Update spaCy pipeline

README.md

@@ -13,13 +13,13 @@ model-index:
     metrics:
     - name: NER Precision
       type: precision
-      value: 0.9911054638
+      value: 0.9918793503
     - name: NER Recall
       type: recall
-      value: 0.9961685824
+      value: 0.9965034965
     - name: NER F Score
       type: f_score
-      value: 0.9936305732
+      value: 0.9941860465
 ---
 | Feature | Description |
 | --- | --- |
@@ -37,11 +37,11 @@ model-index:
 
 <details>
 
-<summary>View label scheme (14 labels for 1 components)</summary>
+<summary>View label scheme (16 labels for 1 components)</summary>
 
 | Component | Labels |
 | --- | --- |
-| **`ner`** | `BOOK`, `COMODITY`, `CONTAINER COUNT`, `CONTAINER SIZE`, `CONTAINER SIZE-COUNT`, `DESTINATION`, `ENQUIRY`, `HELP`, `INCOTERM`, `KYC`, `ORIGIN`, `SEARCH RATES`, `SHIP`, `SHIPMENT TYPE` |
+| **`ner`** | `AGENT_FALLBACK`, `BOOK`, `COMODITY`, `CONTAINER COUNT`, `CONTAINER SIZE`, `CONTAINER SIZE-COUNT`, `DESTINATION`, `ENQUIRY`, `HELP`, `INCOTERM`, `KYC`, `ORIGIN`, `SEARCH RATES`, `SHIP`, `SHIPMENT TYPE`, `WELCOME_MSG` |
 
 </details>
 
@@ -49,8 +49,8 @@ model-index:
 
 | Type | Score |
 | --- | --- |
-| `ENTS_F` | 99.36 |
-| `ENTS_P` | 99.11 |
-| `ENTS_R` | 99.62 |
-| `TOK2VEC_LOSS` | 2568.71 |
-| `NER_LOSS` | 72512.12 |
+| `ENTS_F` | 99.42 |
+| `ENTS_P` | 99.19 |
+| `ENTS_R` | 99.65 |
+| `TOK2VEC_LOSS` | 1794.25 |
+| `NER_LOSS` | 53209.43 |

en_Spacy_Custom_ner-any-py3-none-any.whl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a364263e1ea76bc005845412055c872711c33940cdeefc6a83e0539e681d4443
-size 606702436
+oid sha256:6c1dfad1de671b67c459dd222393bda59cb8b55935047966fae7f871ef4e92a5
+size 606745566

meta.json

@@ -20,6 +20,7 @@
 
     ],
     "ner":[
+      "AGENT_FALLBACK",
       "BOOK",
       "COMODITY",
       "CONTAINER COUNT",
@@ -33,7 +34,8 @@
       "ORIGIN",
       "SEARCH RATES",
       "SHIP",
-      "SHIPMENT TYPE"
+      "SHIPMENT TYPE",
+      "WELCOME_MSG"
     ]
   },
   "pipeline":[
@@ -48,9 +50,9 @@
 
   ],
   "performance":{
-    "ents_f":0.9936305732,
-    "ents_p":0.9911054638,
-    "ents_r":0.9961685824,
+    "ents_f":0.9941860465,
+    "ents_p":0.9918793503,
+    "ents_r":0.9965034965,
     "ents_per_type":{
       "SEARCH RATES":{
         "p":1.0,
@@ -63,9 +65,9 @@
         "f":1.0
       },
       "DESTINATION":{
-        "p":0.9951456311,
-        "r":0.9951456311,
-        "f":0.9951456311
+        "p":0.9903846154,
+        "r":1.0,
+        "f":0.9951690821
       },
       "BOOK":{
         "p":1.0,
@@ -88,9 +90,9 @@
         "f":1.0
       },
       "ENQUIRY":{
-        "p":0.875,
+        "p":0.8823529412,
         "r":1.0,
-        "f":0.9333333333
+        "f":0.9375
       },
       "HELP":{
         "p":1.0,
@@ -118,13 +120,23 @@
         "f":1.0
       },
       "CONTAINER SIZE-COUNT":{
-        "p":0.962962963,
+        "p":1.0,
+        "r":0.9615384615,
+        "f":0.9803921569
+      },
+      "AGENT_FALLBACK":{
+        "p":1.0,
         "r":1.0,
-        "f":0.9811320755
+        "f":1.0
+      },
+      "WELCOME_MSG":{
+        "p":1.0,
+        "r":1.0,
+        "f":1.0
       }
     },
-    "tok2vec_loss":25.687124317,
-    "ner_loss":725.1211642546
+    "tok2vec_loss":17.9424619099,
+    "ner_loss":532.0943451776
   },
   "requirements":[
 

ner/moves

@@ -1 +1 @@
-��moves��{"0":{},"1":{"DESTINATION":321,"ORIGIN":303,"CONTAINER SIZE":188,"SHIP":81,"SHIPMENT TYPE":58,"CONTAINER SIZE-COUNT":39,"COMODITY":31,"BOOK":28,"ENQUIRY":17,"SEARCH RATES":14,"CONTAINER COUNT":10,"INCOTERM":9,"HELP":8,"KYC":2},"2":{"DESTINATION":321,"ORIGIN":303,"CONTAINER SIZE":188,"SHIP":81,"SHIPMENT TYPE":58,"CONTAINER SIZE-COUNT":39,"COMODITY":31,"BOOK":28,"ENQUIRY":17,"SEARCH RATES":14,"CONTAINER COUNT":10,"INCOTERM":9,"HELP":8,"KYC":2},"3":{"DESTINATION":321,"ORIGIN":303,"CONTAINER SIZE":188,"SHIP":81,"SHIPMENT TYPE":58,"CONTAINER SIZE-COUNT":39,"COMODITY":31,"BOOK":28,"ENQUIRY":17,"SEARCH RATES":14,"CONTAINER COUNT":10,"INCOTERM":9,"HELP":8,"KYC":2},"4":{"DESTINATION":321,"ORIGIN":303,"CONTAINER SIZE":188,"SHIP":81,"SHIPMENT TYPE":58,"CONTAINER SIZE-COUNT":39,"COMODITY":31,"BOOK":28,"ENQUIRY":17,"SEARCH RATES":14,"CONTAINER COUNT":10,"INCOTERM":9,"HELP":8,"KYC":2,"":1},"5":{"":1}}�cfg��neg_key�
+��moves�{"0":{},"1":{"DESTINATION":321,"ORIGIN":303,"CONTAINER SIZE":188,"WELCOME_MSG":178,"SHIP":81,"AGENT_FALLBACK":79,"SHIPMENT TYPE":58,"CONTAINER SIZE-COUNT":39,"COMODITY":31,"BOOK":28,"ENQUIRY":18,"SEARCH RATES":14,"CONTAINER COUNT":10,"INCOTERM":9,"HELP":8,"KYC":2},"2":{"DESTINATION":321,"ORIGIN":303,"CONTAINER SIZE":188,"WELCOME_MSG":178,"SHIP":81,"AGENT_FALLBACK":79,"SHIPMENT TYPE":58,"CONTAINER SIZE-COUNT":39,"COMODITY":31,"BOOK":28,"ENQUIRY":18,"SEARCH RATES":14,"CONTAINER COUNT":10,"INCOTERM":9,"HELP":8,"KYC":2},"3":{"DESTINATION":321,"ORIGIN":303,"CONTAINER SIZE":188,"WELCOME_MSG":178,"SHIP":81,"AGENT_FALLBACK":79,"SHIPMENT TYPE":58,"CONTAINER SIZE-COUNT":39,"COMODITY":31,"BOOK":28,"ENQUIRY":18,"SEARCH RATES":14,"CONTAINER COUNT":10,"INCOTERM":9,"HELP":8,"KYC":2},"4":{"DESTINATION":321,"ORIGIN":303,"CONTAINER SIZE":188,"WELCOME_MSG":178,"SHIP":81,"AGENT_FALLBACK":79,"SHIPMENT TYPE":58,"CONTAINER SIZE-COUNT":39,"COMODITY":31,"BOOK":28,"ENQUIRY":18,"SEARCH RATES":14,"CONTAINER COUNT":10,"INCOTERM":9,"HELP":8,"KYC":2,"":1},"5":{"":1}}�cfg��neg_key�

tok2vec/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c83c2459bf502042051b25033c05728ecf79a17b4b147f639bdfef5570b4a869
+oid sha256:4e2f3e2fab9f568a5c3e23cbe9aa9f9e7e51da3c44d61ed32c617696964b45eb
 size 34434008

vocab/strings.json

@@ -41039,11 +41039,13 @@
   "AGE",
   "AGED",
   "AGENCIES",
+  "AGENCIEZ",
   "AGENCY",
   "AGENDA",
   "AGENOR",
   "AGENT",
   "AGENTS",
+  "AGENT_FALLBACK",
   "AGES",
   "AGEs",
   "AGF",
@@ -43300,6 +43302,7 @@
   "Aadhi",
   "Aadi",
   "Aadil",
+  "Aaditi",
   "Aaditya",
   "Aadland",
   "Aadmi",
@@ -47093,6 +47096,7 @@
   "Agros",
   "Agrostis",
   "Agrostophyllum",
+  "Agrotech",
   "Agrotera",
   "Agrotis",
   "Agrupaci\u00f3n",
@@ -53338,6 +53342,7 @@
   "Annapolis",
   "Annapoorna",
   "Annapurna",
+  "Annapushti",
   "Annarella",
   "Annas",
   "Annasaheb",
@@ -58472,6 +58477,7 @@
   "Astrodynamics",
   "Astrof\u00edsica",
   "Astroglide",
+  "Astrokidz",
   "Astrolabe",
   "Astroloba",
   "Astrologer",
@@ -111061,6 +111067,7 @@
   "DINE",
   "DINER",
   "DINESH",
+  "DINESHKUMAR",
   "DING",
   "DINGING",
   "DINGO",
@@ -135710,6 +135717,7 @@
   "Exposure",
   "Exposures",
   "Expos\u00e9",
+  "Expoter",
   "Expounding",
   "Expreso",
   "Express",
@@ -147828,6 +147836,7 @@
   "GARDNER",
   "GARETH",
   "GARFIELD",
+  "GARG",
   "GARLAND",
   "GARLIC",
   "GARMENT",
@@ -149242,6 +149251,7 @@
   "GWB",
   "GWC",
   "GWD",
+  "GWE",
   "GWEN",
   "GWF",
   "GWG",
@@ -159674,6 +159684,7 @@
   "Gruffudd",
   "Gruffydd",
   "Grug",
+  "Gruh",
   "Gruhn",
   "Gruidae",
   "Gruiformes",
@@ -162940,6 +162951,7 @@
   "HITCHCOCK",
   "HITEC",
   "HITECH",
+  "HITESHKUMAR",
   "HITLER",
   "HITMAN",
   "HITRUST",
@@ -168842,6 +168854,7 @@
   "Hellner",
   "Hello",
   "Hello!",
+  "Hello,,Welcome",
   "Hello-",
   "Hello--",
   "HelloFresh",
@@ -177196,6 +177209,7 @@
   "IGTV",
   "IGU",
   "IGV",
+  "IGWE",
   "IGY",
   "IGZO",
   "IGs",
@@ -181067,6 +181081,7 @@
   "Indivisible",
   "Indi\u00eb",
   "Indo",
+  "IndoMart",
   "Indochina",
   "Indochine",
   "Indochinese",
@@ -181163,6 +181178,7 @@
   "Indur\u00e1in",
   "Indus",
   "IndusInd",
+  "Industires",
   "Industri",
   "IndustriALL",
   "Industria",
@@ -181185,6 +181201,7 @@
   "Industrielle",
   "Industriels",
   "Industries",
+  "IndustriesPlease",
   "Industrija",
   "Industrious",
   "Industriously",
@@ -182033,6 +182050,7 @@
   "Insitu",
   "Insitute",
   "Insitutional",
+  "Insiya",
   "Inskeep",
   "Inski",
   "Inskip",
@@ -185283,6 +185301,7 @@
   "JIF",
   "JIG",
   "JIGGER",
+  "JIGNESH",
   "JIGSAW",
   "JIL",
   "JIL-1",
@@ -187399,6 +187418,7 @@
   "Jayadeva",
   "Jayadevan",
   "Jayadratha",
+  "Jayaesh",
   "Jayakanthan",
   "Jayakar",
   "Jayakody",
@@ -207058,6 +207078,7 @@
   "LOG",
   "LOGAN",
   "LOGCAP",
+  "LOGI",
   "LOGIC",
   "LOGICAL",
   "LOGIN",
@@ -263233,6 +263254,7 @@
   "PARAMEDIC",
   "PARAMETERS",
   "PARAMOUNT",
+  "PARAMPARA",
   "PARANOIA",
   "PARANOID",
   "PARANORMAL",
@@ -281066,6 +281088,7 @@
   "Provato",
   "Prove",
   "Proved",
+  "Proveg",
   "Proven",
   "Provenance",
   "Provencal",
@@ -285204,6 +285227,7 @@
   "RATES",
   "RATH",
   "RATHER",
+  "RATHOD",
   "RATING",
   "RATINGS",
   "RATIO",
@@ -285924,6 +285948,7 @@
   "REWINDING",
   "REWRITE",
   "REX",
+  "REXPRESS",
   "REXX",
   "REY",
   "REYES",
@@ -286574,6 +286599,7 @@
   "ROTC",
   "ROTH",
   "ROTJ",
+  "ROTOFAB",
   "ROTOR",
   "ROTTEN",
   "ROU",
@@ -286882,6 +286908,7 @@
   "RUDI",
   "RUDN",
   "RUDOLPH",
+  "RUDRAX",
   "RUDY",
   "RUE",
   "RUF",
@@ -288297,6 +288324,7 @@
   "Rajshri",
   "Rajsich",
   "Rajskub",
+  "Rajsun",
   "Raju",
   "Rajula",
   "Rajvansh",
@@ -302778,6 +302806,7 @@
   "SRHR",
   "SRI",
   "SRINAGAR",
+  "SRINT",
   "SRK",
   "SRL",
   "SRM",
@@ -316596,6 +316625,7 @@
   "Shreds",
   "Shree",
   "Shreeram",
+  "Shreevam",
   "Shreeve",
   "Shreeves",
   "Shrek",
@@ -334664,6 +334694,7 @@
   "TRANSPLANT",
   "TRANSPORT",
   "TRANSPORTATION",
+  "TRANSVISION",
   "TRAP",
   "TRAPPED",
   "TRAPPIST-1",
@@ -360359,6 +360390,7 @@
   "Visker",
   "Visma",
   "Vismara",
+  "Vismay",
   "Visme",
   "Visnu",
   "Viso",
@@ -362704,6 +362736,7 @@
   "WELCH",
   "WELCOME",
   "WELCOMES",
+  "WELCOME_MSG",
   "WELD",
   "WELDED",
   "WELDING",
@@ -372419,6 +372452,7 @@
   "XXXXXXX",
   "XXXXXXXXXX",
   "XXXX]/xxxx",
+  "XXXX_XXX",
   "XXXX_XXXX",
   "XXXX_XXXX_XXXX_XXXX",
   "XXXX_XXXX}-",
@@ -373870,6 +373904,7 @@
   "Xxxxx+Xxx",
   "Xxxxx+Xxxx",
   "Xxxxx+Xxxxx",
+  "Xxxxx,,Xxxxx",
   "Xxxxx,-xxx",
   "Xxxxx-",
   "Xxxxx-'Xxx",
@@ -375764,6 +375799,7 @@
   "Yeliseyev",
   "Yeliz",
   "Yelizaveta",
+  "Yelkar",
   "Yell",
   "Yell.com",
   "Yella",
@@ -381988,6 +382024,7 @@
   "aadhi",
   "aadi",
   "aadil",
+  "aaditi",
   "aaditya",
   "aadl",
   "aadland",
@@ -387073,6 +387110,7 @@
   "agencia",
   "agencias",
   "agencies",
+  "agenciez",
   "agencja",
   "agency",
   "agencys",
@@ -387084,6 +387122,7 @@
   "agenor",
   "agent(s",
   "agent--",
+  "agent_fallback",
   "agente",
   "agentes",
   "agentic",
@@ -387524,6 +387563,7 @@
   "agrosciences",
   "agrostis",
   "agrostophyllum",
+  "agrotech",
   "agrotera",
   "agrotis",
   "aground",
@@ -395048,6 +395088,7 @@
   "annapolis",
   "annapoorna",
   "annapurna",
+  "annapushti",
   "annarella",
   "annas",
   "annasaheb",
@@ -401991,6 +402032,7 @@
   "astroglial",
   "astroglide",
   "astrogliosis",
+  "astrokidz",
   "astrolabe",
   "astrolabes",
   "astroloba",
@@ -470889,6 +470931,7 @@
   "dinescu",
   "dinesen",
   "dinesh",
+  "dineshkumar",
   "dinette",
   "ding",
   "dinga",
@@ -491797,6 +491840,7 @@
   "expos\u00e9",
   "expos\u00e9es",
   "expos\u00e9s",
+  "expoter",
   "expound",
   "expounded",
   "expounding",
@@ -518410,6 +518454,7 @@
   "gruffudd",
   "gruffydd",
   "grug",
+  "gruh",
   "gruhn",
   "gruidae",
   "gruiformes",
@@ -527471,6 +527516,7 @@
   "hello!",
   "hello!,I",
   "hello!,i",
+  "hello,,welcome",
   "hello-",
   "hello--",
   "hellofresh",
@@ -530816,6 +530862,7 @@
   "hitei",
   "hiten",
   "hitesh",
+  "hiteshkumar",
   "hitfix",
   "hither",
   "hitherto",
@@ -542061,6 +542108,7 @@
   "indology",
   "indomalaya",
   "indomalayan",
+  "indomart",
   "indomethacin",
   "indomie",
   "indominus",
@@ -542191,6 +542239,7 @@
   "industrielles",
   "industriels",
   "industries",
+  "industriesplease",
   "industrija",
   "industrious",
   "industriously",
@@ -543552,6 +543601,7 @@
   "insitu",
   "insitute",
   "insitutional",
+  "insiya",
   "inskeep",
   "inski",
   "inskip",
@@ -549999,6 +550049,8 @@
   "jayadeva",
   "jayadevan",
   "jayadratha",
+  "jayaesh",
+  "[email protected]",
   "jayakanthan",
   "jayakar",
   "jayakody",
@@ -661630,6 +661682,7 @@
   "rajshri",
   "rajsich",
   "rajskub",
+  "rajsun",
   "raju",
   "rajula",
   "rajvansh",
@@ -669739,6 +669792,7 @@
   "rexie",
   "rexinger",
   "rexona",
+  "rexpress",
   "rexroth",
   "rexton",
   "rexx",
@@ -674349,6 +674403,7 @@
   "rotj",
   "rotman",
   "roto",
+  "rotofab",
   "rotogravure",
   "rotoiti",
   "rotolo",
@@ -675513,6 +675568,7 @@
   "rudraprayag",
   "rudrapur",
   "rudras",
+  "rudrax",
   "rudresh",
   "rudsar",
   "rudy",
@@ -679387,6 +679443,7 @@
   "saleroom",
   "salers",
   "sales",
+  "[email protected]",
   "salesbury",
   "salesclerk",
   "salesclerks",
@@ -693063,6 +693120,7 @@
   "shreds",
   "shree",
   "shreeram",
+  "shreevam",
   "shreeve",
   "shreeves",
   "shrek",
@@ -704050,6 +704108,7 @@
   "srinivas",
   "srinivasa",
   "srinivasan",
+  "srint",
   "srinu",
   "sripada",
   "sriperumbudur",
@@ -711930,6 +711989,7 @@
   "surges",
   "surgical",
   "surgically",
+  "surgicals",
   "surging",
   "surgisphere",
   "surguja",
@@ -746192,6 +746252,7 @@
   "vism",
   "visma",
   "vismara",
+  "vismay",
   "visme",
   "visnu",
   "viso",
@@ -752242,6 +752303,7 @@
   "welco",
   "welcoat",
   "welcome",
+  "welcome_msg",
   "welcomed",
   "welcomes",
   "welcoming",
@@ -758390,6 +758452,7 @@
   "www.google.com",
   "www.gymnasticsresults.com",
   "www.ibb.gov/editorials",
+  "www.jayagenciez.com",
   "www.mcoa.cn",
   "www.minorplanet.info",
   "www.mysitesname.com/home",
@@ -760549,6 +760612,7 @@
   "xxxx+xxxx+xxxx",
   "xxxx,\"xxx",
   "xxxx,\"xxxx",
+  "xxxx,,xxxx",
   "xxxx,-xxx",
   "xxxx,d",
   "xxxx,ddd",
@@ -760619,6 +760683,7 @@
   "xxxx.xxx.xxxx(xxxx",
   "xxxx.xxx/x/xxx/xxxx/d",
   "xxxx.xxx/xxxx",
+  "[email protected]",
   "xxxx.xxxXxxx.xxxx.xxxx",
   "xxxx.xxxXxxxxXxXx(\"xxxx\").xxxXxxxx",
   "xxxx.xxxx",
@@ -762547,6 +762612,7 @@
   "yeliseyev",
   "yeliz",
   "yelizaveta",
+  "yelkar",
   "yell",
   "yell.com",
   "yella",
@@ -776300,7 +776366,10 @@
   "\ufe0e",
   "\ufe0f",
   "\ufe0f.",
+  "\ufe0fPlease",
+  "\ufe0fXxxxx",
   "\ufe0fphone",
+  "\ufe0fplease",
   "\ufe0fxxxx",
   "\ufe0f\u200d",
   "\ufe0f\ufe0f",
@@ -776359,6 +776428,12 @@
   "\uffe5dd",
   "\ufffc",
   "\ufffd",
+  "\ud835\udc05",
+  "\ud835\udc05\ud835\udc28\ud835\udc27\ud835\udc1d\ud835\udc1e\ud835\udc31",
+  "\ud835\udc0e",
+  "\ud835\udc0e\ud835\udc2f\ud835\udc1e\ud835\udc2b\ud835\udc2c\ud835\udc1e\ud835\udc1a\ud835\udc2c",
+  "\ud835\udc1d\ud835\udc1e\ud835\udc31",
+  "\ud835\udc1e\ud835\udc1a\ud835\udc2c",
   "\ud835\udc65",
   "\ud83c\udde6",
   "\ud83c\udde7",
@@ -776429,8 +776504,13 @@
   "\ud83c\udfc8",
   "\ud83c\udfe1",
   "\ud83c\udfe2",
+  "\ud83c\udfed",
   "\ud83c\udff3",
   "\ud83c\udffb",
+  "\ud83c\udffbJeet",
+  "\ud83c\udffbXxxx",
+  "\ud83c\udffbjeet",
+  "\ud83c\udffbxxxx",
   "\ud83c\udffb\u200d",
   "\ud83c\udffc",
   "\ud83c\udffc\u200d",
@@ -776570,6 +776650,8 @@
   "\ud83d\ude4f",
   "\ud83d\ude80",
   "\ud83d\ude97",
+  "\ud83d\ude9a",
+  "\ud83d\ude9b",
   "\ud83d\udea8",
   "\ud83d\udeab",
   "\ud83e\udc80",