Update spaCy pipeline

README.md

@@ -14,18 +14,18 @@ model-index:
     metrics:
     - name: NER Precision
       type: precision
-      value: 0.9265694149
+      value: 0.9421775682
     - name: NER Recall
       type: recall
-      value: 0.9274815422
+      value: 0.9493801653
     - name: NER F Score
       type: f_score
-      value: 0.9270252542
+      value: 0.9457651539
 ---
 | Feature | Description |
 | --- | --- |
 | **Name** | `en_generic` |
-| **Version** | `0.0.2` |
+| **Version** | `0.0.3` |
 | **spaCy** | `>=3.7.5,<3.8.0` |
 | **Default Pipeline** | `tok2vec`, `ner`, `textcat` |
 | **Components** | `tok2vec`, `ner`, `textcat` |
@@ -51,17 +51,17 @@ model-index:
 
 | Type | Score |
 | --- | --- |
-| `ENTS_F` | 92.70 |
-| `ENTS_P` | 92.66 |
-| `ENTS_R` | 92.75 |
-| `CATS_SCORE` | 98.18 |
-| `CATS_MICRO_P` | 98.34 |
-| `CATS_MICRO_R` | 98.34 |
-| `CATS_MICRO_F` | 98.34 |
-| `CATS_MACRO_P` | 98.17 |
-| `CATS_MACRO_R` | 98.31 |
-| `CATS_MACRO_F` | 98.18 |
-| `CATS_MACRO_AUC` | 99.80 |
-| `TOK2VEC_LOSS` | 29535699.33 |
-| `NER_LOSS` | 267651.65 |
-| `TEXTCAT_LOSS` | 3.26 |
+| `ENTS_F` | 94.58 |
+| `ENTS_P` | 94.22 |
+| `ENTS_R` | 94.94 |
+| `CATS_SCORE` | 97.49 |
+| `CATS_MICRO_P` | 97.14 |
+| `CATS_MICRO_R` | 97.14 |
+| `CATS_MICRO_F` | 97.14 |
+| `CATS_MACRO_P` | 97.89 |
+| `CATS_MACRO_R` | 97.15 |
+| `CATS_MACRO_F` | 97.49 |
+| `CATS_MACRO_AUC` | 99.84 |
+| `TOK2VEC_LOSS` | 22259553.65 |
+| `NER_LOSS` | 723658.37 |
+| `TEXTCAT_LOSS` | 20.50 |

en_generic-any-py3-none-any.whl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d278b05d8100f86213cf7a6193afe93d4e96b6e0d2e58807803c91dbe82f6b5
-size 608050944
+oid sha256:b96ebfacfb98a9aea4816b9a8f581d5b3cb8740b06e5045ec0d02ff2a80922d2
+size 608032406

meta.json

@@ -1,7 +1,7 @@
 {
   "lang":"en",
   "name":"generic",
-  "version":"0.0.2",
+  "version":"0.0.3",
   "description":"",
   "author":"",
   "email":"",
@@ -67,85 +67,90 @@
 
   ],
   "performance":{
-    "ents_f":0.9270252542,
-    "ents_p":0.9265694149,
-    "ents_r":0.9274815422,
+    "ents_f":0.9457651539,
+    "ents_p":0.9421775682,
+    "ents_r":0.9493801653,
     "ents_per_type":{
-      "PROCESSOR":{
-        "p":0.9501039501,
-        "r":0.9461697723,
-        "f":0.9481327801
+      "BRAND":{
+        "p":0.9813907933,
+        "r":0.9690522244,
+        "f":0.9751824818
       },
       "MODEL_IDENTIFIER":{
-        "p":0.8823529412,
-        "r":0.8835616438,
-        "f":0.8829568789
+        "p":0.8911917098,
+        "r":0.8786717752,
+        "f":0.8848874598
       },
-      "PRODUCT_TYPE":{
-        "p":0.9512578616,
-        "r":0.9336419753,
-        "f":0.9423676012
+      "PROCESSOR":{
+        "p":0.9142857143,
+        "r":0.9588014981,
+        "f":0.9360146252
+      },
+      "MEMORY":{
+        "p":0.95125,
+        "r":0.9632911392,
+        "f":0.9572327044
       },
       "MISC":{
-        "p":0.8630609896,
-        "r":0.8949880668,
-        "f":0.8787346221
+        "p":0.903180212,
+        "r":0.9308084487,
+        "f":0.9167862267
       },
-      "BRAND":{
-        "p":0.9771689498,
-        "r":0.9553571429,
-        "f":0.9661399549
+      "PRODUCT_TYPE":{
+        "p":0.961961962,
+        "r":0.9496047431,
+        "f":0.9557434112
       },
-      "DISPLAY":{
-        "p":0.9221052632,
-        "r":0.9221052632,
-        "f":0.9221052632
+      "COLOR":{
+        "p":0.9562575942,
+        "r":0.9609279609,
+        "f":0.9585870889
       },
       "TECH_FEATURE":{
-        "p":0.9501133787,
-        "r":0.9676674365,
-        "f":0.9588100686
+        "p":0.9301801802,
+        "r":0.9538106236,
+        "f":0.9418472064
       },
-      "MEMORY":{
-        "p":0.9727520436,
-        "r":0.9648648649,
-        "f":0.9687924016
-      },
-      "COLOR":{
-        "p":0.8944281525,
-        "r":0.9355828221,
-        "f":0.9145427286
-      },
-      "GENDER":{
-        "p":0.9556650246,
-        "r":0.9897959184,
-        "f":0.9724310777
+      "DISPLAY":{
+        "p":0.9102564103,
+        "r":0.9220779221,
+        "f":0.9161290323
       },
       "STYLE_FIT":{
-        "p":0.7980769231,
-        "r":0.6974789916,
-        "f":0.7443946188
+        "p":0.9402298851,
+        "r":0.9380733945,
+        "f":0.9391504018
+      },
+      "MATERIAL":{
+        "p":0.9782178218,
+        "r":0.9743589744,
+        "f":0.976284585
       },
       "SIZE_MEASUREMENT":{
-        "p":0.9571045576,
-        "r":0.937007874,
-        "f":0.9469496021
+        "p":0.9577625571,
+        "r":0.9665898618,
+        "f":0.9621559633
       },
-      "MATERIAL":{
-        "p":0.7857142857,
-        "r":0.8148148148,
-        "f":0.8
+      "GENDER":{
+        "p":0.985645933,
+        "r":0.9927710843,
+        "f":0.9891956783
+      },
+      "SEASON":{
+        "p":0.9785714286,
+        "r":1.0,
+        "f":0.9891696751
       }
     },
-    "cats_score":0.9818488826,
+    "cats_score":0.9748586969,
     "cats_score_desc":"macro F",
-    "cats_micro_p":0.9833759591,
-    "cats_micro_r":0.9833759591,
-    "cats_micro_f":0.9833759591,
-    "cats_macro_p":0.981702007,
-    "cats_macro_r":0.9831343403,
-    "cats_macro_f":0.9818488826,
-    "cats_macro_auc":0.9979946835,
+    "cats_micro_p":0.9714285714,
+    "cats_micro_r":0.9714285714,
+    "cats_micro_f":0.9714285714,
+    "cats_macro_p":0.9788764421,
+    "cats_macro_r":0.9715313529,
+    "cats_macro_f":0.9748586969,
+    "cats_macro_auc":0.9984373977,
     "cats_f_per_type":{
       "292":{
         "p":0.987012987,
@@ -153,14 +158,14 @@
         "f":0.9934640523
       },
       "325":{
-        "p":0.9855072464,
-        "r":0.9315068493,
-        "f":0.9577464789
+        "p":0.9863013699,
+        "r":0.9863013699,
+        "f":0.9863013699
       },
       "328":{
-        "p":0.962406015,
+        "p":1.0,
         "r":0.9846153846,
-        "f":0.9733840304
+        "f":0.992248062
       },
       "297":{
         "p":1.0,
@@ -173,24 +178,24 @@
         "f":1.0
       },
       "267":{
-        "p":1.0,
+        "p":0.9836065574,
         "r":1.0,
-        "f":1.0
+        "f":0.9917355372
       },
       "204":{
-        "p":1.0,
-        "r":0.9189189189,
-        "f":0.9577464789
+        "p":0.852173913,
+        "r":0.9074074074,
+        "f":0.8789237668
       },
       "207":{
-        "p":0.9677419355,
-        "r":1.0,
-        "f":0.9836065574
+        "p":0.8936170213,
+        "r":0.8316831683,
+        "f":0.8615384615
       },
       "2331":{
         "p":1.0,
-        "r":0.962962963,
-        "f":0.9811320755
+        "r":1.0,
+        "f":1.0
       },
       "211":{
         "p":1.0,
@@ -198,9 +203,9 @@
         "f":1.0
       },
       "212":{
-        "p":0.989010989,
-        "r":0.989010989,
-        "f":0.989010989
+        "p":0.9891304348,
+        "r":1.0,
+        "f":0.9945355191
       },
       "6228":{
         "p":1.0,
@@ -208,24 +213,24 @@
         "f":1.0
       },
       "187":{
-        "p":1.0,
-        "r":0.96,
-        "f":0.9795918367
+        "p":0.9913043478,
+        "r":1.0,
+        "f":0.9956331878
       },
       "5598":{
-        "p":0.8695652174,
-        "r":1.0,
-        "f":0.9302325581
+        "p":1.0,
+        "r":0.9,
+        "f":0.9473684211
       },
       "2271":{
-        "p":0.9642857143,
-        "r":1.0,
-        "f":0.9818181818
+        "p":1.0,
+        "r":0.962962963,
+        "f":0.9811320755
       }
     },
-    "tok2vec_loss":295356.9933269802,
-    "ner_loss":2676.5165451882,
-    "textcat_loss":0.0326477174
+    "tok2vec_loss":222595.5365317888,
+    "ner_loss":7236.5836967812,
+    "textcat_loss":0.2049790774
   },
   "requirements":[
 

ner/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7fa7ef785e4c00602a9cbb2e7fd2481a06142ed1399941d19340ef814153ebf
+oid sha256:df570e0f205fbc5bb8ef6b360461fd3a83b0d7a6583e00579176f49f701ade12
 size 181996

ner/moves

@@ -1 +1 @@
-��moves��{"0":{},"1":{"MISC":5117,"PROCESSOR":4961,"MODEL_IDENTIFIER":4872,"TECH_FEATURE":4716,"MEMORY":4489,"PRODUCT_TYPE":4059,"DISPLAY":2938,"BRAND":2919,"SIZE_MEASUREMENT":2404,"COLOR":1448,"GENDER":829,"STYLE_FIT":704,"MATERIAL":277,"SEASON":1},"2":{"MISC":5117,"PROCESSOR":4961,"MODEL_IDENTIFIER":4872,"TECH_FEATURE":4716,"MEMORY":4489,"PRODUCT_TYPE":4059,"DISPLAY":2938,"BRAND":2919,"SIZE_MEASUREMENT":2404,"COLOR":1448,"GENDER":829,"STYLE_FIT":704,"MATERIAL":277,"SEASON":1},"3":{"MISC":5117,"PROCESSOR":4961,"MODEL_IDENTIFIER":4872,"TECH_FEATURE":4716,"MEMORY":4489,"PRODUCT_TYPE":4059,"DISPLAY":2938,"BRAND":2919,"SIZE_MEASUREMENT":2404,"COLOR":1448,"GENDER":829,"STYLE_FIT":704,"MATERIAL":277,"SEASON":1},"4":{"MISC":5117,"PROCESSOR":4961,"MODEL_IDENTIFIER":4872,"TECH_FEATURE":4716,"MEMORY":4489,"PRODUCT_TYPE":4059,"DISPLAY":2938,"BRAND":2919,"SIZE_MEASUREMENT":2404,"COLOR":1448,"GENDER":829,"STYLE_FIT":704,"MATERIAL":277,"SEASON":1,"":1},"5":{"":1}}�cfg��neg_key�
+��moves��{"0":{},"1":{"MISC":8429,"PRODUCT_TYPE":6179,"SIZE_MEASUREMENT":5974,"PROCESSOR":5470,"MODEL_IDENTIFIER":5233,"BRAND":4908,"MEMORY":4738,"TECH_FEATURE":4716,"COLOR":3662,"DISPLAY":3351,"MATERIAL":2668,"STYLE_FIT":2638,"GENDER":1848,"SEASON":581},"2":{"MISC":8429,"PRODUCT_TYPE":6179,"SIZE_MEASUREMENT":5974,"PROCESSOR":5470,"MODEL_IDENTIFIER":5233,"BRAND":4908,"MEMORY":4738,"TECH_FEATURE":4716,"COLOR":3662,"DISPLAY":3351,"MATERIAL":2668,"STYLE_FIT":2638,"GENDER":1848,"SEASON":581},"3":{"MISC":8429,"PRODUCT_TYPE":6179,"SIZE_MEASUREMENT":5974,"PROCESSOR":5470,"MODEL_IDENTIFIER":5233,"BRAND":4908,"MEMORY":4738,"TECH_FEATURE":4716,"COLOR":3662,"DISPLAY":3351,"MATERIAL":2668,"STYLE_FIT":2638,"GENDER":1848,"SEASON":581},"4":{"MISC":8429,"PRODUCT_TYPE":6179,"SIZE_MEASUREMENT":5974,"PROCESSOR":5470,"MODEL_IDENTIFIER":5233,"BRAND":4908,"MEMORY":4738,"TECH_FEATURE":4716,"COLOR":3662,"DISPLAY":3351,"MATERIAL":2668,"STYLE_FIT":2638,"GENDER":1848,"SEASON":581,"":1},"5":{"":1}}�cfg��neg_key�

textcat/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98935af7512b9be5f0cbc42759a0ec49b34f86a3b268883a467a920c249287d4
+oid sha256:c96b2df8fefd5652d84c302e1a673ee89e4c2ab8a4fd7c55d044226244e9295d
 size 16540172

tok2vec/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24c843358be8357a4311eda83573453135dcc4576cce0ad0ec1d6a0aec81d534
+oid sha256:471b349054b773505954162884ddb2e8c171fa7d65b5e348b0e7fa2b389450b6
 size 34434008

vocab/strings.json

@@ -10359,6 +10359,7 @@
   "101.3",
   "101.4",
   "101.5",
+  "101.5cm",
   "101.5cm)",
   "101.6",
   "101.6cm)",
@@ -10442,6 +10443,7 @@
   "1028",
   "1029",
   "102a",
+  "102cm",
   "102cm)",
   "102d",
   "102nd",
@@ -10582,6 +10584,7 @@
   "106.3",
   "106.4",
   "106.5",
+  "106.5cm",
   "106.5cm)",
   "106.6",
   "106.7",
@@ -10645,6 +10648,7 @@
   "1077",
   "1078",
   "1079",
+  "107cm",
   "107cm)",
   "107th",
   "108",
@@ -11470,6 +11474,7 @@
   "1167",
   "1168",
   "1169",
+  "116cm",
   "116cm)",
   "116th",
   "116\u2013111",
@@ -12104,6 +12109,7 @@
   "1227",
   "1228",
   "1229",
+  "122cm",
   "122cm)",
   "122d",
   "122nd",
@@ -12293,6 +12299,7 @@
   "1277",
   "1278",
   "1279",
+  "127cm",
   "127cm)",
   "127th",
   "128",
@@ -12327,6 +12334,7 @@
   "128GB",
   "128GB)",
   "128K",
+  "128cm",
   "128cm)",
   "128g",
   "128g)",
@@ -13404,6 +13412,7 @@
   "1407",
   "1408",
   "1409",
+  "140cm",
   "140cm)",
   "140k",
   "140lbs",
@@ -13479,6 +13488,7 @@
   "1427",
   "1428",
   "1429",
+  "142cm",
   "142cm)",
   "142d",
   "142nd",
@@ -14094,6 +14104,7 @@
   "1528",
   "1529",
   "1529\u20131536",
+  "152cm",
   "152cm)",
   "152nd",
   "153",
@@ -15161,6 +15172,7 @@
   "1709",
   "170C",
   "170c",
+  "170cm",
   "170cm)",
   "170k",
   "170lbs",
@@ -20331,6 +20343,7 @@
   "19th/20th",
   "19thcentury",
   "19th\u201320th",
+  "19v69",
   "19w",
   "19x",
   "19xx",
@@ -25444,9 +25457,11 @@
   "2568",
   "2569",
   "2569.26",
+  "256G",
   "256G)",
   "256GB",
   "256GB)",
+  "256g",
   "256g)",
   "256gb",
   "256gb)",
@@ -27879,6 +27894,7 @@
   "3/8\u2033",
   "3/9",
   "30",
+  "30\"",
   "30%-40",
   "30'",
   "30')",
@@ -28289,6 +28305,7 @@
   "30\u2032",
   "30\u2033",
   "31",
+  "31\"",
   "31'",
   "31(1",
   "31(2",
@@ -29002,12 +29019,14 @@
   "33A",
   "33B",
   "33C",
+  "33L",
   "33W",
   "33a",
   "33b",
   "33c",
   "33d",
   "33k",
+  "33l",
   "33million",
   "33rd",
   "33rpm",
@@ -34127,6 +34146,7 @@
   "52G",
   "52H",
   "52a",
+  "52cm",
   "52cm)",
   "52d",
   "52g",
@@ -34478,6 +34498,7 @@
   "55a",
   "55b",
   "55bn",
+  "55cm",
   "55cm)",
   "55f",
   "55h",
@@ -34770,6 +34791,7 @@
   "58Q",
   "58U",
   "58a",
+  "58cm",
   "58cm)",
   "58p",
   "58q",
@@ -35064,6 +35086,7 @@
   "5c.",
   "5cc",
   "5cl",
+  "5cm",
   "5ct",
   "5d",
   "5d.",
@@ -35457,6 +35480,7 @@
   "6.55\"4500mAh",
   "6.55\"4500mah",
   "6.55")",
+  "6.55''",
   "6.56",
   "6.56\"",
   "6.56")",
@@ -36064,6 +36088,7 @@
   "631",
   "631,163",
   "6310",
+  "6310i",
   "6311",
   "63110",
   "6312",
@@ -36122,6 +36147,7 @@
   "63UKC65SH",
   "63W",
   "63a",
+  "63cm",
   "63cm)",
   "63d",
   "63rd",
@@ -36447,6 +36473,7 @@
   "66ER",
   "66XL8LFDQ",
   "66a",
+  "66cm",
   "66cm)",
   "66er",
   "66ers",
@@ -37539,6 +37566,7 @@
   "71B",
   "71N",
   "71b",
+  "71cm",
   "71cm)",
   "71n",
   "71s",
@@ -37800,6 +37828,7 @@
   "74A",
   "74G",
   "74a",
+  "74cm",
   "74cm)",
   "74g",
   "74th",
@@ -38393,6 +38422,7 @@
   "7O",
   "7P",
   "7PM",
+  "7Pro",
   "7R",
   "7Rv",
   "7S",
@@ -38468,6 +38498,7 @@
   "7p.m.",
   "7plus",
   "7pm",
+  "7pro",
   "7pts",
   "7px",
   "7qc",
@@ -39016,6 +39047,7 @@
   "81.4",
   "81.5",
   "81.50",
+  "81.5cm",
   "81.5cm)",
   "81.6",
   "81.7",
@@ -39070,6 +39102,7 @@
   "8191",
   "8192",
   "81V",
+  "81cm",
   "81cm)",
   "81st",
   "81v",
@@ -39281,6 +39314,7 @@
   "84E",
   "84F",
   "84W",
+  "84cm",
   "84cm)",
   "84s",
   "84th",
@@ -39450,6 +39484,7 @@
   "86L",
   "86W",
   "86a",
+  "86cm",
   "86cm)",
   "86ers",
   "86f",
@@ -40325,6 +40360,7 @@
   "90b",
   "90bn",
   "90c",
+  "90cm",
   "90cm)",
   "90d",
   "90f",
@@ -40363,8 +40399,10 @@
   "91.3",
   "91.4",
   "91.44",
+  "91.4cm",
   "91.4cm)",
   "91.5",
+  "91.5cm",
   "91.5cm)",
   "91.6",
   "91.67",
@@ -40422,6 +40460,7 @@
   "919th",
   "91Mobiles",
   "91W",
+  "91cm",
   "91cm)",
   "91mobiles",
   "91st",
@@ -40699,6 +40738,7 @@
   "96.4",
   "96.5",
   "96.50",
+  "96.5cm",
   "96.5cm)",
   "96.6",
   "96.7",
@@ -40810,6 +40850,7 @@
   "9797",
   "97a",
   "97b",
+  "97cm",
   "97cm)",
   "97th",
   "97\u201393",
@@ -40967,6 +41008,7 @@
   "99acres.com",
   "99b",
   "99c",
+  "99cm",
   "99designs",
   "99e",
   "99ers",
@@ -64754,6 +64796,7 @@
   "BIRDIE",
   "BIRDS",
   "BIRDSONG",
+  "BIRKENSTOCK",
   "BIRKHOFF",
   "BIRMINGHAM",
   "BIRN",
@@ -111416,6 +111459,7 @@
   "Cyberghost",
   "Cyberia",
   "Cyberinfrastructure",
+  "Cyberjammies",
   "Cyberjaya",
   "Cyberlink",
   "Cyberman",
@@ -286437,6 +286481,7 @@
   "Qichao",
   "Qichen",
   "Qicheng",
+  "Qick",
   "Qidan",
   "Qidong",
   "Qie",
@@ -303063,6 +303108,7 @@
   "SANCTUARY",
   "SAND",
   "SANDAG",
+  "SANDAL",
   "SANDER",
   "SANDERS",
   "SANDERSON",
@@ -306994,6 +307040,7 @@
   "Sabeel",
   "Sabeen",
   "Sabel",
+  "Sabela",
   "Sabela'",
   "Sabella",
   "Sabelli",
@@ -323482,6 +323529,7 @@
   "Smartboard",
   "Smartcard",
   "Smartcode",
+  "Smartdry",
   "Smartek",
   "Smarten",
   "Smarter",
@@ -343047,6 +343095,7 @@
   "Tessmacher",
   "Tessmann",
   "Tesson",
+  "Tessuti",
   "Tessy",
   "Test",
   "TestComplete",
@@ -462301,6 +462350,7 @@
   "cyberhugs",
   "cyberia",
   "cyberinfrastructure",
+  "cyberjammies",
   "cyberjaya",
   "cyberknife",
   "cyberlink",
@@ -682175,6 +682225,7 @@
   "sabeel",
   "sabeen",
   "sabel",
+  "sabela",
   "sabela'",
   "sabella",
   "sabelli",
@@ -702156,6 +702207,7 @@
   "smartcompany",
   "smartdraw",
   "smartdrive",
+  "smartdry",
   "smarted",
   "smartek",
   "smarten",
@@ -724912,6 +724964,7 @@
   "tessmacher",
   "tessmann",
   "tesson",
+  "tessuti",
   "tessy",
   "test",
   "test(s",
@@ -744979,6 +745032,7 @@
   "v60",
   "v600",
   "v600e",
+  "v69",
   "v6s",
   "v7",
   "v70",