the architecture. ~~Model[List[Doc], Floats2d]~~                                                                                                                               |
 
+### spacy.TextCatBOW.v2 {id="TextCatBOW"}
+
+Versions of this model before `spacy.TextCatBOW.v3` used an erroneous sparse
+linear layer that only used a small number of the allocated parameters.
+
+> #### Example Config
+>
+> ```ini
+> [model]
+> @architectures = "spacy.TextCatBOW.v2"
+> exclusive_classes = false
+> ngram_size = 1
+> no_output_layer = false
+> nO = null
+> ```
+
+An n-gram "bag-of-words" model. This architecture should run much faster than
+the others, but may not be as accurate, especially if texts are short.
+
+| Name                | Description                                                                                                                                                                                    |
+| ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `exclusive_classes` | Whether or not categories are mutually exclusive. ~~bool~~                                                                                                                                     |
+| `ngram_size`        | Determines the maximum length of the n-grams in the BOW model. For instance, `ngram_size=3` would give unigram, trigram and bigram features. ~~int~~                                           |
+| `no_output_layer`   | Whether or not to add an output layer to the model (`Softmax` activation if `exclusive_classes` is `True`, else `Logistic`). ~~bool~~                                                          |
+| `nO`                | Output dimension, determined by the number of different labels. If not set, the [`TextCategorizer`](/api/textcategorizer) component will set it when `initialize` is called. ~~Optional[int]~~ |
+| **CREATES**         | The model using the architecture. ~~Model[List[Doc], Floats2d]~~                                                                                                                               |
+
 ### spacy.TransitionBasedParser.v1 {id="TransitionBasedParser_v1"}
 
 Identical to

website/docs/api/transformer.mdx

@@ -397,6 +397,17 @@ are wrapped into the
 by this class. Instances of this class are typically assigned to the
 [`Doc._.trf_data`](/api/transformer#assigned-attributes) extension attribute.
 
+> #### Example
+>
+> ```python
+> # Get the last hidden layer output for "is" (token index 1)
+> doc = nlp("This is a text.")
+> indices = doc._.trf_data.align[1].data.flatten()
+> last_hidden_state = doc._.trf_data.model_output.last_hidden_state
+> dim = last_hidden_state.shape[-1]
+> tensors = last_hidden_state.reshape(-1, dim)[indices]
+> ```
+
 | Name           | Description                                                                                                                                                                                                                                                                                                                          |
 | -------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
 | `tokens`       | A slice of the tokens data produced by the tokenizer. This may have several fields, including the token IDs, the texts and the attention mask. See the [`transformers.BatchEncoding`](https://huggingface.co/transformers/main_classes/tokenizer.html#transformers.BatchEncoding) object for details. ~~dict~~                       |

website/docs/models/index.mdx

@@ -108,12 +108,12 @@ In the `sm`/`md`/`lg` models:
 
 #### CNN/CPU pipelines with floret vectors
 
-The Finnish, Korean and Swedish `md` and `lg` pipelines use
+The Croatian, Finnish, Korean, Slovenian, Swedish and Ukrainian `md` and `lg`
-[floret vectors](/usage/v3-2#vectors) instead of default vectors. If you're
+pipelines use [floret vectors](/usage/v3-2#vectors) instead of default vectors.
-running a trained pipeline on texts and working with [`Doc`](/api/doc) objects,
+If you're running a trained pipeline on texts and working with [`Doc`](/api/doc)
-you shouldn't notice any difference with floret vectors. With floret vectors no
+objects, you shouldn't notice any difference with floret vectors. With floret
-tokens are out-of-vocabulary, so [`Token.is_oov`](/api/token#attributes) will
+vectors no tokens are out-of-vocabulary, so
-return `False` for all tokens.
+[`Token.is_oov`](/api/token#attributes) will return `False` for all tokens.
 
 If you access vectors directly for similarity comparisons, there are a few
 differences because floret vectors don't include a fixed word list like the
@@ -132,10 +132,20 @@ vector keys for default vectors.
 
 ### Transformer pipeline design {id="design-trf"}
 
-In the transformer (`trf`) models, the `tagger`, `parser` and `ner` (if present)
+In the transformer (`trf`) pipelines, the `tagger`, `parser` and `ner` (if
-all listen to the `transformer` component. The `attribute_ruler` and
+present) all listen to the `transformer` component. The `attribute_ruler` and
 `lemmatizer` have the same configuration as in the CNN models.
 
+For spaCy v3.0-v3.6, `trf` pipelines use
+[`spacy-transformers`](https://github.com/explosion/spacy-transformers) and the
+transformer output in `doc._.trf_data` is a
+[`TransformerData`](/api/transformer#transformerdata) object.
+
+For spaCy v3.7+, `trf` pipelines use
+[`spacy-curated-transformers`](https://github.com/explosion/spacy-curated-transformers)
+and `doc._.trf_data` is a
+[`DocTransformerOutput`](/api/curatedtransformer#doctransformeroutput) object.
+
 ### Modifying the default pipeline {id="design-modify"}
 
 For faster processing, you may only want to run a subset of the components in a

website/docs/usage/layers-architectures.mdx

@@ -153,8 +153,9 @@ maxout_pieces = 3
 depth = 2
 
 [components.textcat.model.linear_model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatBOW.v3"
 exclusive_classes = true
+length = 262144
 ngram_size = 1
 no_output_layer = false
 ```
@@ -170,8 +171,9 @@ factory = "textcat"
 labels = []
 
 [components.textcat.model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatBOW.v3"
 exclusive_classes = true
+length = 262144
 ngram_size = 1
 no_output_layer = false
 nO = null

website/docs/usage/processing-pipelines.mdx

@@ -1328,8 +1328,9 @@ labels = []
 # This function is created and then passed to the "textcat" component as
 # the argument "model"
 [components.textcat.model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatBOW.v3"
 exclusive_classes = true
+length = 262144
 ngram_size = 1
 no_output_layer = false
 

website/meta/languages.json

@@ -103,6 +103,10 @@
             "has_examples": true,
             "models": ["fi_core_news_sm", "fi_core_news_md", "fi_core_news_lg"]
         },
+        {
+            "code": "fo",
+            "name": "Faroese"
+        },
         {
             "code": "fr",
             "name": "French",
@@ -290,6 +294,12 @@
             "example": "Dit is een zin.",
             "has_examples": true
         },
+        {
+            "code": "nn",
+            "name": "Norwegian Nynorsk",
+            "example": "Det er ein meir enn i same periode i fjor.",
+            "has_examples": true
+        },
         {
             "code": "pl",
             "name": "Polish",

website/meta/site.json

@@ -66,6 +66,10 @@
                 {
                     "text": "Stack Overflow",
                     "url": "http://stackoverflow.com/questions/tagged/spacy"
+                },
+                {
+                    "text": "Merchandise",
+                    "url": "https://explosion.ai/merch"
                 }
             ]
         },

website/meta/universe.json

@@ -4500,6 +4500,23 @@
                 "website": "https://nlp.unibuc.ro/people/snisioi.html"
             },
             "category": ["pipeline", "training", "models"]
+        },
+        {
+            "id": "redfield-spacy-nodes",
+            "title": "Redfield NLP Nodes for KNIME",
+            "slogan": "Makes the functionality of the spaCy library available in KNIME Analytics Platform.",
+            "description": "This extension provides nodes that make the functionality of the spaCy library available in the [KNIME Analytics Platform](https://www.knime.com/).",
+            "github": "Redfield-AB/Spacy-Nodes",
+            "url": "https://redfield.ai/spacy-redfield/",
+            "thumb": "https://raw.githubusercontent.com/Redfield-AB/Spacy-Nodes/master/resource/redfield_logo_100x100.png",
+            "image": "https://raw.githubusercontent.com/Redfield-AB/Spacy-Nodes/master/resource/screen1.png",
+            "author": "Redfield AB",
+            "author_links": {
+                "twitter": "Redfield_AB",
+                "github": "Redfield-AB",
+                "website": "https://redfield.ai"
+            },
+            "category": ["standalone"]
         }
     ],