Update spaCy pipeline

README.md

@@ -13,13 +13,13 @@ model-index:
     metrics:
     - name: NER Precision
       type: precision
-      value: 0.7517301038
+      value: 0.7437641723
     - name: NER Recall
       type: recall
-      value: 0.7376910017
+      value: 0.7248618785
     - name: NER F Score
       type: f_score
-      value: 0.7446443873
+      value: 0.7341913822
 ---
 | Feature | Description |
 | --- | --- |
@@ -30,8 +30,8 @@ model-index:
 | **Components** | `tok2vec`, `ner` |
 | **Vectors** | 514157 keys, 514157 unique vectors (300 dimensions) |
 | **Sources** | n/a |
-| **License** | MIT |
-| **Author** | Selas.ai(https://www.selas.ai/) |
+| **License** | n/a |
+| **Author** | [n/a]() |
 
 ### Label Scheme
 

config.cfg

@@ -1,6 +1,6 @@
 [paths]
-train = null
-dev = null
+train = "corpus/ner_prompting_training.spacy"
+dev = "corpus/ner_prompting_eval.spacy"
 vectors = "en_core_web_lg"
 init_tok2vec = "training/pretrain_embedding/model50.bin"
 
@@ -62,22 +62,22 @@ window_size = 1
 maxout_pieces = 3
 
 [corpora]
-@readers = "prodigy.MergedCorpus.v1"
-eval_split = 0.2
-sample_size = 1.0
-textcat = null
-textcat_multilabel = null
-parser = null
-tagger = null
-senter = null
-spancat = null
-
-[corpora.ner]
-@readers = "prodigy.NERCorpus.v1"
-datasets = ["prompt_ner_data"]
-eval_datasets = []
-default_fill = "outside"
-incorrect_key = "incorrect_spans"
+
+[corpora.dev]
+@readers = "spacy.Corpus.v1"
+path = ${paths.dev}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
+
+[corpora.train]
+@readers = "spacy.Corpus.v1"
+path = ${paths.train}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
 
 [training]
 dev_corpus = "corpora.dev"
@@ -87,8 +87,8 @@ gpu_allocator = ${system.gpu_allocator}
 dropout = 0.1
 accumulate_gradient = 1
 patience = 1600
-max_epochs = 0
-max_steps = 20000
+max_epochs = 200
+max_steps = 5000
 eval_frequency = 200
 frozen_components = []
 annotating_components = []

en_ner_prompting-any-py3-none-any.whl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9a637faaf89ee9081fb79810bd057c57121952cbfc906847296cedcfd46d01c
-size 606800932
+oid sha256:5d9755bb2d870ebfb2d2bde3ff39df42fb9bd82fee259c42d8c12eb20f5e2dd7
+size 606727740

meta.json

@@ -8,7 +8,7 @@
   "url":"",
   "license":"",
   "spacy_version":">=3.4.3,<3.5.0",
-  "spacy_git_version":"Unknown",
+  "spacy_git_version":"63673a792",
   "vectors":{
     "width":300,
     "vectors":514157,
@@ -21,8 +21,7 @@
     ],
     "ner":[
       "color",
-      "composition/scale",
-      "composition/view",
+      "composition",
       "context/emotion",
       "context/era",
       "context/weather",
@@ -36,7 +35,6 @@
       "medium/painting",
       "medium/photography",
       "medium/rendering",
-      "other",
       "subject"
     ]
   },
@@ -52,103 +50,93 @@
 
   ],
   "performance":{
-    "ents_f":0.7446443873,
-    "ents_p":0.7517301038,
-    "ents_r":0.7376910017,
+    "ents_f":0.7341913822,
+    "ents_p":0.7437641723,
+    "ents_r":0.7248618785,
     "ents_per_type":{
-      "context/emotion":{
-        "p":0.7924528302,
-        "r":0.6885245902,
-        "f":0.7368421053
-      },
-      "influence/artwork":{
-        "p":0.9666666667,
-        "r":0.7837837838,
-        "f":0.8656716418
-      },
       "subject":{
-        "p":0.6339622642,
-        "r":0.6176470588,
-        "f":0.625698324
-      },
-      "influence/genre":{
-        "p":0.7222222222,
-        "r":0.6610169492,
-        "f":0.6902654867
-      },
-      "medium/illustration":{
-        "p":0.8153846154,
-        "r":0.7910447761,
-        "f":0.803030303
+        "p":0.556122449,
+        "r":0.5396039604,
+        "f":0.5477386935
       },
       "influence/artist":{
-        "p":0.817679558,
-        "r":0.875739645,
-        "f":0.8457142857
+        "p":0.8592592593,
+        "r":0.8992248062,
+        "f":0.8787878788
       },
-      "detail":{
-        "p":0.88,
-        "r":0.9462365591,
-        "f":0.9119170984
-      },
-      "context/era":{
-        "p":0.8125,
-        "r":0.7222222222,
-        "f":0.7647058824
+      "light":{
+        "p":0.8684210526,
+        "r":0.9166666667,
+        "f":0.8918918919
       },
-      "medium/painting":{
-        "p":0.65625,
-        "r":0.724137931,
-        "f":0.6885245902
+      "context/weather":{
+        "p":0.5714285714,
+        "r":0.4444444444,
+        "f":0.5
       },
       "influence/repository":{
-        "p":0.8620689655,
-        "r":0.8474576271,
-        "f":0.8547008547
-      },
-      "medium/photography":{
-        "p":0.7641509434,
-        "r":0.7363636364,
-        "f":0.75
+        "p":0.7307692308,
+        "r":0.8837209302,
+        "f":0.8
       },
-      "light":{
-        "p":0.724137931,
-        "r":0.7636363636,
-        "f":0.7433628319
+      "detail":{
+        "p":0.9285714286,
+        "r":0.8921568627,
+        "f":0.91
       },
-      "other":{
-        "p":0.0,
-        "r":0.0,
-        "f":0.0
+      "context/emotion":{
+        "p":0.7021276596,
+        "r":0.6470588235,
+        "f":0.6734693878
       },
-      "medium/rendering":{
-        "p":0.8636363636,
-        "r":0.6785714286,
-        "f":0.76
+      "medium/illustration":{
+        "p":0.880952381,
+        "r":0.7254901961,
+        "f":0.7956989247
       },
-      "context/weather":{
-        "p":0.6111111111,
-        "r":0.6111111111,
-        "f":0.6111111111
+      "composition":{
+        "p":0.6666666667,
+        "r":0.5882352941,
+        "f":0.625
       },
       "color":{
-        "p":0.5967741935,
-        "r":0.6851851852,
-        "f":0.6379310345
+        "p":0.75,
+        "r":0.7714285714,
+        "f":0.7605633803
+      },
+      "influence/genre":{
+        "p":0.6285714286,
+        "r":0.7586206897,
+        "f":0.6875
       },
-      "composition/view":{
-        "p":0.78125,
-        "r":0.6578947368,
-        "f":0.7142857143
+      "medium/photography":{
+        "p":0.7692307692,
+        "r":0.6756756757,
+        "f":0.7194244604
+      },
+      "medium/painting":{
+        "p":0.9166666667,
+        "r":0.7857142857,
+        "f":0.8461538462
+      },
+      "medium/rendering":{
+        "p":0.9166666667,
+        "r":0.7857142857,
+        "f":0.8461538462
       },
-      "composition/scale":{
+      "influence/artwork":{
         "p":0.75,
-        "r":0.3333333333,
-        "f":0.4615384615
+        "r":0.4285714286,
+        "f":0.5454545455
+      },
+      "context/era":{
+        "p":0.7272727273,
+        "r":0.8888888889,
+        "f":0.8
       }
     },
-    "tok2vec_loss":160.9330185827,
-    "ner_loss":1431.7583294513
+    "tok2vec_loss":193.2384098415,
+    "ner_loss":1445.2481568924
   },
   "requirements":[
 

ner/moves

@@ -1 +1 @@
-��moves��{"0":{},"1":{"subject":4553,"influence/artist":1419,"detail":1064,"medium/photography":716,"medium/illustration":461,"light":428,"influence/repository":417,"influence/genre":390,"context/emotion":300,"composition/view":291,"medium/rendering":282,"color":270,"influence/artwork":250,"medium/painting":193,"context/era":140,"context/weather":112,"composition/scale":22,"other":2},"2":{"subject":4553,"influence/artist":1419,"detail":1064,"medium/photography":716,"medium/illustration":461,"light":428,"influence/repository":417,"influence/genre":390,"context/emotion":300,"composition/view":291,"medium/rendering":282,"color":270,"influence/artwork":250,"medium/painting":193,"context/era":140,"context/weather":112,"composition/scale":22,"other":2},"3":{"subject":4553,"influence/artist":1419,"detail":1064,"medium/photography":716,"medium/illustration":461,"light":428,"influence/repository":417,"influence/genre":390,"context/emotion":300,"composition/view":291,"medium/rendering":282,"color":270,"influence/artwork":250,"medium/painting":193,"context/era":140,"context/weather":112,"composition/scale":22,"other":2},"4":{"subject":4553,"influence/artist":1419,"detail":1064,"medium/photography":716,"medium/illustration":461,"light":428,"influence/repository":417,"influence/genre":390,"context/emotion":300,"composition/view":291,"medium/rendering":282,"color":270,"influence/artwork":250,"medium/painting":193,"context/era":140,"context/weather":112,"composition/scale":22,"other":2,"":1},"5":{"":1}}�cfg��neg_key�
+��moves�8{"0":{},"1":{"subject":2659,"influence/artist":992,"detail":709,"medium/photography":455,"influence/genre":303,"medium/illustration":287,"light":278,"influence/repository":273,"color":207,"composition":197,"medium/rendering":183,"context/emotion":173,"influence/artwork":168,"medium/painting":141,"context/era":89,"context/weather":70},"2":{"subject":2659,"influence/artist":992,"detail":709,"medium/photography":455,"influence/genre":303,"medium/illustration":287,"light":278,"influence/repository":273,"color":207,"composition":197,"medium/rendering":183,"context/emotion":173,"influence/artwork":168,"medium/painting":141,"context/era":89,"context/weather":70},"3":{"subject":2659,"influence/artist":992,"detail":709,"medium/photography":455,"influence/genre":303,"medium/illustration":287,"light":278,"influence/repository":273,"color":207,"composition":197,"medium/rendering":183,"context/emotion":173,"influence/artwork":168,"medium/painting":141,"context/era":89,"context/weather":70},"4":{"subject":2659,"influence/artist":992,"detail":709,"medium/photography":455,"influence/genre":303,"medium/illustration":287,"light":278,"influence/repository":273,"color":207,"composition":197,"medium/rendering":183,"context/emotion":173,"influence/artwork":168,"medium/painting":141,"context/era":89,"context/weather":70,"":1},"5":{"":1}}�cfg��neg_key�

tok2vec/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:892198f793ba9dadc96ba7d4d6d86e76e2fe451360647dac8bab065959cf718a
+oid sha256:bc2ffe6a6cd103c9e73a386c9462ce17cdb7f33b42530d5f34b4bce6039da8af
 size 34434008

vocab/strings.json

@@ -1152,7 +1152,6 @@
   ",50",
   ",60",
   ",62",
-  ",8k",
   ",99",
   ",In",
   ",LTD",
@@ -1164,6 +1163,7 @@
   ",Xxx",
   ",Xxxxx",
   ",and",
+  ",in",
   ",limited",
   ",ltd",
   ",n",
@@ -9680,7 +9680,6 @@
   "1/144",
   "1/15",
   "1/16",
-  "1/160s",
   "1/16th",
   "1/16\u2033",
   "1/17",
@@ -32877,7 +32876,6 @@
   "538",
   "538,000",
   "5380",
-  "5384",
   "538532836498889",
   "5387",
   "539",
@@ -112357,7 +112355,6 @@
   "Daendels",
   "Daenerys",
   "Daeng",
-  "Daeni",
   "Daens",
   "Daer",
   "Daerah",
@@ -121091,7 +121088,6 @@
   "Dofollow",
   "Dofus",
   "Dog",
-  "DogDay",
   "Doga",
   "Dogan",
   "Dogana",
@@ -129626,7 +129622,6 @@
   "Ejisu",
   "Ejnar",
   "Ejogo",
-  "Ejsing",
   "Ejuice",
   "Ej\u00e9rcito",
   "Ek",
@@ -148231,7 +148226,6 @@
   "GIGA",
   "GIGABYTE",
   "GIGANTIC",
-  "GIGER",
   "GIGGLE",
   "GIGGLES",
   "GIGGLING",
@@ -155612,7 +155606,6 @@
   "Gmelina",
   "Gmina",
   "Gmo",
-  "Gmod",
   "Gmp",
   "Gms",
   "Gmunden",
@@ -162483,7 +162476,6 @@
   "HDPE",
   "HDR",
   "HDR+",
-  "HDR,8k",
   "HDR10",
   "HDRI",
   "HDRip",
@@ -165794,7 +165786,6 @@
   "Hantz",
   "Hantzsch",
   "Hanu",
-  "Hanuka",
   "Hanukah",
   "Hanukkah",
   "Hanul",
@@ -178140,7 +178131,6 @@
   "IPython",
   "IQ",
   "IQ+",
-  "IQ4",
   "IQ97",
   "IQA",
   "IQAC",
@@ -187439,7 +187429,6 @@
   "Jayhawk",
   "Jayhawkers",
   "Jayhawks",
-  "Jayison",
   "Jayla",
   "Jaylah",
   "Jaylen",
@@ -194746,7 +194735,6 @@
   "Karlin",
   "Karlina",
   "Karlis",
-  "Karlkka",
   "Karlo",
   "Karloff",
   "Karlos",
@@ -201933,7 +201921,6 @@
   "Kopelson",
   "Kopenhagen",
   "Koper",
-  "Kopera",
   "Koperasi",
   "Kopernik",
   "Kopernika",
@@ -204898,7 +204885,6 @@
   "Kuvempu",
   "Kuvin",
   "Kuvira",
-  "Kuvshinov",
   "Kuwa",
   "Kuwabara",
   "Kuwahara",
@@ -216674,7 +216660,6 @@
   "Lorcan",
   "Lorcaserin",
   "Lorch",
-  "Lorck",
   "Lorc\u00e1n",
   "Lord",
   "Lord's",
@@ -278834,7 +278819,6 @@
   "Prance",
   "Prancer",
   "Prancing",
-  "Pranckevicius",
   "Prandelli",
   "Prandi",
   "Prandtl",
@@ -285979,7 +285963,6 @@
   "RGs",
   "RH",
   "RHA",
-  "RHADS",
   "RHB",
   "RHC",
   "RHCE",
@@ -289947,7 +289930,6 @@
   "Raytheon",
   "Rayton",
   "Raytown",
-  "Raytracing",
   "Rayudu",
   "Rayvanny",
   "Rayver",
@@ -338806,7 +338788,6 @@
   "Tekke",
   "Tekken",
   "Tekkesi",
-  "Tekkonkinkreet",
   "Tekla",
   "Tekle",
   "Tekna",
@@ -372285,7 +372266,6 @@
   "XXX+XxxXxxxx",
   "XXX+d",
   "XXX+dd",
-  "XXX,dx",
   "XXX-",
   "XXX--",
   "XXX-d",
@@ -374212,7 +374192,6 @@
   "Y'ello",
   "Y'know",
   "Y'see",
-  "Y'shtola",
   "Y-",
   "Y--",
   "Y-1",
@@ -377878,7 +377857,6 @@
   "Zabou",
   "Zabranjeno",
   "Zabriskie",
-  "Zabrocki",
   "Zabrus",
   "Zabrze",
   "Zabu",
@@ -392371,7 +392349,6 @@
   "ambrosious",
   "ambrosius",
   "ambrosoli",
-  "ambrotype",
   "ambrus",
   "ambrym",
   "ambr\u00ec",
@@ -400390,7 +400367,6 @@
   "artrocker",
   "arts",
   "artsakh",
-  "artsation",
   "artscape",
   "artschwager",
   "artscience",
@@ -409766,7 +409742,6 @@
   "barkerville",
   "barkett",
   "barkey",
-  "barkfolk",
   "barkha",
   "barkhaa",
   "barkhad",
@@ -417759,7 +417734,6 @@
   "bioluminecant",
   "bioluminescence",
   "bioluminescent",
-  "bioluminiscence",
   "biomagnification",
   "bioman",
   "biomanufacturing",
@@ -419706,7 +419680,6 @@
   "blob",
   "blobby",
   "blobel",
-  "blobfish",
   "blobs",
   "bloc",
   "blocage",
@@ -438806,7 +438779,6 @@
   "cgsc",
   "cgsociety",
   "cgst",
-  "cgstudio",
   "cgt",
   "cgtn",
   "cgu",
@@ -446371,7 +446343,6 @@
   "close",
   "close-",
   "close--",
-  "close:7",
   "closeburn",
   "closebut",
   "closeby",
@@ -447332,7 +447303,6 @@
   "cockamamie",
   "cockapoo",
   "cockapoos",
-  "cockateil",
   "cockatiel",
   "cockatiels",
   "cockatoo",
@@ -449783,8 +449753,6 @@
   "compositeurs",
   "compositing",
   "composition",
-  "composition/scale",
-  "composition/view",
   "compositional",
   "compositionality",
   "compositionally",
@@ -458922,7 +458890,6 @@
   "cybercenter",
   "cyberchase",
   "cyberconnect2",
-  "cybercore",
   "cybercrime",
   "cybercrimes",
   "cybercriminal",
@@ -460661,7 +460628,6 @@
   "d/ddd",
   "d/dddd",
   "d/ddddxx",
-  "d/dddx",
   "d/dddxx",
   "d/dddxxx",
   "d/ddxx",
@@ -460988,7 +460954,6 @@
   "dabra",
   "dabrafenib",
   "dabral",
-  "dabrowa",
   "dabrowski",
   "dabs",
   "dabu",
@@ -461144,7 +461109,6 @@
   "daendels",
   "daenerys",
   "daeng",
-  "daeni",
   "daens",
   "daer",
   "daerah",
@@ -465625,7 +465589,6 @@
   "dehaene",
   "dehaj",
   "dehalogenase",
-  "deharme",
   "dehart",
   "dehat",
   "dehaven",
@@ -470815,7 +470778,6 @@
   "dimming",
   "dimmit",
   "dimmitt",
-  "dimmly",
   "dimmock",
   "dimms",
   "dimmu",
@@ -472506,8 +472468,6 @@
   "distler",
   "distomo",
   "diston",
-  "distopia",
-  "distopian",
   "distort",
   "distorta",
   "distorted",
@@ -473708,7 +473668,6 @@
   "dogbert",
   "dogboy",
   "dogcatcher",
-  "dogday",
   "doge",
   "dogeared",
   "dogecoin",
@@ -473859,7 +473818,6 @@
   "doit",
   "doityourself.com",
   "doivent",
-  "doizon",
   "doj",
   "doja",
   "dojang",
@@ -478750,6 +478708,7 @@
   "dwys",
   "dw\u00f3r",
   "dx",
+  "dx.",
   "dx.x",
   "dx.x.",
   "dx/ddx",
@@ -479975,7 +479934,6 @@
   "e95",
   "e:-",
   "e:0",
-  "e:7",
   "e=",
   "e?s",
   "e?}",
@@ -486816,7 +486774,6 @@
   "enviromental",
   "enviroments",
   "environ",
-  "environement",
   "environics",
   "environing",
   "environment",
@@ -487749,7 +487706,6 @@
   "erdene",
   "erdenet",
   "erdf",
-  "erdil",
   "erding",
   "erdinger",
   "erdington",
@@ -489371,7 +489327,6 @@
   "etain",
   "etajima",
   "etal",
-  "etale",
   "etalon",
   "etam",
   "etan",
@@ -495960,7 +495915,6 @@
   "femicides",
   "femina",
   "feminazi",
-  "femine",
   "feminin",
   "feminina",
   "feminine",
@@ -505933,7 +505887,6 @@
   "g95",
   "g9a",
   "g:-",
-  "g:7",
   "g?I",
   "gAN",
   "gB",
@@ -513682,7 +513635,6 @@
   "gmmtv",
   "gmn",
   "gmo",
-  "gmod",
   "gmos",
   "gmp",
   "gmps",
@@ -523870,7 +523822,6 @@
   "hantz",
   "hantzsch",
   "hanu",
-  "hanuka",
   "hanukah",
   "hanukkah",
   "hanul",
@@ -526191,7 +526142,6 @@
   "hdpe",
   "hdr",
   "hdr+",
-  "hdr,8k",
   "hdr10",
   "hdri",
   "hdrip",
@@ -545791,7 +545741,6 @@
   "ip\u00e9",
   "ip\u00fa",
   "iq",
-  "iq4",
   "iq97",
   "iqa",
   "iqac",
@@ -550157,7 +550106,6 @@
   "jayhawk",
   "jayhawkers",
   "jayhawks",
-  "jayison",
   "jayla",
   "jaylah",
   "jaylen",
@@ -557115,7 +557063,6 @@
   "karlin",
   "karlina",
   "karlis",
-  "karlkka",
   "karlo",
   "karloff",
   "karlos",
@@ -559027,7 +558974,6 @@
   "kelaudin",
   "kelber",
   "kelburn",
-  "kelbv",
   "kelby",
   "kelce",
   "kelcey",
@@ -564586,7 +564532,6 @@
   "kolomenskoye",
   "kolomna",
   "kolomoisky",
-  "kolomoyskaya",
   "kolomoyskyi",
   "kolomyia",
   "kolon",
@@ -576430,7 +576375,6 @@
   "leyden",
   "leydig",
   "leydon",
-  "leydy",
   "leye",
   "leyen",
   "leyenda",
@@ -581199,7 +581143,6 @@
   "lorcan",
   "lorcaserin",
   "lorch",
-  "lorck",
   "lorc\u00e1n",
   "lord",
   "lord's",
@@ -587101,7 +587044,6 @@
   "mail?|",
   "maila",
   "mailable",
-  "mailai",
   "mailand",
   "mailata",
   "mailbag",
@@ -610536,7 +610478,6 @@
   "muscadine",
   "muscae",
   "muscala",
-  "muscan",
   "muscarella",
   "muscari",
   "muscaria",
@@ -618797,7 +618738,6 @@
   "nicoletta",
   "nicolette",
   "nicoletti",
-  "nicoletto",
   "nicoli",
   "nicolina",
   "nicoline",
@@ -647699,7 +647639,6 @@
   "pneumonic",
   "pneumonie",
   "pneumonitis",
-  "pneumonoultramicroscopicsilicovolcanoconiosis",
   "pneumoperitoneum",
   "pneumophila",
   "pneumothorax",
@@ -649393,7 +649332,6 @@
   "ponyboy",
   "ponyfish",
   "ponying",
-  "ponylawson",
   "ponyo",
   "ponyri",
   "ponys",
@@ -651480,7 +651418,6 @@
   "prancer",
   "prances",
   "prancing",
-  "pranckevicius",
   "prandelli",
   "prandi",
   "prandial",
@@ -656823,7 +656760,6 @@
   "punking",
   "punkish",
   "punknews.org",
-  "punkpastels",
   "punks",
   "punkt",
   "punkte",
@@ -657105,7 +657041,6 @@
   "purpurascens",
   "purpurata",
   "purpuratus",
-  "purpure",
   "purpurea",
   "purpureum",
   "purpureus",
@@ -664299,7 +664234,6 @@
   "realself",
   "realsense",
   "realsies",
-  "realsim",
   "realspace",
   "realted",
   "realtek",
@@ -667559,7 +667493,6 @@
   "renaming",
   "renamings",
   "renamo",
-  "renamon",
   "renan",
   "renard",
   "renart",
@@ -669113,7 +669046,6 @@
   "retablo",
   "retablos",
   "retail",
-  "retaildesignblog",
   "retailed",
   "retailer",
   "retailers",
@@ -671809,7 +671741,6 @@
   "ritchies",
   "ritchson",
   "rite",
-  "ritehusk",
   "riteish",
   "ritek",
   "ritenour",
@@ -676339,7 +676270,6 @@
   "rushydro",
   "rusi",
   "rusia",
-  "rusian",
   "rusin",
   "rusinga",
   "rusinov",
@@ -680706,7 +680636,6 @@
   "sandomir",
   "sandon",
   "sandor",
-  "sandorfi",
   "sandos",
   "sandoval",
   "sandover",
@@ -688804,7 +688733,6 @@
   "serres",
   "serret",
   "serri",
-  "serria",
   "serried",
   "serrulata",
   "serrulatus",
@@ -693903,7 +693831,6 @@
   "sibur",
   "sibusiso",
   "sibutramine",
-  "sibuya",
   "sibuyan",
   "siby",
   "sibyl",
@@ -701772,7 +701699,6 @@
   "spaceshiptwo",
   "spacesuit",
   "spacesuits",
-  "spacesut",
   "spacetime",
   "spacetimes",
   "spacetoon",
@@ -703040,7 +702966,6 @@
   "spitzer",
   "spitzhauben",
   "spitzweg",
-  "spitzweg:7",
   "spiv",
   "spiva",
   "spivack",
@@ -712016,7 +711941,6 @@
   "surber",
   "surbhi",
   "surbiton",
-  "surburb",
   "surcease",
   "surcharge",
   "surcharged",
@@ -719296,7 +719220,6 @@
   "tekken",
   "tekkes",
   "tekkesi",
-  "tekkonkinkreet",
   "tekla",
   "tekle",
   "teklynx",
@@ -726305,7 +726228,6 @@
   "tomainian",
   "tomake",
   "tomakomai",
-  "tomalak",
   "tomales",
   "tomalin",
   "toman",
@@ -732943,7 +732865,6 @@
   "turramurra",
   "turrbal",
   "turre",
-  "turrel",
   "turrell",
   "turrentine",
   "turret",
@@ -735692,7 +735613,6 @@
   "ultraconservative",
   "ultracore",
   "ultracute",
-  "ultradetailed",
   "ultrafast",
   "ultrafilter",
   "ultrafilters",
@@ -735728,7 +735648,6 @@
   "ultraportable",
   "ultrapure",
   "ultrarealism",
-  "ultrarealistic",
   "ultrarunner",
   "ultrarunning",
   "ultras",
@@ -747536,7 +747455,6 @@
   "voluma",
   "volume",
   "volumen",
-  "volumentric",
   "volumes",
   "volumetric",
   "volumetrically",
@@ -749877,7 +749795,6 @@
   "walter",
   "walter--",
   "walterboro",
-  "walterdale",
   "walteri",
   "walternate",
   "walters",
@@ -760664,9 +760581,11 @@
   "xxxx",
   "xxxx!",
   "xxxx!!!!xx",
+  "xxxx!!,xx",
   "xxxx!!|",
   "xxxx!,X",
   "xxxx!,Xx",
+  "xxxx!,xx",
   "xxxx!X",
   "xxxx!Xx",
   "xxxx!Xxx",
@@ -760835,6 +760754,7 @@
   "xxxx/dd,ddd",
   "xxxx/ddd",
   "xxxx/ddd,ddd",
+  "xxxx/xxx",
   "xxxx/xxxx",
   "xxxx:",
   "xxxx:\"X",
@@ -761409,7 +761329,6 @@
   "y're",
   "y's",
   "y'see",
-  "y'shtola",
   "y(A",
   "y(s",
   "y(t",
@@ -765124,7 +765043,6 @@
   "zabou",
   "zabranjeno",
   "zabriskie",
-  "zabrocki",
   "zabrus",
   "zabrze",
   "zabu",
@@ -776558,7 +776476,6 @@
   "\ud83c\udde6",
   "\ud83c\udde7",
   "\ud83c\udde8",
-  "\ud83c\udde9",
   "\ud83c\uddea",
   "\ud83c\uddec",
   "\ud83c\udded",
@@ -776791,8 +776708,6 @@
   "\ud83e\udd37",
   "\ud83e\udd42",
   "\ud83e\udd47",
-  "\ud83e\udd51",
-  "\ud83e\udd52",
   "\ud83e\udd70",
   "\ud83e\udd73",
   "\ud83e\udd7a",