CyberPeace-Institute/Cybersecurity-Knowledge-Graph-Extraction
4
1{2 "cells": [3 {4 "cell_type": "code",5 "execution_count": 1,6 "metadata": {},7 "outputs": [8 {9 "name": "stderr",10 "output_type": "stream",11 "text": [12 "A new version of the following files was downloaded from https://huggingface.co/CyberPeace-Institute/Cybersecurity-Knowledge-Graph:\n",13 "- configuration.py\n",14 ". Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.\n"15 ]16 },17 {18 "data": {19 "application/vnd.jupyter.widget-view+json": {20 "model_id": "047d95084e98403589b108942daf1a0c",21 "version_major": 2,22 "version_minor": 023 },24 "text/plain": [25 "Downloading (…)esolve/main/model.py: 0%| | 0.00/6.66k [00:00<?, ?B/s]"26 ]27 },28 "metadata": {},29 "output_type": "display_data"30 },31 {32 "data": {33 "application/vnd.jupyter.widget-view+json": {34 "model_id": "840315351a8e489d9e65c4285a9511b2",35 "version_major": 2,36 "version_minor": 037 },38 "text/plain": [39 "Downloading (…)event_arg_predict.py: 0%| | 0.00/12.8k [00:00<?, ?B/s]"40 ]41 },42 "metadata": {},43 "output_type": "display_data"44 },45 {46 "data": {47 "application/vnd.jupyter.widget-view+json": {48 "model_id": "e211aa84be44465396acb1e1e1b5b683",49 "version_major": 2,50 "version_minor": 051 },52 "text/plain": [53 "Downloading (…)/args_model_utils.py: 0%| | 0.00/11.2k [00:00<?, ?B/s]"54 ]55 },56 "metadata": {},57 "output_type": "display_data"58 },59 {60 "name": "stderr",61 "output_type": "stream",62 "text": [63 "A new version of the following files was downloaded from https://huggingface.co/CyberPeace-Institute/Cybersecurity-Knowledge-Graph:\n",64 "- args_model_utils.py\n",65 ". Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.\n"66 ]67 },68 {69 "data": {70 "application/vnd.jupyter.widget-view+json": {71 "model_id": "b4c2fe2b94884fa5bc8e245a874ad21a",72 "version_major": 2,73 "version_minor": 074 },75 "text/plain": [76 "Downloading (…)nt_nugget_predict.py: 0%| | 0.00/10.7k [00:00<?, ?B/s]"77 ]78 },79 "metadata": {},80 "output_type": "display_data"81 },82 {83 "data": {84 "application/vnd.jupyter.widget-view+json": {85 "model_id": "d192dbc95c6749b6a9c6a5c984c646fd",86 "version_major": 2,87 "version_minor": 088 },89 "text/plain": [90 "Downloading (…)ugget_model_utils.py: 0%| | 0.00/6.59k [00:00<?, ?B/s]"91 ]92 },93 "metadata": {},94 "output_type": "display_data"95 },96 {97 "name": "stderr",98 "output_type": "stream",99 "text": [100 "A new version of the following files was downloaded from https://huggingface.co/CyberPeace-Institute/Cybersecurity-Knowledge-Graph:\n",101 "- nugget_model_utils.py\n",102 ". Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.\n"103 ]104 },105 {106 "data": {107 "application/vnd.jupyter.widget-view+json": {108 "model_id": "0ca6f6c3195c4708bb1834a0c876e893",109 "version_major": 2,110 "version_minor": 0111 },112 "text/plain": [113 "Downloading (…)esolve/main/utils.py: 0%| | 0.00/7.05k [00:00<?, ?B/s]"114 ]115 },116 "metadata": {},117 "output_type": "display_data"118 },119 {120 "name": "stderr",121 "output_type": "stream",122 "text": [123 "A new version of the following files was downloaded from https://huggingface.co/CyberPeace-Institute/Cybersecurity-Knowledge-Graph:\n",124 "- utils.py\n",125 ". Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.\n",126 "A new version of the following files was downloaded from https://huggingface.co/CyberPeace-Institute/Cybersecurity-Knowledge-Graph:\n",127 "- event_nugget_predict.py\n",128 "- nugget_model_utils.py\n",129 "- utils.py\n",130 ". Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.\n",131 "A new version of the following files was downloaded from https://huggingface.co/CyberPeace-Institute/Cybersecurity-Knowledge-Graph:\n",132 "- event_arg_predict.py\n",133 "- args_model_utils.py\n",134 "- event_nugget_predict.py\n",135 ". Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.\n"136 ]137 },138 {139 "data": {140 "application/vnd.jupyter.widget-view+json": {141 "model_id": "2776f9469d414ed6aaa5b594fae0c6a8",142 "version_major": 2,143 "version_minor": 0144 },145 "text/plain": [146 "Downloading (…)nt_realis_predict.py: 0%| | 0.00/11.5k [00:00<?, ?B/s]"147 ]148 },149 "metadata": {},150 "output_type": "display_data"151 },152 {153 "data": {154 "application/vnd.jupyter.widget-view+json": {155 "model_id": "22265c1ceb7d4611a5118fbde096bc1d",156 "version_major": 2,157 "version_minor": 0158 },159 "text/plain": [160 "Downloading (…)ealis_model_utils.py: 0%| | 0.00/7.09k [00:00<?, ?B/s]"161 ]162 },163 "metadata": {},164 "output_type": "display_data"165 },166 {167 "name": "stderr",168 "output_type": "stream",169 "text": [170 "A new version of the following files was downloaded from https://huggingface.co/CyberPeace-Institute/Cybersecurity-Knowledge-Graph:\n",171 "- realis_model_utils.py\n",172 ". Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.\n",173 "A new version of the following files was downloaded from https://huggingface.co/CyberPeace-Institute/Cybersecurity-Knowledge-Graph:\n",174 "- event_realis_predict.py\n",175 "- realis_model_utils.py\n",176 ". Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.\n",177 "A new version of the following files was downloaded from https://huggingface.co/CyberPeace-Institute/Cybersecurity-Knowledge-Graph:\n",178 "- model.py\n",179 "- event_arg_predict.py\n",180 "- event_realis_predict.py\n",181 ". Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.\n",182 "Some weights of RobertaModel were not initialized from the model checkpoint at ehsanaghaei/SecureBERT and are newly initialized: ['roberta.pooler.dense.weight', 'roberta.pooler.dense.bias']\n",183 "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n",184 "Some weights of RobertaModel were not initialized from the model checkpoint at ehsanaghaei/SecureBERT and are newly initialized: ['roberta.pooler.dense.weight', 'roberta.pooler.dense.bias']\n",185 "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n",186 "Some weights of RobertaModel were not initialized from the model checkpoint at ehsanaghaei/SecureBERT and are newly initialized: ['roberta.pooler.dense.weight', 'roberta.pooler.dense.bias']\n",187 "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"188 ]189 }190 ],191 "source": [192 "# Load model directly\n",193 "from transformers import AutoModelForTokenClassification\n",194 "model = AutoModelForTokenClassification.from_pretrained(\"CyberPeace-Institute/Cybersecurity-Knowledge-Graph\", trust_remote_code=True)"195 ]196 },197 {198 "cell_type": "code",199 "execution_count": 2,200 "metadata": {},201 "outputs": [202 {203 "data": {204 "application/vnd.jupyter.widget-view+json": {205 "model_id": "e3e5818a4d6b4ba99243603a068622d0",206 "version_major": 2,207 "version_minor": 0208 },209 "text/plain": [210 "Map: 0%| | 0/1 [00:00<?, ? examples/s]"211 ]212 },213 "metadata": {},214 "output_type": "display_data"215 },216 {217 "data": {218 "application/vnd.jupyter.widget-view+json": {219 "model_id": "f3a24eb19f414ae3ad974b1461fc3e64",220 "version_major": 2,221 "version_minor": 0222 },223 "text/plain": [224 "Map: 0%| | 0/1 [00:00<?, ? examples/s]"225 ]226 },227 "metadata": {},228 "output_type": "display_data"229 },230 {231 "data": {232 "application/vnd.jupyter.widget-view+json": {233 "model_id": "3c3dd376f5614f739e5c0780af8b3a9b",234 "version_major": 2,235 "version_minor": 0236 },237 "text/plain": [238 "Map: 0%| | 0/1 [00:00<?, ? examples/s]"239 ]240 },241 "metadata": {},242 "output_type": "display_data"243 },244 {245 "data": {246 "application/vnd.jupyter.widget-view+json": {247 "model_id": "20c9cd31ea854bb58208249c18840e14",248 "version_major": 2,249 "version_minor": 0250 },251 "text/plain": [252 "Map: 0%| | 0/1 [00:00<?, ? examples/s]"253 ]254 },255 "metadata": {},256 "output_type": "display_data"257 },258 {259 "data": {260 "application/vnd.jupyter.widget-view+json": {261 "model_id": "a668052410cf41968f97ebdcf187debc",262 "version_major": 2,263 "version_minor": 0264 },265 "text/plain": [266 "Map: 0%| | 0/1 [00:00<?, ? examples/s]"267 ]268 },269 "metadata": {},270 "output_type": "display_data"271 },272 {273 "data": {274 "text/plain": [275 "[{'id': 1437, 'token': ' ', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",276 " {'id': 50118, 'token': '\\n', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",277 " {'id': 287, 'token': ' As', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",278 " {'id': 9, 'token': ' of', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",279 " {'id': 502, 'token': ' June', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",280 " {'id': 336, 'token': ' 2016', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",281 " {'id': 2156, 'token': ',', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",282 " {'id': 55, 'token': ' more', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",283 " {'id': 87, 'token': ' than', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",284 " {'id': 3982, 'token': ' 150', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",285 " {'id': 153,\n",286 " 'token': ' million',\n",287 " 'nugget': 'O',\n",288 " 'argument': 'O',\n",289 " 'realis': 'O'},\n",290 " {'id': 2171,\n",291 " 'token': ' active',\n",292 " 'nugget': 'O',\n",293 " 'argument': 'O',\n",294 " 'realis': 'O'},\n",295 " {'id': 1434,\n",296 " 'token': ' users',\n",297 " 'nugget': 'O',\n",298 " 'argument': 'O',\n",299 " 'realis': 'O'},\n",300 " {'id': 10754,\n",301 " 'token': ' interact',\n",302 " 'nugget': 'O',\n",303 " 'argument': 'O',\n",304 " 'realis': 'O'},\n",305 " {'id': 19, 'token': ' with', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",306 " {'id': 65, 'token': ' one', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",307 " {'id': 277,\n",308 " 'token': ' another',\n",309 " 'nugget': 'O',\n",310 " 'argument': 'O',\n",311 " 'realis': 'O'},\n",312 " {'id': 1230,\n",313 " 'token': ' daily',\n",314 " 'nugget': 'O',\n",315 " 'argument': 'O',\n",316 " 'realis': 'O'},\n",317 " {'id': 1241, 'token': ' via', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",318 " {'id': 11477,\n",319 " 'token': ' Snapchat',\n",320 " 'nugget': 'O',\n",321 " 'argument': 'O',\n",322 " 'realis': 'O'},\n",323 " {'id': 479, 'token': '.', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",324 " {'id': 5763,\n",325 " 'token': ' Others',\n",326 " 'nugget': 'O',\n",327 " 'argument': 'O',\n",328 " 'realis': 'O'},\n",329 " {'id': 32, 'token': ' are', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",330 " {'id': 4777,\n",331 " 'token': ' drawn',\n",332 " 'nugget': 'O',\n",333 " 'argument': 'O',\n",334 " 'realis': 'O'},\n",335 " {'id': 30, 'token': ' by', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",336 " {'id': 5, 'token': ' the', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",337 " {'id': 544,\n",338 " 'token': ' service',\n",339 " 'nugget': 'O',\n",340 " 'argument': 'O',\n",341 " 'realis': 'O'},\n",342 " {'id': 128, 'token': \" '\", 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",343 " {'id': 29, 'token': 's', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",344 " {'id': 55, 'token': ' more', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",345 " {'id': 485,\n",346 " 'token': ' recent',\n",347 " 'nugget': 'O',\n",348 " 'argument': 'O',\n",349 " 'realis': 'O'},\n",350 " {'id': 1575,\n",351 " 'token': ' features',\n",352 " 'nugget': 'O',\n",353 " 'argument': 'O',\n",354 " 'realis': 'O'},\n",355 " {'id': 479, 'token': '.', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",356 " {'id': 2246,\n",357 " 'token': ' Those',\n",358 " 'nugget': 'O',\n",359 " 'argument': 'O',\n",360 " 'realis': 'O'},\n",361 " {'id': 680,\n",362 " 'token': ' include',\n",363 " 'nugget': 'O',\n",364 " 'argument': 'O',\n",365 " 'realis': 'O'},\n",366 " {'id': 14100,\n",367 " 'token': ' Snap',\n",368 " 'nugget': 'O',\n",369 " 'argument': 'O',\n",370 " 'realis': 'O'},\n",371 " {'id': 20122, 'token': 'cash', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",372 " {'id': 2156, 'token': ',', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",373 " {'id': 10, 'token': ' a', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",374 " {'id': 5448,\n",375 " 'token': ' method',\n",376 " 'nugget': 'O',\n",377 " 'argument': 'O',\n",378 " 'realis': 'O'},\n",379 " {'id': 2942,\n",380 " 'token': ' introduced',\n",381 " 'nugget': 'O',\n",382 " 'argument': 'O',\n",383 " 'realis': 'O'},\n",384 " {'id': 13, 'token': ' for', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",385 " {'id': 1434,\n",386 " 'token': ' users',\n",387 " 'nugget': 'O',\n",388 " 'argument': 'O',\n",389 " 'realis': 'O'},\n",390 " {'id': 7, 'token': ' to', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",391 " {'id': 2142, 'token': ' send', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",392 " {'id': 1830,\n",393 " 'token': ' mobile',\n",394 " 'nugget': 'O',\n",395 " 'argument': 'O',\n",396 " 'realis': 'O'},\n",397 " {'id': 3081,\n",398 " 'token': ' payments',\n",399 " 'nugget': 'O',\n",400 " 'argument': 'O',\n",401 " 'realis': 'O'},\n",402 " {'id': 7, 'token': ' to', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",403 " {'id': 49, 'token': ' their', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",404 " {'id': 964,\n",405 " 'token': ' friends',\n",406 " 'nugget': 'O',\n",407 " 'argument': 'O',\n",408 " 'realis': 'O'},\n",409 " {'id': 479, 'token': '.', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",410 " {'id': 1437, 'token': ' ', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",411 " {'id': 50118, 'token': '\\n', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",412 " {'id': 6211,\n",413 " 'token': ' Given',\n",414 " 'nugget': 'O',\n",415 " 'argument': 'O',\n",416 " 'realis': 'O'},\n",417 " {'id': 5, 'token': ' the', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",418 " {'id': 1553, 'token': ' app', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",419 " {'id': 128, 'token': \" '\", 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",420 " {'id': 29, 'token': 's', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",421 " {'id': 7347,\n",422 " 'token': ' popularity',\n",423 " 'nugget': 'O',\n",424 " 'argument': 'O',\n",425 " 'realis': 'O'},\n",426 " {'id': 2156, 'token': ',', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",427 " {'id': 24, 'token': ' it', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",428 " {'id': 128, 'token': \" '\", 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",429 " {'id': 29, 'token': 's', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",430 " {'id': 117, 'token': ' no', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",431 " {'id': 5170,\n",432 " 'token': ' wonder',\n",433 " 'nugget': 'O',\n",434 " 'argument': 'O',\n",435 " 'realis': 'O'},\n",436 " {'id': 804,\n",437 " 'token': ' online',\n",438 " 'nugget': 'O',\n",439 " 'argument': 'O',\n",440 " 'realis': 'O'},\n",441 " {'id': 9177,\n",442 " 'token': ' criminals',\n",443 " 'nugget': 'O',\n",444 " 'argument': 'O',\n",445 " 'realis': 'O'},\n",446 " {'id': 33, 'token': ' have', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",447 " {'id': 278, 'token': ' set', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",448 " {'id': 49, 'token': ' their', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",449 " {'id': 579, 'token': ' s', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",450 " {'id': 6183, 'token': 'ights', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",451 " {'id': 15, 'token': ' on', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",452 " {'id': 11597,\n",453 " 'token': ' hacking',\n",454 " 'nugget': 'O',\n",455 " 'argument': 'O',\n",456 " 'realis': 'O'},\n",457 " {'id': 1434,\n",458 " 'token': ' users',\n",459 " 'nugget': 'O',\n",460 " 'argument': 'O',\n",461 " 'realis': 'O'},\n",462 " {'id': 128, 'token': \" '\", 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",463 " {'id': 11477,\n",464 " 'token': ' Snapchat',\n",465 " 'nugget': 'O',\n",466 " 'argument': 'B-PII',\n",467 " 'realis': 'O'},\n",468 " {'id': 2349,\n",469 " 'token': ' accounts',\n",470 " 'nugget': 'O',\n",471 " 'argument': 'I-PII',\n",472 " 'realis': 'O'},\n",473 " {'id': 479, 'token': '.', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",474 " {'id': 286, 'token': ' For', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",475 " {'id': 4327,\n",476 " 'token': ' instance',\n",477 " 'nugget': 'O',\n",478 " 'argument': 'O',\n",479 " 'realis': 'O'},\n",480 " {'id': 2156, 'token': ',', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",481 " {'id': 124, 'token': ' back', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",482 " {'id': 11, 'token': ' in', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",483 " {'id': 628,\n",484 " 'token': ' late',\n",485 " 'nugget': 'O',\n",486 " 'argument': 'B-Time',\n",487 " 'realis': 'O'},\n",488 " {'id': 1014,\n",489 " 'token': ' 2013',\n",490 " 'nugget': 'O',\n",491 " 'argument': 'I-Time',\n",492 " 'realis': 'O'},\n",493 " {'id': 2156, 'token': ',', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",494 " {'id': 10,\n",495 " 'token': ' a',\n",496 " 'nugget': 'O',\n",497 " 'argument': 'B-Person',\n",498 " 'realis': 'O'},\n",499 " {'id': 333,\n",500 " 'token': ' group',\n",501 " 'nugget': 'O',\n",502 " 'argument': 'I-Person',\n",503 " 'realis': 'O'},\n",504 " {'id': 9,\n",505 " 'token': ' of',\n",506 " 'nugget': 'O',\n",507 " 'argument': 'I-Person',\n",508 " 'realis': 'O'},\n",509 " {'id': 11344,\n",510 " 'token': ' hackers',\n",511 " 'nugget': 'O',\n",512 " 'argument': 'I-Person',\n",513 " 'realis': 'O'},\n",514 " {'id': 1027,\n",515 " 'token': ' published',\n",516 " 'nugget': 'B-Databreach',\n",517 " 'argument': 'O',\n",518 " 'realis': 'Actual'},\n",519 " {'id': 10, 'token': ' a', 'nugget': 'O', 'argument': 'B-Data', 'realis': 'O'},\n",520 " {'id': 8503,\n",521 " 'token': ' database',\n",522 " 'nugget': 'O',\n",523 " 'argument': 'I-Data',\n",524 " 'realis': 'O'},\n",525 " {'id': 8200,\n",526 " 'token': ' containing',\n",527 " 'nugget': 'O',\n",528 " 'argument': 'O',\n",529 " 'realis': 'O'},\n",530 " {'id': 5, 'token': ' the', 'nugget': 'O', 'argument': 'B-PII', 'realis': 'O'},\n",531 " {'id': 32200,\n",532 " 'token': ' usernames',\n",533 " 'nugget': 'O',\n",534 " 'argument': 'I-PII',\n",535 " 'realis': 'O'},\n",536 " {'id': 8, 'token': ' and', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",537 " {'id': 1028,\n",538 " 'token': ' phone',\n",539 " 'nugget': 'O',\n",540 " 'argument': 'B-PII',\n",541 " 'realis': 'O'},\n",542 " {'id': 1530,\n",543 " 'token': ' numbers',\n",544 " 'nugget': 'O',\n",545 " 'argument': 'I-PII',\n",546 " 'realis': 'O'},\n",547 " {'id': 9, 'token': ' of', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",548 " {'id': 2219,\n",549 " 'token': ' approximately',\n",550 " 'nugget': 'O',\n",551 " 'argument': 'O',\n",552 " 'realis': 'O'},\n",553 " {'id': 204, 'token': ' 4', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",554 " {'id': 4, 'token': '.', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",555 " {'id': 401, 'token': '6', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",556 " {'id': 153,\n",557 " 'token': ' million',\n",558 " 'nugget': 'O',\n",559 " 'argument': 'O',\n",560 " 'realis': 'O'},\n",561 " {'id': 11477,\n",562 " 'token': ' Snapchat',\n",563 " 'nugget': 'O',\n",564 " 'argument': 'B-Person',\n",565 " 'realis': 'O'},\n",566 " {'id': 1434,\n",567 " 'token': ' users',\n",568 " 'nugget': 'O',\n",569 " 'argument': 'I-Person',\n",570 " 'realis': 'O'},\n",571 " {'id': 479, 'token': '.', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",572 " {'id': 1437, 'token': ' ', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",573 " {'id': 50118, 'token': '\\n', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",574 " {'id': 234, 'token': ' N', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",575 " {'id': 4550, 'token': 'ef', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",576 " {'id': 38313,\n",577 " 'token': 'arious',\n",578 " 'nugget': 'O',\n",579 " 'argument': 'O',\n",580 " 'realis': 'O'},\n",581 " {'id': 2172,\n",582 " 'token': ' individuals',\n",583 " 'nugget': 'O',\n",584 " 'argument': 'O',\n",585 " 'realis': 'O'},\n",586 " {'id': 115, 'token': ' could', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",587 " {'id': 33, 'token': ' have', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",588 " {'id': 341, 'token': ' used', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",589 " {'id': 14, 'token': ' that', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",590 " {'id': 335,\n",591 " 'token': ' information',\n",592 " 'nugget': 'O',\n",593 " 'argument': 'O',\n",594 " 'realis': 'O'},\n",595 " {'id': 7, 'token': ' to', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",596 " {'id': 4392,\n",597 " 'token': ' profile',\n",598 " 'nugget': 'O',\n",599 " 'argument': 'O',\n",600 " 'realis': 'O'},\n",601 " {'id': 3247,\n",602 " 'token': ' targets',\n",603 " 'nugget': 'O',\n",604 " 'argument': 'O',\n",605 " 'realis': 'O'},\n",606 " {'id': 420,\n",607 " 'token': ' across',\n",608 " 'nugget': 'O',\n",609 " 'argument': 'O',\n",610 " 'realis': 'O'},\n",611 " {'id': 1533,\n",612 " 'token': ' multiple',\n",613 " 'nugget': 'O',\n",614 " 'argument': 'O',\n",615 " 'realis': 'O'},\n",616 " {'id': 3748, 'token': ' web', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",617 " {'id': 2349,\n",618 " 'token': ' accounts',\n",619 " 'nugget': 'O',\n",620 " 'argument': 'O',\n",621 " 'realis': 'O'},\n",622 " {'id': 479, 'token': '.', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",623 " {'id': 166, 'token': ' We', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",624 " {'id': 67, 'token': ' also', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",625 " {'id': 6056, 'token': ' ca', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",626 " {'id': 295, 'token': ' n', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",627 " {'id': 75, 'token': \"'t\", 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",628 " {'id': 4309,\n",629 " 'token': ' forget',\n",630 " 'nugget': 'O',\n",631 " 'argument': 'O',\n",632 " 'realis': 'O'},\n",633 " {'id': 59, 'token': ' about', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",634 " {'id': 5, 'token': ' the', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",635 " {'id': 573,\n",636 " 'token': ' security',\n",637 " 'nugget': 'O',\n",638 " 'argument': 'O',\n",639 " 'realis': 'O'},\n",640 " {'id': 1160,\n",641 " 'token': ' incident',\n",642 " 'nugget': 'O',\n",643 " 'argument': 'O',\n",644 " 'realis': 'O'},\n",645 " {'id': 14, 'token': ' that', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",646 " {'id': 2756,\n",647 " 'token': ' occurred',\n",648 " 'nugget': 'O',\n",649 " 'argument': 'O',\n",650 " 'realis': 'O'},\n",651 " {'id': 124, 'token': ' back', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",652 " {'id': 11, 'token': ' in', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",653 " {'id': 902,\n",654 " 'token': ' February',\n",655 " 'nugget': 'O',\n",656 " 'argument': 'B-Time',\n",657 " 'realis': 'O'},\n",658 " {'id': 336,\n",659 " 'token': ' 2016',\n",660 " 'nugget': 'O',\n",661 " 'argument': 'I-Time',\n",662 " 'realis': 'O'},\n",663 " {'id': 479, 'token': '.', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",664 " {'id': 96, 'token': ' In', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",665 " {'id': 14,\n",666 " 'token': ' that',\n",667 " 'nugget': 'B-Phishing',\n",668 " 'argument': 'O',\n",669 " 'realis': 'O'},\n",670 " {'id': 908,\n",671 " 'token': ' attack',\n",672 " 'nugget': 'I-Phishing',\n",673 " 'argument': 'O',\n",674 " 'realis': 'Actual'},\n",675 " {'id': 2156, 'token': ',', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",676 " {'id': 951,\n",677 " 'token': ' someone',\n",678 " 'nugget': 'O',\n",679 " 'argument': 'B-Person',\n",680 " 'realis': 'O'},\n",681 " {'id': 7444,\n",682 " 'token': ' posed',\n",683 " 'nugget': 'B-Phishing',\n",684 " 'argument': 'O',\n",685 " 'realis': 'Actual'},\n",686 " {'id': 25,\n",687 " 'token': ' as',\n",688 " 'nugget': 'I-Phishing',\n",689 " 'argument': 'O',\n",690 " 'realis': 'Actual'},\n",691 " {'id': 5, 'token': ' the', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",692 " {'id': 138,\n",693 " 'token': ' company',\n",694 " 'nugget': 'O',\n",695 " 'argument': 'B-Organization',\n",696 " 'realis': 'O'},\n",697 " {'id': 128, 'token': \" '\", 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",698 " {'id': 29, 'token': 's', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",699 " {'id': 1324,\n",700 " 'token': ' CEO',\n",701 " 'nugget': 'O',\n",702 " 'argument': 'B-Person',\n",703 " 'realis': 'O'},\n",704 " {'id': 8, 'token': ' and', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",705 " {'id': 7013,\n",706 " 'token': ' convinced',\n",707 " 'nugget': 'B-Phishing',\n",708 " 'argument': 'O',\n",709 " 'realis': 'Actual'},\n",710 " {'id': 10, 'token': ' a', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",711 " {'id': 11477,\n",712 " 'token': ' Snapchat',\n",713 " 'nugget': 'O',\n",714 " 'argument': 'B-Person',\n",715 " 'realis': 'O'},\n",716 " {'id': 3200,\n",717 " 'token': ' employee',\n",718 " 'nugget': 'O',\n",719 " 'argument': 'I-Person',\n",720 " 'realis': 'O'},\n",721 " {'id': 7, 'token': ' to', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",722 " {'id': 2142,\n",723 " 'token': ' send',\n",724 " 'nugget': 'O',\n",725 " 'argument': 'B-Purpose',\n",726 " 'realis': 'O'},\n",727 " {'id': 81,\n",728 " 'token': ' over',\n",729 " 'nugget': 'O',\n",730 " 'argument': 'I-Purpose',\n",731 " 'realis': 'O'},\n",732 " {'id': 10984,\n",733 " 'token': ' payroll',\n",734 " 'nugget': 'O',\n",735 " 'argument': 'I-Purpose',\n",736 " 'realis': 'O'},\n",737 " {'id': 335,\n",738 " 'token': ' information',\n",739 " 'nugget': 'O',\n",740 " 'argument': 'I-Purpose',\n",741 " 'realis': 'O'},\n",742 " {'id': 479, 'token': '.', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",743 " {'id': 1437, 'token': ' ', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",744 " {'id': 50118, 'token': '\\n', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",745 " {'id': 20,\n",746 " 'token': ' The',\n",747 " 'nugget': 'B-Phishing',\n",748 " 'argument': 'O',\n",749 " 'realis': 'Actual'},\n",750 " {'id': 1800,\n",751 " 'token': ' successful',\n",752 " 'nugget': 'I-Phishing',\n",753 " 'argument': 'O',\n",754 " 'realis': 'Actual'},\n",755 " {'id': 28237,\n",756 " 'token': ' phish',\n",757 " 'nugget': 'I-Phishing',\n",758 " 'argument': 'O',\n",759 " 'realis': 'Actual'},\n",760 " {'id': 3284,\n",761 " 'token': ' ultimately',\n",762 " 'nugget': 'O',\n",763 " 'argument': 'O',\n",764 " 'realis': 'O'},\n",765 " {'id': 13969,\n",766 " 'token': ' compromised',\n",767 " 'nugget': 'B-Databreach',\n",768 " 'argument': 'O',\n",769 " 'realis': 'Actual'},\n",770 " {'id': 4295,\n",771 " 'token': ' dozens',\n",772 " 'nugget': 'O',\n",773 " 'argument': 'O',\n",774 " 'realis': 'O'},\n",775 " {'id': 9, 'token': ' of', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",776 " {'id': 1321,\n",777 " 'token': ' employees',\n",778 " 'nugget': 'O',\n",779 " 'argument': 'B-Person',\n",780 " 'realis': 'O'},\n",781 " {'id': 128, 'token': \" '\", 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",782 " {'id': 14875,\n",783 " 'token': ' identities',\n",784 " 'nugget': 'O',\n",785 " 'argument': 'B-PII',\n",786 " 'realis': 'O'},\n",787 " {'id': 479, 'token': '.', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",788 " {'id': 598, 'token': ' To', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",789 " {'id': 28, 'token': ' be', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",790 " {'id': 2105, 'token': ' fair', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",791 " {'id': 2156, 'token': ',', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",792 " {'id': 10, 'token': ' a', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",793 " {'id': 14251,\n",794 " 'token': ' mega',\n",795 " 'nugget': 'O',\n",796 " 'argument': 'O',\n",797 " 'realis': 'O'},\n",798 " {'id': 6999,\n",799 " 'token': ' breach',\n",800 " 'nugget': 'O',\n",801 " 'argument': 'O',\n",802 " 'realis': 'O'},\n",803 " {'id': 15, 'token': ' on', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",804 " {'id': 5, 'token': ' the', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",805 " {'id': 3189,\n",806 " 'token': ' scale',\n",807 " 'nugget': 'O',\n",808 " 'argument': 'O',\n",809 " 'realis': 'O'},\n",810 " {'id': 9, 'token': ' of', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",811 " {'id': 99, 'token': ' what', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",812 " {'id': 2132,\n",813 " 'token': ' affected',\n",814 " 'nugget': 'O',\n",815 " 'argument': 'O',\n",816 " 'realis': 'O'},\n",817 " {'id': 6582,\n",818 " 'token': ' LinkedIn',\n",819 " 'nugget': 'O',\n",820 " 'argument': 'O',\n",821 " 'realis': 'O'},\n",822 " {'id': 2156, 'token': ',', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",823 " {'id': 9494,\n",824 " 'token': ' Tumblr',\n",825 " 'nugget': 'O',\n",826 " 'argument': 'O',\n",827 " 'realis': 'O'},\n",828 " {'id': 2156, 'token': ',', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",829 " {'id': 8, 'token': ' and', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",830 " {'id': 10354,\n",831 " 'token': ' Yahoo',\n",832 " 'nugget': 'O',\n",833 " 'argument': 'O',\n",834 " 'realis': 'O'},\n",835 " {'id': 34, 'token': ' has', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",836 " {'id': 648, 'token': ' yet', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",837 " {'id': 7, 'token': ' to', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",838 " {'id': 2506,\n",839 " 'token': ' strike',\n",840 " 'nugget': 'O',\n",841 " 'argument': 'O',\n",842 " 'realis': 'O'},\n",843 " {'id': 5, 'token': ' the', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",844 " {'id': 11203,\n",845 " 'token': ' messaging',\n",846 " 'nugget': 'O',\n",847 " 'argument': 'O',\n",848 " 'realis': 'O'},\n",849 " {'id': 1553, 'token': ' app', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",850 " {'id': 479, 'token': '.', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",851 " {'id': 125, 'token': ' But', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",852 " {'id': 14, 'token': ' that', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",853 " {'id': 128, 'token': \" '\", 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",854 " {'id': 29, 'token': 's', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",855 " {'id': 45, 'token': ' not', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",856 " {'id': 7, 'token': ' to', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",857 " {'id': 224, 'token': ' say', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",858 " {'id': 9177,\n",859 " 'token': ' criminals',\n",860 " 'nugget': 'O',\n",861 " 'argument': 'O',\n",862 " 'realis': 'O'},\n",863 " {'id': 32, 'token': ' are', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",864 " {'id': 295, 'token': ' n', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",865 " {'id': 75, 'token': \"'t\", 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",866 " {'id': 667,\n",867 " 'token': ' trying',\n",868 " 'nugget': 'O',\n",869 " 'argument': 'O',\n",870 " 'realis': 'O'},\n",871 " {'id': 7, 'token': ' to', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",872 " {'id': 465, 'token': ' find', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",873 " {'id': 10, 'token': ' a', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",874 " {'id': 169, 'token': ' way', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",875 " {'id': 88, 'token': ' into', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",876 " {'id': 82, 'token': ' people', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",877 " {'id': 128, 'token': \" '\", 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",878 " {'id': 29, 'token': 's', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",879 " {'id': 2349,\n",880 " 'token': ' accounts',\n",881 " 'nugget': 'O',\n",882 " 'argument': 'O',\n",883 " 'realis': 'O'},\n",884 " {'id': 479, 'token': '.', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",885 " {'id': 1437, 'token': ' ', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",886 " {'id': 50118, 'token': '\\n', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",887 " {'id': 46450,\n",888 " 'token': ' Hackers',\n",889 " 'nugget': 'O',\n",890 " 'argument': 'O',\n",891 " 'realis': 'O'},\n",892 " {'id': 2563,\n",893 " 'token': ' clearly',\n",894 " 'nugget': 'O',\n",895 " 'argument': 'O',\n",896 " 'realis': 'O'},\n",897 " {'id': 33, 'token': ' have', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",898 " {'id': 11477,\n",899 " 'token': ' Snapchat',\n",900 " 'nugget': 'O',\n",901 " 'argument': 'O',\n",902 " 'realis': 'O'},\n",903 " {'id': 11, 'token': ' in', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",904 " {'id': 49, 'token': ' their', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",905 " {'id': 579, 'token': ' s', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",906 " {'id': 6183, 'token': 'ights', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",907 " {'id': 2156, 'token': ',', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",908 " {'id': 61, 'token': ' which', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",909 " {'id': 16, 'token': ' is', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",910 " {'id': 596, 'token': ' why', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",911 " {'id': 1434,\n",912 " 'token': ' users',\n",913 " 'nugget': 'O',\n",914 " 'argument': 'O',\n",915 " 'realis': 'O'},\n",916 " {'id': 240, 'token': ' need', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",917 " {'id': 7, 'token': ' to', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",918 " {'id': 1532,\n",919 " 'token': ' learn',\n",920 " 'nugget': 'O',\n",921 " 'argument': 'O',\n",922 " 'realis': 'O'},\n",923 " {'id': 141, 'token': ' how', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",924 " {'id': 7, 'token': ' to', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",925 " {'id': 1514, 'token': ' spot', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",926 " {'id': 5, 'token': ' the', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",927 " {'id': 2892,\n",928 " 'token': ' warning',\n",929 " 'nugget': 'O',\n",930 " 'argument': 'O',\n",931 " 'realis': 'O'},\n",932 " {'id': 2434,\n",933 " 'token': ' signs',\n",934 " 'nugget': 'O',\n",935 " 'argument': 'O',\n",936 " 'realis': 'O'},\n",937 " {'id': 9, 'token': ' of', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",938 " {'id': 10, 'token': ' a', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",939 " {'id': 14157,\n",940 " 'token': ' hack',\n",941 " 'nugget': 'O',\n",942 " 'argument': 'O',\n",943 " 'realis': 'O'},\n",944 " {'id': 8, 'token': ' and', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",945 " {'id': 141, 'token': ' how', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",946 " {'id': 51, 'token': ' they', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",947 " {'id': 64, 'token': ' can', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",948 " {'id': 5312,\n",949 " 'token': ' recover',\n",950 " 'nugget': 'O',\n",951 " 'argument': 'O',\n",952 " 'realis': 'O'},\n",953 " {'id': 49, 'token': ' their', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",954 " {'id': 2349,\n",955 " 'token': ' accounts',\n",956 " 'nugget': 'O',\n",957 " 'argument': 'O',\n",958 " 'realis': 'O'},\n",959 " {'id': 114, 'token': ' if', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",960 " {'id': 951,\n",961 " 'token': ' someone',\n",962 " 'nugget': 'O',\n",963 " 'argument': 'O',\n",964 " 'realis': 'O'},\n",965 " {'id': 30478,\n",966 " 'token': ' compromises',\n",967 " 'nugget': 'O',\n",968 " 'argument': 'O',\n",969 " 'realis': 'O'},\n",970 " {'id': 106, 'token': ' them', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",971 " {'id': 479, 'token': '.', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",972 " {'id': 1437, 'token': ' ', 'nugget': 'O', 'argument': 'O', 'realis': 'O'},\n",973 " {'id': 50118, 'token': '\\n', 'nugget': 'O', 'argument': 'O', 'realis': 'O'}]"974 ]975 },976 "execution_count": 2,977 "metadata": {},978 "output_type": "execute_result"979 }980 ],981 "source": [982 "input = \"\"\"\n",983 "As of June 2016, more than 150 million active users interact with one another daily via Snapchat. Others are drawn by the service's more recent features. Those include Snapcash, a method introduced for users to send mobile payments to their friends. \n",984 "Given the app's popularity, it's no wonder online criminals have set their sights on hacking users' Snapchat accounts. For instance, back in late 2013, a group of hackers published a database containing the usernames and phone numbers of approximately 4.6 million Snapchat users. \n",985 "Nefarious individuals could have used that information to profile targets across multiple web accounts. We also can't forget about the security incident that occurred back in February 2016. In that attack, someone posed as the company's CEO and convinced a Snapchat employee to send over payroll information. \n",986 "The successful phish ultimately compromised dozens of employees' identities. To be fair, a mega breach on the scale of what affected LinkedIn, Tumblr, and Yahoo has yet to strike the messaging app. But that's not to say criminals aren't trying to find a way into people's accounts. \n",987 "Hackers clearly have Snapchat in their sights, which is why users need to learn how to spot the warning signs of a hack and how they can recover their accounts if someone compromises them.\n",988 "\"\"\"\n",989 "\n",990 "model(input)"991 ]992 },993 {994 "cell_type": "code",995 "execution_count": null,996 "metadata": {},997 "outputs": [],998 "source": [999 "model.forward()"1000 ]1001 },1002 {1003 "cell_type": "code",1004 "execution_count": null,1005 "metadata": {},1006 "outputs": [],1007 "source": []1008 }1009 ],1010 "metadata": {1011 "kernelspec": {1012 "display_name": "Python 3",1013 "language": "python",1014 "name": "python3"1015 },1016 "language_info": {1017 "codemirror_mode": {1018 "name": "ipython",1019 "version": 31020 },1021 "file_extension": ".py",1022 "mimetype": "text/x-python",1023 "name": "python",1024 "nbconvert_exporter": "python",1025 "pygments_lexer": "ipython3",1026 "version": "3.9.15"1027 },1028 "orig_nbformat": 41029 },1030 "nbformat": 4,1031 "nbformat_minor": 21032}1033 