Update README.md
Browse files
README.md
CHANGED
|
@@ -56,72 +56,72 @@ The model was fine-tuned as a regular BERT-based model for NER task using Huggin
|
|
| 56 |
|
| 57 |
| Label | Examples |
|
| 58 |
|:-----------------------------------------|:---------------------------------------------------------------------------------------------------------|
|
| 59 |
-
|
|
| 60 |
-
|
|
| 61 |
-
|
|
| 62 |
-
|
|
| 63 |
-
|
|
| 64 |
-
|
|
| 65 |
-
|
|
| 66 |
-
|
|
| 67 |
-
|
|
| 68 |
-
|
|
| 69 |
-
|
|
| 70 |
-
|
|
| 71 |
-
|
|
| 72 |
-
|
|
| 73 |
-
|
|
| 74 |
-
|
|
| 75 |
-
|
|
| 76 |
-
|
|
| 77 |
-
|
|
| 78 |
-
|
|
| 79 |
-
|
|
| 80 |
-
|
|
| 81 |
-
|
|
| 82 |
-
|
|
| 83 |
-
|
|
| 84 |
-
|
|
| 85 |
-
|
|
| 86 |
-
|
|
| 87 |
-
|
|
| 88 |
-
|
|
| 89 |
-
|
|
| 90 |
-
|
|
| 91 |
-
|
|
| 92 |
-
|
|
| 93 |
-
|
|
| 94 |
-
|
|
| 95 |
-
|
|
| 96 |
-
|
|
| 97 |
-
|
|
| 98 |
-
|
|
| 99 |
-
|
|
| 100 |
-
|
|
| 101 |
-
|
|
| 102 |
-
|
|
| 103 |
-
|
|
| 104 |
-
|
|
| 105 |
-
|
|
| 106 |
-
|
|
| 107 |
-
|
|
| 108 |
-
|
|
| 109 |
-
|
|
| 110 |
-
|
|
| 111 |
-
|
|
| 112 |
-
|
|
| 113 |
-
|
|
| 114 |
-
|
|
| 115 |
-
|
|
| 116 |
-
|
|
| 117 |
-
|
|
| 118 |
-
|
|
| 119 |
-
|
|
| 120 |
-
|
|
| 121 |
-
|
|
| 122 |
-
|
|
| 123 |
-
|
|
| 124 |
-
|
|
| 125 |
|
| 126 |
## Uses
|
| 127 |
|
|
@@ -139,73 +139,73 @@ The model was fine-tuned as a regular BERT-based model for NER task using Huggin
|
|
| 139 |
)
|
| 140 |
>>> classifier(text)
|
| 141 |
|
| 142 |
-
[{'entity_group': '
|
| 143 |
'score': 0.9424858,
|
| 144 |
'word': ' Washington',
|
| 145 |
'start': 82,
|
| 146 |
'end': 92},
|
| 147 |
-
{'entity_group': '
|
| 148 |
-
'score': 0.
|
| 149 |
'word': 'CNN',
|
| 150 |
'start': 94,
|
| 151 |
'end': 97},
|
| 152 |
-
{'entity_group': '
|
| 153 |
-
'score': 0.
|
| 154 |
'word': ' iPhone',
|
| 155 |
'start': 157,
|
| 156 |
'end': 163},
|
| 157 |
-
{'entity_group': '
|
| 158 |
-
'score': 0.
|
| 159 |
'word': ' Android',
|
| 160 |
'start': 168,
|
| 161 |
'end': 175},
|
| 162 |
-
{'entity_group': '
|
| 163 |
-
'score': 0.
|
| 164 |
'word': ' US',
|
| 165 |
'start': 263,
|
| 166 |
'end': 265},
|
| 167 |
-
{'entity_group': '
|
| 168 |
'score': 0.9712124,
|
| 169 |
'word': ' Apple',
|
| 170 |
'start': 288,
|
| 171 |
'end': 293},
|
| 172 |
-
{'entity_group': '
|
| 173 |
'score': 0.9634242,
|
| 174 |
'word': ' Google',
|
| 175 |
'start': 298,
|
| 176 |
'end': 304},
|
| 177 |
-
{'entity_group': '
|
| 178 |
'score': 0.9451448,
|
| 179 |
'word': ' US',
|
| 180 |
'start': 348,
|
| 181 |
'end': 350},
|
| 182 |
-
{'entity_group': '
|
| 183 |
'score': 0.96848464,
|
| 184 |
'word': ' Apple',
|
| 185 |
'start': 449,
|
| 186 |
'end': 454},
|
| 187 |
-
{'entity_group': '
|
| 188 |
'score': 0.964712,
|
| 189 |
'word': ' Google',
|
| 190 |
'start': 459,
|
| 191 |
'end': 465},
|
| 192 |
-
{'entity_group': '
|
| 193 |
-
'score': 0.
|
| 194 |
'word': ' Oregon',
|
| 195 |
'start': 649,
|
| 196 |
'end': 655},
|
| 197 |
-
{'entity_group': '
|
| 198 |
-
'score': 0.
|
| 199 |
'word': ' Democratic',
|
| 200 |
'start': 656,
|
| 201 |
'end': 666},
|
| 202 |
-
{'entity_group': '
|
| 203 |
'score': 0.902996,
|
| 204 |
'word': ' Ron Wyden',
|
| 205 |
'start': 672,
|
| 206 |
'end': 681},
|
| 207 |
-
{'entity_group': '
|
| 208 |
-
'score': 0.
|
| 209 |
'word': ' Wyden',
|
| 210 |
'start': 704,
|
| 211 |
'end': 709}]
|
|
|
|
| 56 |
|
| 57 |
| Label | Examples |
|
| 58 |
|:-----------------------------------------|:---------------------------------------------------------------------------------------------------------|
|
| 59 |
+
| art_broadcastprogram | "Corazones", "The Gale Storm Show : Oh , Susanna", "Street Cents" |
|
| 60 |
+
| art_film | "Shawshank Redemption", "L'Atlantide", "Bosch" |
|
| 61 |
+
| art_music | "Hollywood Studio Symphony", "Atkinson , Danko and Ford ( with Brockie and Hilton )", "Champion Lover" |
|
| 62 |
+
| art_other | "The Today Show", "Venus de Milo", "Aphrodite of Milos" |
|
| 63 |
+
| art_painting | "Production/Reproduction", "Touit", "Cofiwch Dryweryn" |
|
| 64 |
+
| art_writtenart | "The Seven Year Itch", "Imelda de ' Lambertazzi", "Time" |
|
| 65 |
+
| building_airport | "Sheremetyevo International Airport", "Newark Liberty International Airport", "Luton Airport" |
|
| 66 |
+
| building_hospital | "Yeungnam University Hospital", "Hokkaido University Hospital", "Memorial Sloan-Kettering Cancer Center" |
|
| 67 |
+
| building_hotel | "The Standard Hotel", "Flamingo Hotel", "Radisson Blu Sea Plaza Hotel" |
|
| 68 |
+
| building_library | "British Library", "Bayerische Staatsbibliothek", "Berlin State Library" |
|
| 69 |
+
| building_other | "Henry Ford Museum", "Alpha Recording Studios", "Communiplex" |
|
| 70 |
+
| building_restaurant | "Carnegie Deli", "Fatburger", "Trumbull" |
|
| 71 |
+
| building_sportsfacility | "Boston Garden", "Sports Center", "Glenn Warner Soccer Facility" |
|
| 72 |
+
| building_theater | "Sanders Theatre", "National Paris Opera", "Pittsburgh Civic Light Opera" |
|
| 73 |
+
| event_attack/battle/war/militaryconflict | "Easter Offensive", "Jurist", "Vietnam War" |
|
| 74 |
+
| event_disaster | "the 1912 North Mount Lyell Disaster", "1990s North Korean famine", "1693 Sicily earthquake" |
|
| 75 |
+
| event_election | "Elections to the European Parliament", "March 1898 elections", "1982 Mitcham and Morden by-election" |
|
| 76 |
+
| event_other | "Union for a Popular Movement", "Masaryk Democratic Movement", "Eastwood Scoring Stage" |
|
| 77 |
+
| event_protest | "Iranian Constitutional Revolution", "French Revolution", "Russian Revolution" |
|
| 78 |
+
| event_sportsevent | "World Cup", "National Champions", "Stanley Cup" |
|
| 79 |
+
| location_GPE | "Croatian", "Mediterranean Basin", "the Republic of Croatia" |
|
| 80 |
+
| location_bodiesofwater | "Arthur Kill", "Atatürk Dam Lake", "Norfolk coast" |
|
| 81 |
+
| location_island | "new Samsat district", "Laccadives", "Staten Island" |
|
| 82 |
+
| location_mountain | "Salamander Glacier", "Miteirya Ridge", "Ruweisat Ridge" |
|
| 83 |
+
| location_other | "Victoria line", "Northern City Line", "Cartuther" |
|
| 84 |
+
| location_park | "Painted Desert Community Complex Historic District", "Gramercy Park", "Shenandoah National Park" |
|
| 85 |
+
| location_road/railway/highway/transit | "NJT", "Newark-Elizabeth Rail Link", "Friern Barnet Road" |
|
| 86 |
+
| organization_company | "Texas Chicken", "Dixy Chicken", "Church 's Chicken" |
|
| 87 |
+
| organization_education | "MIT", "Belfast Royal Academy and the Ulster College of Physical Education", "Barnard College" |
|
| 88 |
+
| organization_government/governmentagency | "Congregazione dei Nobili", "Diet", "Supreme Court" |
|
| 89 |
+
| organization_media/newspaper | "Clash", "Al Jazeera", "TimeOut Melbourne" |
|
| 90 |
+
| organization_other | "Defence Sector C", "IAEA", "4th Army" |
|
| 91 |
+
| organization_politicalparty | "Al Wafa ' Islamic", "Shimpotō", "Kenseitō" |
|
| 92 |
+
| organization_religion | "UPCUSA", "Christian", "Jewish" |
|
| 93 |
+
| organization_showorganization | "Lizzy", "Bochumer Symphoniker", "Mr. Mister" |
|
| 94 |
+
| organization_sportsleague | "China League One", "NHL", "First Division" |
|
| 95 |
+
| organization_sportsteam | "Arsenal", "Luc Alphand Aventures", "Tottenham" |
|
| 96 |
+
| other_astronomything | "Algol", "`` Caput Larvae ''", "Zodiac" |
|
| 97 |
+
| other_award | "Order of the Republic of Guinea and Nigeria", "Grand Commander of the Order of the Niger", "GCON" |
|
| 98 |
+
| other_biologything | "N-terminal lipid", "Amphiphysin", "BAR" |
|
| 99 |
+
| other_chemicalthing | "uranium", "carbon dioxide", "sulfur" |
|
| 100 |
+
| other_currency | "$", "lac crore", "Travancore Rupee" |
|
| 101 |
+
| other_disease | "bladder cancer", "French Dysentery Epidemic of 1779", "hypothyroidism" |
|
| 102 |
+
| other_educationaldegree | "BSc ( Hons ) in physics", "Bachelor", "Master" |
|
| 103 |
+
| other_god | "Raijin", "Fujin", "El" |
|
| 104 |
+
| other_language | "Breton-speaking", "Latin", "English" |
|
| 105 |
+
| other_law | "Leahy–Smith America Invents Act ( AIA", "United States Freedom Support Act", "Thirty Years ' Peace" |
|
| 106 |
+
| other_livingthing | "monkeys", "patchouli", "insects" |
|
| 107 |
+
| other_medical | "amitriptyline", "Pediatrics", "pediatrician" |
|
| 108 |
+
| person_actor | "Tchéky Karyo", "Edmund Payne", "Ellaline Terriss" |
|
| 109 |
+
| person_artist/author | "Hicks", "Gaetano Donizett", "George Axelrod" |
|
| 110 |
+
| person_athlete | "Tozawa", "Neville", "Jaguar" |
|
| 111 |
+
| person_director | "Richard Quine", "Bob Swaim", "Frank Darabont" |
|
| 112 |
+
| person_other | "Campbell", "Holden", "Richard Benson" |
|
| 113 |
+
| person_politician | "William", "Rivière", "Emeric" |
|
| 114 |
+
| person_scholar | "Wurdack", "Stalmine", "Stedman" |
|
| 115 |
+
| person_soldier | "Joachim Ziegler", "Helmuth Weidling", "Krukenberg" |
|
| 116 |
+
| product_airplane | "Spey-equipped FGR.2s", "EC135T2 CPDS", "Luton" |
|
| 117 |
+
| product_car | "Phantom", "100EX", "Corvettes - GT1 C6R" |
|
| 118 |
+
| product_food | "red grape", "yakiniku", "V. labrusca" |
|
| 119 |
+
| product_game | "Hardcore RPG", "Splinter Cell", "Airforce Delta" |
|
| 120 |
+
| product_other | "X11", "PDP-1", "Fairbottom Bobs" |
|
| 121 |
+
| product_ship | "Essex", "Congress", "HMS `` Chinkara ''" |
|
| 122 |
+
| product_software | "AmiPDF", "Wikipedia", "Apdf" |
|
| 123 |
+
| product_train | "55022", "Royal Scots Grey", "High Speed Trains" |
|
| 124 |
+
| product_weapon | "AR-15 's", "ZU-23-2MR Wróbel II", "ZU-23-2M Wróbel" |
|
| 125 |
|
| 126 |
## Uses
|
| 127 |
|
|
|
|
| 139 |
)
|
| 140 |
>>> classifier(text)
|
| 141 |
|
| 142 |
+
[{'entity_group': 'location_GPE',
|
| 143 |
'score': 0.9424858,
|
| 144 |
'word': ' Washington',
|
| 145 |
'start': 82,
|
| 146 |
'end': 92},
|
| 147 |
+
{'entity_group': 'organization_media/newspaper',
|
| 148 |
+
'score': 0.83160853,
|
| 149 |
'word': 'CNN',
|
| 150 |
'start': 94,
|
| 151 |
'end': 97},
|
| 152 |
+
{'entity_group': 'product_other',
|
| 153 |
+
'score': 0.80409557,
|
| 154 |
'word': ' iPhone',
|
| 155 |
'start': 157,
|
| 156 |
'end': 163},
|
| 157 |
+
{'entity_group': 'product_other',
|
| 158 |
+
'score': 0.7345743,
|
| 159 |
'word': ' Android',
|
| 160 |
'start': 168,
|
| 161 |
'end': 175},
|
| 162 |
+
{'entity_group': 'location_GPE',
|
| 163 |
+
'score': 0.70951134,
|
| 164 |
'word': ' US',
|
| 165 |
'start': 263,
|
| 166 |
'end': 265},
|
| 167 |
+
{'entity_group': 'organization_company',
|
| 168 |
'score': 0.9712124,
|
| 169 |
'word': ' Apple',
|
| 170 |
'start': 288,
|
| 171 |
'end': 293},
|
| 172 |
+
{'entity_group': 'organization_company',
|
| 173 |
'score': 0.9634242,
|
| 174 |
'word': ' Google',
|
| 175 |
'start': 298,
|
| 176 |
'end': 304},
|
| 177 |
+
{'entity_group': 'location_GPE',
|
| 178 |
'score': 0.9451448,
|
| 179 |
'word': ' US',
|
| 180 |
'start': 348,
|
| 181 |
'end': 350},
|
| 182 |
+
{'entity_group': 'organization_company',
|
| 183 |
'score': 0.96848464,
|
| 184 |
'word': ' Apple',
|
| 185 |
'start': 449,
|
| 186 |
'end': 454},
|
| 187 |
+
{'entity_group': 'organization_company',
|
| 188 |
'score': 0.964712,
|
| 189 |
'word': ' Google',
|
| 190 |
'start': 459,
|
| 191 |
'end': 465},
|
| 192 |
+
{'entity_group': 'location_GPE',
|
| 193 |
+
'score': 0.7764447,
|
| 194 |
'word': ' Oregon',
|
| 195 |
'start': 649,
|
| 196 |
'end': 655},
|
| 197 |
+
{'entity_group': 'organization_politicalparty',
|
| 198 |
+
'score': 0.7019166,
|
| 199 |
'word': ' Democratic',
|
| 200 |
'start': 656,
|
| 201 |
'end': 666},
|
| 202 |
+
{'entity_group': 'person_politician',
|
| 203 |
'score': 0.902996,
|
| 204 |
'word': ' Ron Wyden',
|
| 205 |
'start': 672,
|
| 206 |
'end': 681},
|
| 207 |
+
{'entity_group': 'person_politician',
|
| 208 |
+
'score': 0.82849455,
|
| 209 |
'word': ' Wyden',
|
| 210 |
'start': 704,
|
| 211 |
'end': 709}]
|