Ybhav14 commited on
Commit
0014b42
1 Parent(s): afa9f96

Update spaCy pipeline

Browse files
README.md CHANGED
@@ -13,13 +13,13 @@ model-index:
13
  metrics:
14
  - name: NER Precision
15
  type: precision
16
- value: 0.9911054638
17
  - name: NER Recall
18
  type: recall
19
- value: 0.9961685824
20
  - name: NER F Score
21
  type: f_score
22
- value: 0.9936305732
23
  ---
24
  | Feature | Description |
25
  | --- | --- |
@@ -37,11 +37,11 @@ model-index:
37
 
38
  <details>
39
 
40
- <summary>View label scheme (14 labels for 1 components)</summary>
41
 
42
  | Component | Labels |
43
  | --- | --- |
44
- | **`ner`** | `BOOK`, `COMODITY`, `CONTAINER COUNT`, `CONTAINER SIZE`, `CONTAINER SIZE-COUNT`, `DESTINATION`, `ENQUIRY`, `HELP`, `INCOTERM`, `KYC`, `ORIGIN`, `SEARCH RATES`, `SHIP`, `SHIPMENT TYPE` |
45
 
46
  </details>
47
 
@@ -49,8 +49,8 @@ model-index:
49
 
50
  | Type | Score |
51
  | --- | --- |
52
- | `ENTS_F` | 99.36 |
53
- | `ENTS_P` | 99.11 |
54
- | `ENTS_R` | 99.62 |
55
- | `TOK2VEC_LOSS` | 10283.83 |
56
- | `NER_LOSS` | 72242.77 |
 
13
  metrics:
14
  - name: NER Precision
15
  type: precision
16
+ value: 0.9914634146
17
  - name: NER Recall
18
  type: recall
19
+ value: 0.9963235294
20
  - name: NER F Score
21
  type: f_score
22
+ value: 0.9938875306
23
  ---
24
  | Feature | Description |
25
  | --- | --- |
 
37
 
38
  <details>
39
 
40
+ <summary>View label scheme (15 labels for 1 components)</summary>
41
 
42
  | Component | Labels |
43
  | --- | --- |
44
+ | **`ner`** | `AGENT_FALLBACK`, `BOOK`, `COMODITY`, `CONTAINER COUNT`, `CONTAINER SIZE`, `CONTAINER SIZE-COUNT`, `DESTINATION`, `ENQUIRY`, `HELP`, `INCOTERM`, `KYC`, `ORIGIN`, `SEARCH RATES`, `SHIP`, `SHIPMENT TYPE` |
45
 
46
  </details>
47
 
 
49
 
50
  | Type | Score |
51
  | --- | --- |
52
+ | `ENTS_F` | 99.39 |
53
+ | `ENTS_P` | 99.15 |
54
+ | `ENTS_R` | 99.63 |
55
+ | `TOK2VEC_LOSS` | 11705.89 |
56
+ | `NER_LOSS` | 73604.05 |
en_Spacy_Custom_ner2-any-py3-none-any.whl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82deb4dcedc1697cb7c04aa8bb5bd24465fcf13f8f9ac3f11620e486b6944684
3
- size 5683219
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7743b2f22633d673034a38e534ced88e1d2de091f27e11c5f5d8155691a4556
3
+ size 5685862
meta.json CHANGED
@@ -20,6 +20,7 @@
20
 
21
  ],
22
  "ner":[
 
23
  "BOOK",
24
  "COMODITY",
25
  "CONTAINER COUNT",
@@ -48,9 +49,9 @@
48
 
49
  ],
50
  "performance":{
51
- "ents_f":0.9936305732,
52
- "ents_p":0.9911054638,
53
- "ents_r":0.9961685824,
54
  "ents_per_type":{
55
  "SEARCH RATES":{
56
  "p":1.0,
@@ -63,9 +64,9 @@
63
  "f":1.0
64
  },
65
  "DESTINATION":{
66
- "p":0.9903846154,
67
- "r":1.0,
68
- "f":0.9951690821
69
  },
70
  "BOOK":{
71
  "p":1.0,
@@ -88,9 +89,9 @@
88
  "f":1.0
89
  },
90
  "ENQUIRY":{
91
- "p":0.875,
92
  "r":1.0,
93
- "f":0.9333333333
94
  },
95
  "HELP":{
96
  "p":1.0,
@@ -108,9 +109,9 @@
108
  "f":1.0
109
  },
110
  "COMODITY":{
111
- "p":0.9523809524,
112
- "r":0.9523809524,
113
- "f":0.9523809524
114
  },
115
  "CONTAINER COUNT":{
116
  "p":1.0,
@@ -121,10 +122,15 @@
121
  "p":0.962962963,
122
  "r":1.0,
123
  "f":0.9811320755
 
 
 
 
 
124
  }
125
  },
126
- "tok2vec_loss":102.8382523687,
127
- "ner_loss":722.4276996157
128
  },
129
  "requirements":[
130
 
 
20
 
21
  ],
22
  "ner":[
23
+ "AGENT_FALLBACK",
24
  "BOOK",
25
  "COMODITY",
26
  "CONTAINER COUNT",
 
49
 
50
  ],
51
  "performance":{
52
+ "ents_f":0.9938875306,
53
+ "ents_p":0.9914634146,
54
+ "ents_r":0.9963235294,
55
  "ents_per_type":{
56
  "SEARCH RATES":{
57
  "p":1.0,
 
64
  "f":1.0
65
  },
66
  "DESTINATION":{
67
+ "p":0.9951456311,
68
+ "r":0.9951456311,
69
+ "f":0.9951456311
70
  },
71
  "BOOK":{
72
  "p":1.0,
 
89
  "f":1.0
90
  },
91
  "ENQUIRY":{
92
+ "p":0.8823529412,
93
  "r":1.0,
94
+ "f":0.9375
95
  },
96
  "HELP":{
97
  "p":1.0,
 
109
  "f":1.0
110
  },
111
  "COMODITY":{
112
+ "p":0.9130434783,
113
+ "r":1.0,
114
+ "f":0.9545454545
115
  },
116
  "CONTAINER COUNT":{
117
  "p":1.0,
 
122
  "p":0.962962963,
123
  "r":1.0,
124
  "f":0.9811320755
125
+ },
126
+ "AGENT_FALLBACK":{
127
+ "p":1.0,
128
+ "r":1.0,
129
+ "f":1.0
130
  }
131
  },
132
+ "tok2vec_loss":117.0588980803,
133
+ "ner_loss":736.0405311402
134
  },
135
  "requirements":[
136
 
ner/model CHANGED
Binary files a/ner/model and b/ner/model differ
 
ner/moves CHANGED
@@ -1 +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�
 
1
+ ��moves��{"0":{},"1":{"DESTINATION":321,"ORIGIN":303,"CONTAINER SIZE":188,"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,"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,"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,"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 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:211fe5fa4283e43ae6b34bffbd19f77e63212df73a934ce5ba9fbebd06b93c5f
3
  size 6009091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:822be8a54a09b5c9df436b15ca1de414fca5830de7fe6ed9226c094e7718bf3f
3
  size 6009091
vocab/strings.json CHANGED
@@ -340,15 +340,19 @@
340
  "@",
341
  "@_@",
342
  "A",
 
343
  "AEJEA",
 
344
  "AIR",
345
  "ANGELES",
 
346
  "AVA",
347
  "Abbas",
348
  "Aden",
349
  "Adm",
350
  "Adm.",
351
  "Africa",
 
352
  "Ai",
353
  "Air",
354
  "Aires",
@@ -437,6 +441,7 @@
437
  "Confirm",
438
  "Conn",
439
  "Conn.",
 
440
  "Connecticut",
441
  "Consolidated",
442
  "Container",
@@ -486,6 +491,7 @@
486
  "EXW",
487
  "Egypt",
488
  "Enquiries",
 
489
  "Expedited",
490
  "Export",
491
  "Express",
@@ -551,6 +557,7 @@
551
  "How",
552
  "How's",
553
  "How\u2019s",
 
554
  "I",
555
  "I.E.",
556
  "I.e",
@@ -821,6 +828,7 @@
821
  "S",
822
  "S.C.",
823
  "SAJED",
 
824
  "SEARCH RATES",
825
  "SGH",
826
  "SHEVA",
@@ -860,6 +868,7 @@
860
  "South",
861
  "South Carolina",
862
  "Spain",
 
863
  "Special",
864
  "Specialized",
865
  "Sri",
@@ -874,6 +883,7 @@
874
  "TO",
875
  "TZDAR",
876
  "Taiwan",
 
877
  "Tanzania",
878
  "Temperature",
879
  "Tenn",
@@ -897,6 +907,7 @@
897
  "Town",
898
  "Track",
899
  "Trade",
 
900
  "Tuticorin",
901
  "Tuticorine",
902
  "Two",
@@ -966,6 +977,7 @@
966
  "XXXX",
967
  "XXXX XXXX",
968
  "XXXX XXXX-XXXX",
 
969
  "XYZ",
970
  "X_X",
971
  "X_x",
@@ -1041,6 +1053,7 @@
1041
  "ace",
1042
  "ach",
1043
  "ack",
 
1044
  "ada",
1045
  "ade",
1046
  "aden",
@@ -1049,6 +1062,7 @@
1049
  "aejea",
1050
  "africa",
1051
  "age",
 
1052
  "ago",
1053
  "ai",
1054
  "ain",
@@ -1059,12 +1073,14 @@
1059
  "ala",
1060
  "ala.",
1061
  "ali",
 
1062
  "all",
1063
  "almaty",
1064
  "als",
1065
  "also",
1066
  "am",
1067
  "ami",
 
1068
  "an.",
1069
  "ana",
1070
  "and",
@@ -1075,6 +1091,7 @@
1075
  "ant",
1076
  "any",
1077
  "ape",
 
1078
  "appropriate",
1079
  "apr",
1080
  "apr.",
@@ -1094,6 +1111,7 @@
1094
  "artworks",
1095
  "as",
1096
  "asa",
 
1097
  "ase",
1098
  "ash",
1099
  "asr",
@@ -1129,6 +1147,7 @@
1129
  "beijing",
1130
  "bel",
1131
  "belongings",
 
1132
  "berlin",
1133
  "bhuj",
1134
  "ble",
@@ -1155,7 +1174,9 @@
1155
  "cal",
1156
  "calif",
1157
  "calif.",
 
1158
  "callao",
 
1159
  "can",
1160
  "canada",
1161
  "cape",
@@ -1199,8 +1220,10 @@
1199
  "confirm",
1200
  "conn",
1201
  "conn.",
 
1202
  "consignment",
1203
  "consolidated",
 
1204
  "container",
1205
  "container count",
1206
  "container size",
@@ -1219,6 +1242,7 @@
1219
  "cross",
1220
  "ct.",
1221
  "cts",
 
1222
  "customs",
1223
  "cuz",
1224
  "c\u2019m",
@@ -1308,6 +1332,8 @@
1308
  "e.g",
1309
  "e.g.",
1310
  "each",
 
 
1311
  "eb.",
1312
  "ebr",
1313
  "ec.",
@@ -1338,6 +1364,7 @@
1338
  "ers",
1339
  "ery",
1340
  "es-",
 
1341
  "ese",
1342
  "esh",
1343
  "ess",
@@ -1389,6 +1416,7 @@
1389
  "gen.",
1390
  "germany",
1391
  "ges",
 
1392
  "ght",
1393
  "give",
1394
  "glassware",
@@ -1442,6 +1470,7 @@
1442
  "how's",
1443
  "how\u2019s",
1444
  "huj",
 
1445
  "i",
1446
  "i.",
1447
  "i.e",
@@ -1463,6 +1492,7 @@
1463
  "if.",
1464
  "igh",
1465
  "ihi",
 
1466
  "ila",
1467
  "ile",
1468
  "ill",
@@ -1486,6 +1516,7 @@
1486
  "inmun",
1487
  "inn",
1488
  "innsa",
 
1489
  "insurance",
1490
  "interested",
1491
  "intkd",
@@ -1497,6 +1528,7 @@
1497
  "irla",
1498
  "irm",
1499
  "iro",
 
1500
  "is",
1501
  "is.",
1502
  "iss",
@@ -1571,8 +1603,10 @@
1571
  "lhi",
1572
  "lia",
1573
  "lif",
 
1574
  "lin",
1575
  "line",
 
1576
  "lkcmb",
1577
  "ll",
1578
  "ll.",
@@ -1621,6 +1655,7 @@
1621
  "measuring",
1622
  "melbourne",
1623
  "men",
 
1624
  "mersin",
1625
  "mes",
1626
  "messrs",
@@ -1784,6 +1819,7 @@
1784
  "out",
1785
  "ov.",
1786
  "ove",
 
1787
  "oversized",
1788
  "owe",
1789
  "own",
@@ -1804,10 +1840,12 @@
1804
  "per",
1805
  "perishable",
1806
  "permits",
 
1807
  "personal",
1808
  "ph",
1809
  "ph.d.",
1810
  "pharmaceutical",
 
1811
  "pl",
1812
  "planning",
1813
  "ple",
@@ -1844,12 +1882,15 @@
1844
  "re",
1845
  "re.",
1846
  "rea",
 
1847
  "red",
1848
  "ree",
1849
  "refer",
 
1850
  "regulations",
1851
  "rep",
1852
  "rep.",
 
1853
  "request",
1854
  "require",
1855
  "required",
@@ -1891,6 +1932,7 @@
1891
  "sajed",
1892
  "sample",
1893
  "san",
 
1894
  "schedule",
1895
  "sea",
1896
  "search",
@@ -1939,13 +1981,16 @@
1939
  "sokhna",
1940
  "solution",
1941
  "some",
 
1942
  "somethin",
1943
  "somethin'",
1944
  "something",
1945
  "somethin\u2019",
 
1946
  "south",
1947
  "space",
1948
  "spain",
 
1949
  "special",
1950
  "specialized",
1951
  "sri",
@@ -1966,6 +2011,7 @@
1966
  "t.",
1967
  "ta",
1968
  "taiwan",
 
1969
  "tanzania",
1970
  "td.",
1971
  "ted",
@@ -2002,6 +2048,7 @@
2002
  "town",
2003
  "track",
2004
  "trade",
 
2005
  "transport",
2006
  "transportation",
2007
  "transported",
 
340
  "@",
341
  "@_@",
342
  "A",
343
+ "ACK",
344
  "AEJEA",
345
+ "AGENT_FALLBACK",
346
  "AIR",
347
  "ANGELES",
348
+ "ASAP",
349
  "AVA",
350
  "Abbas",
351
  "Aden",
352
  "Adm",
353
  "Adm.",
354
  "Africa",
355
+ "Agent",
356
  "Ai",
357
  "Air",
358
  "Aires",
 
441
  "Confirm",
442
  "Conn",
443
  "Conn.",
444
+ "Connect",
445
  "Connecticut",
446
  "Consolidated",
447
  "Container",
 
491
  "EXW",
492
  "Egypt",
493
  "Enquiries",
494
+ "Escalate",
495
  "Expedited",
496
  "Export",
497
  "Express",
 
557
  "How",
558
  "How's",
559
  "How\u2019s",
560
+ "Human",
561
  "I",
562
  "I.E.",
563
  "I.e",
 
828
  "S",
829
  "S.C.",
830
  "SAJED",
831
+ "SAP",
832
  "SEARCH RATES",
833
  "SGH",
834
  "SHEVA",
 
868
  "South",
869
  "South Carolina",
870
  "Spain",
871
+ "Speak",
872
  "Special",
873
  "Specialized",
874
  "Sri",
 
883
  "TO",
884
  "TZDAR",
885
  "Taiwan",
886
+ "Talk",
887
  "Tanzania",
888
  "Temperature",
889
  "Tenn",
 
907
  "Town",
908
  "Track",
909
  "Trade",
910
+ "Transfer",
911
  "Tuticorin",
912
  "Tuticorine",
913
  "Two",
 
977
  "XXXX",
978
  "XXXX XXXX",
979
  "XXXX XXXX-XXXX",
980
+ "XXXX_XXXX",
981
  "XYZ",
982
  "X_X",
983
  "X_x",
 
1053
  "ace",
1054
  "ach",
1055
  "ack",
1056
+ "act",
1057
  "ada",
1058
  "ade",
1059
  "aden",
 
1062
  "aejea",
1063
  "africa",
1064
  "age",
1065
+ "agent_fallback",
1066
  "ago",
1067
  "ai",
1068
  "ain",
 
1073
  "ala",
1074
  "ala.",
1075
  "ali",
1076
+ "alk",
1077
  "all",
1078
  "almaty",
1079
  "als",
1080
  "also",
1081
  "am",
1082
  "ami",
1083
+ "an",
1084
  "an.",
1085
  "ana",
1086
  "and",
 
1091
  "ant",
1092
  "any",
1093
  "ape",
1094
+ "appreciate",
1095
  "appropriate",
1096
  "apr",
1097
  "apr.",
 
1111
  "artworks",
1112
  "as",
1113
  "asa",
1114
+ "asap",
1115
  "ase",
1116
  "ash",
1117
  "asr",
 
1147
  "beijing",
1148
  "bel",
1149
  "belongings",
1150
+ "ber",
1151
  "berlin",
1152
  "bhuj",
1153
  "ble",
 
1174
  "cal",
1175
  "calif",
1176
  "calif.",
1177
+ "call",
1178
  "callao",
1179
+ "callback",
1180
  "can",
1181
  "canada",
1182
  "cape",
 
1220
  "confirm",
1221
  "conn",
1222
  "conn.",
1223
+ "connect",
1224
  "consignment",
1225
  "consolidated",
1226
+ "contact",
1227
  "container",
1228
  "container count",
1229
  "container size",
 
1242
  "cross",
1243
  "ct.",
1244
  "cts",
1245
+ "customer",
1246
  "customs",
1247
  "cuz",
1248
  "c\u2019m",
 
1332
  "e.g",
1333
  "e.g.",
1334
  "each",
1335
+ "eak",
1336
+ "eal",
1337
  "eb.",
1338
  "ebr",
1339
  "ec.",
 
1364
  "ers",
1365
  "ery",
1366
  "es-",
1367
+ "escalate",
1368
  "ese",
1369
  "esh",
1370
  "ess",
 
1416
  "gen.",
1417
  "germany",
1418
  "ges",
1419
+ "get",
1420
  "ght",
1421
  "give",
1422
  "glassware",
 
1470
  "how's",
1471
  "how\u2019s",
1472
  "huj",
1473
+ "human",
1474
  "i",
1475
  "i.",
1476
  "i.e",
 
1492
  "if.",
1493
  "igh",
1494
  "ihi",
1495
+ "ike",
1496
  "ila",
1497
  "ile",
1498
  "ill",
 
1516
  "inmun",
1517
  "inn",
1518
  "innsa",
1519
+ "inquiry",
1520
  "insurance",
1521
  "interested",
1522
  "intkd",
 
1528
  "irla",
1529
  "irm",
1530
  "iro",
1531
+ "iry",
1532
  "is",
1533
  "is.",
1534
  "iss",
 
1603
  "lhi",
1604
  "lia",
1605
  "lif",
1606
+ "like",
1607
  "lin",
1608
  "line",
1609
+ "live",
1610
  "lkcmb",
1611
  "ll",
1612
  "ll.",
 
1655
  "measuring",
1656
  "melbourne",
1657
  "men",
1658
+ "mer",
1659
  "mersin",
1660
  "mes",
1661
  "messrs",
 
1819
  "out",
1820
  "ov.",
1821
  "ove",
1822
+ "over",
1823
  "oversized",
1824
  "owe",
1825
  "own",
 
1840
  "per",
1841
  "perishable",
1842
  "permits",
1843
+ "person",
1844
  "personal",
1845
  "ph",
1846
  "ph.d.",
1847
  "pharmaceutical",
1848
+ "phone",
1849
  "pl",
1850
  "planning",
1851
  "ple",
 
1882
  "re",
1883
  "re.",
1884
  "rea",
1885
+ "real",
1886
  "red",
1887
  "ree",
1888
  "refer",
1889
+ "regarding",
1890
  "regulations",
1891
  "rep",
1892
  "rep.",
1893
+ "representative",
1894
  "request",
1895
  "require",
1896
  "required",
 
1932
  "sajed",
1933
  "sample",
1934
  "san",
1935
+ "sap",
1936
  "schedule",
1937
  "sea",
1938
  "search",
 
1981
  "sokhna",
1982
  "solution",
1983
  "some",
1984
+ "someone",
1985
  "somethin",
1986
  "somethin'",
1987
  "something",
1988
  "somethin\u2019",
1989
+ "son",
1990
  "south",
1991
  "space",
1992
  "spain",
1993
+ "speak",
1994
  "special",
1995
  "specialized",
1996
  "sri",
 
2011
  "t.",
2012
  "ta",
2013
  "taiwan",
2014
+ "talk",
2015
  "tanzania",
2016
  "td.",
2017
  "ted",
 
2048
  "town",
2049
  "track",
2050
  "trade",
2051
+ "transfer",
2052
  "transport",
2053
  "transportation",
2054
  "transported",