Merge branch 'master' of github.com:pmbaumgartner/spaCy

pyproject.toml

@@ -5,6 +5,6 @@ requires = ["setuptools",
             "cymem>=2.0.2,<2.1.0",
             "preshed>=2.0.1,<2.1.0",
             "murmurhash>=0.28.0,<1.1.0",
-            "thinc>=7.0.6,<7.1.0",
+            "thinc>=7.0.8,<7.1.0",
             ]
 build-backend = "setuptools.build_meta"

requirements.txt

@@ -1,7 +1,7 @@
 # Our libraries
 cymem>=2.0.2,<2.1.0
 preshed>=2.0.1,<2.1.0
-thinc>=7.0.6,<7.1.0
+thinc>=7.0.8,<7.1.0
 blis>=0.2.2,<0.3.0
 murmurhash>=0.28.0,<1.1.0
 wasabi>=0.2.0,<1.1.0

setup.py

@@ -228,7 +228,7 @@ def setup_package():
                 "murmurhash>=0.28.0,<1.1.0",
                 "cymem>=2.0.2,<2.1.0",
                 "preshed>=2.0.1,<2.1.0",
-                "thinc>=7.0.6,<7.1.0",
+                "thinc>=7.0.8,<7.1.0",
                 "blis>=0.2.2,<0.3.0",
                 "plac<1.0.0,>=0.9.6",
                 "requests>=2.13.0,<3.0.0",

spacy/about.py

@@ -4,13 +4,13 @@
 # fmt: off
 
 __title__ = "spacy"
-__version__ = "2.1.5.dev0"
+__version__ = "2.1.6"
 __summary__ = "Industrial-strength Natural Language Processing (NLP) with Python and Cython"
 __uri__ = "https://spacy.io"
 __author__ = "Explosion AI"
 __email__ = "contact@explosion.ai"
 __license__ = "MIT"
-__release__ = False
+__release__ = True
 
 __download_url__ = "https://github.com/explosion/spacy-models/releases/download"
 __compatibility__ = "https://raw.githubusercontent.com/explosion/spacy-models/master/compatibility.json"

spacy/attrs.pxd

@@ -1,4 +1,6 @@
 # Reserve 64 values for flag features
+from . cimport symbols
+
 cdef enum attr_id_t:
     NULL_ATTR
     IS_ALPHA
@@ -82,10 +84,10 @@ cdef enum attr_id_t:
     DEP
     ENT_IOB
     ENT_TYPE
-    ENT_KB_ID
     HEAD
     SENT_START
     SPACY
     PROB
 
     LANG
+    ENT_KB_ID = symbols.ENT_KB_ID

spacy/lang/da/punctuation.py

@@ -14,10 +14,11 @@
     + [
         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}]),(?=[{a}])".format(a=ALPHA),
         r"(?<=[{a}])([{q}\)\]\(\[])(?=[{a}])".format(a=ALPHA, q=_quotes),
         r"(?<=[{a}])--(?=[{a}])".format(a=ALPHA),
+        r"(?<=[{a}0-9])[:<>=/](?=[{a}])".format(a=ALPHA),
     ]
 )
 

spacy/lang/da/tokenizer_exceptions.py

@@ -52,6 +52,7 @@
     {ORTH: "Ons.", LEMMA: "onsdag"},
     {ORTH: "Fre.", LEMMA: "fredag"},
     {ORTH: "Lør.", LEMMA: "lørdag"},
+    {ORTH: "og/eller", LEMMA: "og/eller", NORM: "og/eller", TAG: "CC"},
 ]:
     _exc[exc_data[ORTH]] = [exc_data]
 
@@ -64,6 +65,8 @@
     "mik.",
     "pers.",
     "A.D.",
+    "A/B",
+    "a/s",
     "A/S",
     "B.C.",
     "BK.",
@@ -79,7 +82,9 @@
     "Kprs.",
     "L.A.",
     "Ll.",
+    "m/k",
     "m/s",
+    "m/sek.",
     "M/S",
     "Mag.",
     "Mr.",
@@ -90,6 +95,7 @@
     "Sdr.",
     "Skt.",
     "Spl.",
+    "TCP/IP",
     "Vg.",
 ]:
     _exc[orth] = [{ORTH: orth}]
@@ -141,6 +147,7 @@
     "brolægn.",
     "bto.",
     "bygn.",
+    "c/o",
     "ca.",
     "cand.",
     "d.d.",
@@ -293,6 +300,7 @@
     "kgl.",
     "kl.",
     "kld.",
+    "km/t",
     "knsp.",
     "komm.",
     "kons.",

spacy/symbols.pxd

@@ -81,7 +81,6 @@ cdef enum symbol_t:
     DEP
     ENT_IOB
     ENT_TYPE
-    ENT_KB_ID
     HEAD
     SENT_START
     SPACY
@@ -461,3 +460,5 @@ cdef enum symbol_t:
     xcomp
 
     acl
+
+    ENT_KB_ID

spacy/tests/lang/da/test_exceptions.py

@@ -43,3 +43,27 @@ def test_da_tokenizer_handles_custom_base_exc(da_tokenizer):
 def test_da_tokenizer_norm_exceptions(da_tokenizer, text, norm):
     tokens = da_tokenizer(text)
     assert tokens[0].norm_ == norm
+
+
+@pytest.mark.parametrize(
+    "text,n_tokens",
+    [
+        ("Godt og/eller skidt", 3),
+        ("Kør 4 km/t på vejen", 5),
+        ("Det blæser 12 m/s.", 5),
+        ("Det blæser 12 m/sek. på havnen", 6),
+        ("Windows 8/Windows 10", 5),
+        ("Billeten virker til bus/tog/metro", 8),
+        ("26/02/2019", 1),
+        ("Kristiansen c/o Madsen", 3),
+        ("Sprogteknologi a/s", 2),
+        ("De boede i A/B Bellevue", 5),
+        ("Rotorhastigheden er 3400 o/m.", 5),
+        ("Jeg købte billet t/r.", 5),
+        ("Murerarbejdsmand m/k søges", 3),
+        ("Netværket kører over TCP/IP", 4),
+    ],
+)
+def test_da_tokenizer_slash(da_tokenizer, text, n_tokens):
+    tokens = da_tokenizer(text)
+    assert len(tokens) == n_tokens

spacy/tests/regression/test_issue3611.py

@@ -0,0 +1,51 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+import pytest
+import spacy
+from spacy.util import minibatch, compounding
+
+
+def test_issue3611():
+    """ Test whether adding n-grams in the textcat works even when n > token length of some docs """
+    unique_classes = ["offensive", "inoffensive"]
+    x_train = ["This is an offensive text",
+               "This is the second offensive text",
+               "inoff"]
+    y_train = ["offensive", "offensive", "inoffensive"]
+
+    # preparing the data
+    pos_cats = list()
+    for train_instance in y_train:
+        pos_cats.append({label: label == train_instance for label in unique_classes})
+    train_data = list(zip(x_train, [{'cats': cats} for cats in pos_cats]))
+
+    # set up the spacy model with a text categorizer component
+    nlp = spacy.blank('en')
+
+    textcat = nlp.create_pipe(
+        "textcat",
+        config={
+            "exclusive_classes": True,
+            "architecture": "bow",
+            "ngram_size": 2
+        }
+    )
+
+    for label in unique_classes:
+        textcat.add_label(label)
+    nlp.add_pipe(textcat, last=True)
+
+    # training the network
+    other_pipes = [pipe for pipe in nlp.pipe_names if pipe != 'textcat']
+    with nlp.disable_pipes(*other_pipes):
+        optimizer = nlp.begin_training()
+        for i in range(3):
+            losses = {}
+            batches = minibatch(train_data, size=compounding(4.0, 32.0, 1.001))
+
+            for batch in batches:
+                texts, annotations = zip(*batch)
+                nlp.update(docs=texts, golds=annotations, sgd=optimizer, drop=0.1, losses=losses)
+
+

website/src/widgets/landing.js

@@ -152,20 +152,21 @@ const Landing = ({ data }) => {
             <LandingBannerGrid>
                 <LandingBanner
                     title="spaCy IRL 2019: Two days of NLP"
-                    label="Join us in Berlin"
-                    to="https://irl.spacy.io/2019"
-                    button="Get tickets"
+                    label="Watch the videos"
+                    to="https://www.youtube.com/playlist?list=PLBmcuObd5An4UC6jvK_-eSl6jCvP1gwXc"
+                    button="Watch the videos"
                     background="#ffc194"
                     backgroundImage={irlBackground}
                     color="#1a1e23"
                     small
                 >
-                    We're pleased to invite the spaCy community and other folks working on Natural
+                    We were pleased to invite the spaCy community and other folks working on Natural
                     Language Processing to Berlin this summer for a small and intimate event{' '}
-                    <strong>July 5-6, 2019</strong>. The event includes a hands-on training day for
-                    teams using spaCy in production, followed by a one-track conference. We've
-                    booked a beautiful venue, hand-picked an awesome lineup of speakers and
-                    scheduled plenty of social time to get to know each other and exchange ideas.
+                    <strong>July 6, 2019</strong>. We booked a beautiful venue, hand-picked an
+                    awesome lineup of speakers and scheduled plenty of social time to get to know
+                    each other and exchange ideas. The YouTube playlist includes 12 talks about NLP
+                    research, development and applications, with keynotes by Sebastian Ruder
+                    (DeepMind) and Yoav Goldberg (Allen AI).
                 </LandingBanner>
 
                 <LandingBanner