import com.johnsnowlabs.nlp.annotator._ import com.johnsnowlabs.nlp.annotators.ner.NerConverter import com.johnsnowlabs.nlp.base._ import com.johnsnowlabs.util.Benchmark import org.apache.spark.ml.Pipeline import org.apache.spark.sql.SparkSession import org.apache.hadoop.mapreduce.lib.input.TextInputFormat import org.apache.hadoop.io.{LongWritable, Text} import org.apache.spark.rdd.RDD import scala.collection.mutable.ArrayBuffer import scala.util.control.Breaks._ import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
import com.johnsnowlabs.nlp.annotator._
import com.johnsnowlabs.nlp.annotators.ner.NerConverter
import com.johnsnowlabs.nlp.base._
import com.johnsnowlabs.util.Benchmark
import org.apache.spark.ml.Pipeline
import org.apache.spark.sql.SparkSession
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat
import org.apache.hadoop.io.{LongWritable, Text}
import org.apache.spark.rdd.RDD
import scala.collection.mutable.ArrayBuffer
import scala.util.control.Breaks._
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
Command took 2.28 seconds
val data = Seq( "Spider-Man is a fictional superhero created by writer-editor Stan Lee and writer-artist Steve Ditko. He first appeared in the anthology comic book Amazing Fantasy #15 in the Silver Age of Comic Books." ).toDS.toDF("text")
data: org.apache.spark.sql.DataFrame = [text: string]
Command took 1.06 seconds
pipeline.transform(data).select("ner_converter.result").show(false)
+-------------------------------------------------------------------+
|result |
+-------------------------------------------------------------------+
|[Stan Lee, Steve Ditko, Amazing Fantasy, Silver Age of Comic Books]|
+-------------------------------------------------------------------+
Command took 14.85 seconds
val testDataset = Seq( "Super-Man is a superhero character played by Christopher Reeves. This character can fly and do various amazing things." ).toDS.toDF("text") /* val testDataset = spark.read .option("header", false) .csv("/FileStore/tables/someUploadedFile.csv") .select($"_c0".as("text")) */
testDataset: org.apache.spark.sql.DataFrame = [text: string]
Command took 0.72 seconds
display(pipeline.transform(testDataset))
Super-Man is a superhero character played by Christopher Reeves. This character can fly and do various amazing things. | [{"annotatorType":"document","begin":0,"end":117,"result":"Super-Man is a superhero character played by Christopher Reeves. This character can fly and do various amazing things.","metadata":{"sentence":"0"},"embeddings":[],"sentence_embeddings":[]}] | [{"annotatorType":"document","begin":0,"end":63,"result":"Super-Man is a superhero character played by Christopher Reeves.","metadata":{"sentence":"0"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"document","begin":65,"end":117,"result":"This character can fly and do various amazing things.","metadata":{"sentence":"1"},"embeddings":[],"sentence_embeddings":[]}] | [{"annotatorType":"token","begin":0,"end":8,"result":"Super-Man","metadata":{"sentence":"0","chunk":"0"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"token","begin":10,"end":11,"result":"is","metadata":{"sentence":"0","chunk":"0"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"token","begin":13,"end":13,"result":"a","metadata":{"sentence":"0","chunk":"0"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"token","begin":15,"end":23,"result":"superhero","metadata":{"sentence":"0","chunk":"0"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"token","begin":25,"end":33,"result":"character","metadata":{"sentence":"0","chunk":"0"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"token","begin":35,"end":40,"result":"played","metadata":{"sentence":"0","chunk":"0"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"token","begin":42,"end":43,"result":"by","metadata":{"sentence":"0","chunk":"0"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"token","begin":45,"end":55,"result":"Christopher","metadata":{"sentence":"0","chunk":"0"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"token","begin":57,"end":62,"result":"Reeves","metadata":{"sentence":"0","chunk":"0"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"token","begin":63,"end":63,"result":".","metadata":{"sentence":"0","chunk":"0"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"token","begin":65,"end":68,"result":"This","metadata":{"sentence":"1","chunk":"1"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"token","begin":70,"end":78,"result":"character","metadata":{"sentence":"1","chunk":"1"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"token","begin":80,"end":82,"result":"can","metadata":{"sentence":"1","chunk":"1"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"token","begin":84,"end":86,"result":"fly","metadata":{"sentence":"1","chunk":"1"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"token","begin":88,"end":90,"result":"and","metadata":{"sentence":"1","chunk":"1"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"token","begin":92,"end":93,"result":"do","metadata":{"sentence":"1","chunk":"1"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"token","begin":95,"end":101,"result":"various","metadata":{"sentence":"1","chunk":"1"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"token","begin":103,"end":109,"result":"amazing","metadata":{"sentence":"1","chunk":"1"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"token","begin":111,"end":116,"result":"things","metadata":{"sentence":"1","chunk":"1"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"token","begin":117,"end":117,"result":".","metadata":{"sentence":"1","chunk":"1"},"embeddings":[],"sentence_embeddings":[]}] | [{"annotatorType":"word_embeddings","begin":0,"end":8,"result":"Super-Man","metadata":{"sentence":"0","token":"Super-Man","pieceId":"-1","isWordStart":"true"},"embeddings":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"sentence_embeddings":[]},{"annotatorType":"word_embeddings","begin":10,"end":11,"result":"is","metadata":{"sentence":"0","token":"is","pieceId":"-1","isWordStart":"true"},"embeddings":[-0.54264,0.41476,1.0322,-0.40244,0.46691,0.21816,-0.074864,0.47332,0.080996,-0.22079,-0.12808,-0.1144,0.50891,0.11568,0.028211,-0.3628,0.43823,0.047511,0.20282,0.49857,-0.10068,0.13269,0.16972,0.11653,0.31355,0.25713,0.092783,-0.56826,-0.52975,-0.051456,-0.67326,0.92533,0.2693,0.22734,0.66365,0.26221,0.19719,0.2609,0.18774,-0.3454,-0.42635,0.13975,0.56338,-0.56907,0.12398,-0.12894,0.72484,-0.26105,-0.26314,-0.43605,0.078908,-0.84146,0.51595,1.3997,-0.7646,-3.1453,-0.29202,-0.31247,1.5129,0.52435,0.21456,0.42452,-0.088411,-0.17805,1.1876,0.10579,0.76571,0.21914,0.35824,-0.11636,0.093261,-0.62483,-0.21898,0.21796,0.74056,-0.43735,0.14343,0.14719,-1.1605,-0.050508,0.12677,-0.014395,-0.98676,-0.091297,-1.2054,-0.11974,0.047847,-0.54001,0.52457,-0.70963,-0.32528,-0.1346,-0.41314,0.33435,-0.0072412,0.32253,-0.044219,-1.2969,0.76217,0.46349],"sentence_embeddings":[]},{"annotatorType":"word_embeddings","begin":13,"end":13,"result":"a","metadata":{"sentence":"0","token":"a","pieceId":"-1","isWordStart":"true"},"embeddings":[-0.27086,0.044006,-0.02026,-0.17395,0.6444,0.71213,0.3551,0.47138,-0.29637,0.54427,-0.72294,-0.0047612,0.040611,0.043236,0.29729,0.10725,0.40156,-0.53662,0.033382,0.067396,0.64556,-0.085523,0.14103,0.094539,0.74947,-0.194,-0.68739,-0.41741,-0.22807,0.12,-0.48999,0.80945,0.045138,-0.11898,0.20161,0.39276,-0.20121,0.31354,0.75304,0.25907,-0.11566,-0.029319,0.93499,-0.36067,0.5242,0.23706,0.52715,0.22869,-0.51958,-0.79349,-0.20368,-0.50187,0.18748,0.94282,-0.44834,-3.6792,0.044183,-0.26751,2.1997,0.241,-0.033425,0.69553,-0.64472,-0.0072277,0.89575,0.20015,0.46493,0.61933,-0.1066,0.08691,-0.4623,0.18262,-0.15849,0.020791,0.19373,0.063426,-0.31673,-0.48177,-1.3848,0.13669,0.96859,0.049965,-0.2738,-0.035686,-1.0577,-0.24467,0.90366,-0.12442,0.080776,-0.83401,0.57201,0.088945,-0.42532,-0.018253,-0.079995,-0.28581,-0.01089,-0.4923,0.63687,0.23642],"sentence_embeddings":[]},{"annotatorType":"word_embeddings","begin":15,"end":23,"result":"superhero","metadata":{"sentence":"0","token":"superhero","pieceId":"-1","isWordStart":"true"},"embeddings":[0.049952,-0.009251,0.23294,-0.9527,0.060802,0.64233,-0.18271,-0.65618,0.18542,0.25151,-0.47902,-1.0879,0.46962,-0.80675,0.28321,0.45856,1.117,0.89048,1.1575,0.082254,1.1163,-0.51053,-0.53273,-0.50797,0.8503,0.48928,-0.037738,-0.61112,-0.4424,0.21037,0.12534,0.16777,-0.80398,-0.6715,-0.034722,-0.040662,-0.73461,-0.10139,-0.15531,0.30424,0.041514,1.0403,-0.2867,-0.021094,0.21583,0.2681,-0.43519,0.48503,0.60368,0.53334,-0.72647,0.33136,0.27829,0.68819,0.64338,-0.71098,-0.2926,0.25727,-0.30671,0.54915,0.34244,1.0899,-0.43006,0.18436,1.4453,-0.18653,-0.32441,0.38719,0.03019,0.36978,0.49933,-0.46893,-0.4038,0.27708,-0.32204,0.46606,-0.0922,-0.0067253,-0.40388,-0.16263,-0.8112,0.15313,0.47488,0.020725,-0.47818,0.14085,-0.87766,-0.22234,0.22641,-0.51546,-0.1632,0.39092,0.33169,-0.51953,0.2338,-0.59595,0.086845,-0.034258,0.38577,-0.11992],"sentence_embeddings":[]},{"annotatorType":"word_embeddings","begin":25,"end":33,"result":"character","metadata":{"sentence":"0","token":"character","pieceId":"-1","isWordStart":"true"},"embeddings":[0.056951,-0.011958,0.45949,-0.40205,0.11432,0.64298,-0.18108,-0.59519,0.16423,0.025829,-0.84815,-0.51983,0.30331,-0.021558,0.20537,0.61944,0.72671,0.691,0.30493,1.2351,0.42527,-0.78581,-0.18104,-0.33291,1.0104,-0.047434,0.013179,-0.46831,-0.27288,0.53269,0.10248,0.87001,-0.094714,-0.37797,0.34009,0.24346,0.15385,0.12826,0.074839,0.00071542,-0.106,0.14678,0.28431,0.61777,-0.15263,0.36078,-0.64462,-0.17524,0.25269,-0.30756,-0.071689,0.087817,1.0129,1.6403,0.72108,-2.3364,0.01927,-0.17663,-0.055044,0.30303,0.42514,1.4098,-0.35703,0.25565,1.5807,-0.36794,0.64496,-0.084393,0.030454,0.6586,-0.09907,-0.066467,-0.063636,-0.060706,0.53333,0.092229,-0.14248,0.15896,-0.12885,-0.27333,-0.76738,0.13256,-0.205,-0.16149,-1.5769,-0.031601,-0.74795,-0.22234,0.31041,-0.71075,-0.19467,0.29785,0.21059,0.31695,0.054587,-0.076512,-0.44174,-1.1054,-0.14803,0.30275],"sentence_embeddings":[]},{"annotatorType":"word_embeddings","begin":35,"end":40,"result":"played","metadata":{"sentence":"0","token":"played","pieceId":"-1","isWordStart":"true"},"embeddings":[-0.37869,0.059073,0.24802,-0.37607,-0.06631,0.64661,0.27481,0.31712,-1.2448,-0.45063,0.22176,-1.1149,-0.11355,0.43537,0.034575,-0.02945,0.3609,0.47133,-0.1946,0.63912,0.16841,0.39337,0.49114,0.1676,0.39917,-0.52532,-0.38683,-0.78041,0.36205,0.75733,-0.88034,1.1463,0.35832,0.099747,0.17299,-0.39269,-0.21809,0.88098,-0.59475,-0.15801,0.024491,-0.048224,0.39388,0.071387,0.49728,-0.096297,0.50516,-0.59857,0.56269,-0.93341,-0.67195,-0.021831,0.34169,0.87003,-0.19385,-2.6721,-0.51875,-0.22178,-0.4969,1.334,-0.63715,1.0821,-1.0649,-0.007408,0.22452,-0.34375,0.48248,0.53217,-0.12344,0.80067,0.022189,-0.4555,0.012998,0.04662,0.2602,-0.14379,-0.071346,0.070334,-0.027716,-0.13284,0.63656,-0.0094122,0.057679,-0.078596,-1.3584,-0.42888,-0.54009,-0.094211,-0.32858,0.033501,-1.0108,0.03493,-0.6636,0.61096,-0.36479,0.1309,-0.81273,0.31451,0.42636,0.024494],"sentence_embeddings":[]},{"annotatorType":"word_embeddings","begin":42,"end":43,"result":"by","metadata":{"sentence":"0","token":"by","pieceId":"-1","isWordStart":"true"},"embeddings":[-0.20875,-0.1174,0.26478,-0.28339,0.19584,0.7446,-0.03887,0.028499,-0.44252,-0.30426,0.27133,-0.51907,0.52183,-0.76648,0.28043,-0.48344,-0.15626,-0.49705,-0.51024,-0.03652,0.20579,-0.6136,0.46388,0.73497,0.66813,-0.4443,-0.17603,-0.5478,-0.013521,0.16333,0.28148,0.054223,-0.19906,-0.1907,-0.43179,0.14781,0.27555,0.18571,-0.40776,-0.15415,-0.5885,-0.0085281,-0.14178,0.7061,0.54031,-0.43305,0.17497,-0.46208,-0.31372,-0.34039,-0.25128,0.68228,0.33576,1.5862,-0.39427,-2.9938,-0.29773,0.04213,1.9075,-0.072628,-0.092191,0.66133,0.13868,0.78774,0.69307,-0.22185,0.71705,1.1453,1.2153,0.14196,-0.79914,0.16965,-0.34532,-0.51742,-0.15648,0.18757,0.1694,-0.0082713,-1.4511,0.061983,1.1019,0.084411,-0.34148,0.49994,-1.1106,-0.13759,0.15377,-0.061006,-0.53826,-0.78941,-0.12566,-0.57381,-0.73484,0.54774,-0.28455,-0.24348,-0.27511,-0.33267,0.27878,-0.8705],"sentence_embeddings":[]},{"annotatorType":"word_embeddings","begin":45,"end":55,"result":"Christopher","metadata":{"sentence":"0","token":"Christopher","pieceId":"-1","isWordStart":"true"},"embeddings":[-0.69782,-0.59651,0.054392,-0.43545,0.36289,-0.88198,0.097809,0.16313,-0.54932,-0.62679,-0.55099,-0.12195,0.039863,0.70019,0.11119,-0.43725,-0.44921,-0.43837,-0.82412,0.039575,-0.20611,-0.28591,0.015793,0.11249,0.30518,0.36721,-0.33827,-0.18287,0.40683,0.33718,-0.25111,0.16722,-0.2839,-0.050752,-0.069345,-0.035005,0.6009,0.1028,0.75585,0.27434,-0.93565,-0.16303,0.12189,0.2392,-0.33384,-0.39866,-0.83068,-0.83614,-0.0012178,0.26378,0.71813,-0.25458,0.044914,-0.20084,0.26332,-2.0592,-0.68156,-0.040343,-0.10506,-0.25064,-0.013616,0.69601,-0.067455,-0.3209,-0.2423,-0.88436,0.67138,2.0608,-0.26845,0.02579,-0.32094,-0.61362,-0.5183,0.0023771,0.23268,0.071948,-0.16808,0.098793,-0.68452,-0.45936,0.046735,0.19824,0.4134,-0.23284,-0.32792,0.19845,-0.61827,-0.65258,-0.069037,-1.0737,-0.40459,-0.058468,-0.22877,0.21116,-0.50491,0.52897,0.43983,-0.62985,-0.17613,-0.1658],"sentence_embeddings":[]},{"annotatorType":"word_embeddings","begin":57,"end":62,"result":"Reeves","metadata":{"sentence":"0","token":"Reeves","pieceId":"-1","isWordStart":"true"},"embeddings":[-0.19478,-0.77576,0.51825,-1.3646,-0.22267,-0.19435,-0.11931,0.35158,0.20041,-0.44365,-0.23581,-0.61688,-0.16646,0.095222,0.015208,-0.3007,0.1434,0.5238,-0.25303,0.99166,-0.2908,-0.25004,-0.59743,0.18797,0.95204,-0.24558,0.42843,-0.3174,0.24376,0.26896,-0.48183,0.35541,0.3329,-0.46115,-0.23598,-0.11805,0.07009,0.84959,0.21785,-0.049773,-0.2095,-0.061589,0.23643,0.18446,-0.55597,0.41388,-0.21071,-0.4068,0.83019,-0.33019,0.084512,-0.41134,0.32333,0.35191,0.29637,-0.702,0.45272,0.36671,-0.40726,0.2257,-0.048825,0.46066,-0.10959,-0.29839,0.12026,-0.21633,0.76661,0.2807,-1.2825,1.1702,-0.21232,0.20785,-0.51903,0.23696,0.082014,-0.91184,-0.002737,0.23365,-0.071916,0.46044,0.22924,-0.25634,-0.35748,-0.43547,-0.12762,0.0074532,0.54577,-0.43861,-0.70264,-0.17226,-0.067615,-0.33395,-0.28751,0.055256,-0.33429,0.11395,-0.53912,0.14855,-0.20377,0.12456],"sentence_embeddings":[]},{"annotatorType":"word_embeddings","begin":63,"end":63,"result":".","metadata":{"sentence":"0","token":".","pieceId":"-1","isWordStart":"true"},"embeddings":[-0.33979,0.20941,0.46348,-0.64792,-0.38377,0.038034,0.17127,0.15978,0.46619,-0.019169,0.41479,-0.34349,0.26872,0.04464,0.42131,-0.41032,0.15459,0.022239,-0.64653,0.25256,0.043136,-0.19445,0.46516,0.45651,0.68588,0.091295,0.21875,-0.70351,0.16785,-0.35079,-0.12634,0.66384,-0.2582,0.036542,-0.13605,0.40253,0.14289,0.38132,-0.12283,-0.45886,-0.25282,-0.30432,-0.11215,-0.26182,-0.22482,-0.44554,0.2991,-0.85612,-0.14503,-0.49086,0.0082973,-0.17491,0.27524,1.4401,-0.21239,-2.8435,-0.27958,-0.45722,1.6386,0.78808,-0.55262,0.65,0.086426,0.39012,1.0632,-0.35379,0.48328,0.346,0.84174,0.098707,-0.24213,-0.27053,0.045287,-0.40147,0.11395,0.0062226,0.036673,0.018518,-1.0213,-0.20806,0.64072,-0.068763,-0.58635,0.33476,-1.1432,-0.1148,-0.25091,-0.45907,-0.096819,-0.17946,-0.063351,-0.67412,-0.068895,0.53604,-0.87773,0.31802,-0.39242,-0.23394,0.47298,-0.028803],"sentence_embeddings":[]},{"annotatorType":"word_embeddings","begin":65,"end":68,"result":"This","metadata":{"sentence":"1","token":"This","pieceId":"-1","isWordStart":"true"},"embeddings":[-0.57058,0.44183,0.70102,-0.41713,-0.34058,0.02339,-0.071537,0.48177,-0.013121,0.16834,-0.13389,0.040626,0.15827,-0.44342,-0.019403,-0.009661,-0.046284,0.093228,-0.27331,0.2285,0.33089,-0.36474,0.078741,0.3585,0.44757,-0.2299,0.18077,-0.6265,0.053852,-0.29154,-0.4256,0.62903,0.14393,-0.046004,-0.21007,0.48879,-0.057698,0.37431,-0.030075,-0.34494,-0.29702,0.15095,0.28248,-0.16578,0.076131,-0.093016,0.79365,-0.60489,-0.18874,-1.0173,0.31962,-0.16344,0.54177,1.1725,-0.47875,-3.3842,-0.081301,-0.3528,1.8372,0.44516,-0.52666,0.99786,-0.32178,0.033462,1.1783,-0.072905,0.39737,0.26166,0.33111,-0.35629,-0.16558,-0.44382,-0.14183,-0.37976,0.28994,-0.029114,-0.35169,-0.27694,-1.344,0.19555,0.16887,0.040237,-0.80212,0.23366,-1.3837,-0.023132,0.085395,-0.74051,-0.073934,-0.58838,-0.085735,-0.10525,-0.51571,0.15038,-0.16694,-0.16372,-0.22702,-0.66102,0.47197,0.37253],"sentence_embeddings":[]},{"annotatorType":"word_embeddings","begin":70,"end":78,"result":"character","metadata":{"sentence":"1","token":"character","pieceId":"-1","isWordStart":"true"},"embeddings":[0.056951,-0.011958,0.45949,-0.40205,0.11432,0.64298,-0.18108,-0.59519,0.16423,0.025829,-0.84815,-0.51983,0.30331,-0.021558,0.20537,0.61944,0.72671,0.691,0.30493,1.2351,0.42527,-0.78581,-0.18104,-0.33291,1.0104,-0.047434,0.013179,-0.46831,-0.27288,0.53269,0.10248,0.87001,-0.094714,-0.37797,0.34009,0.24346,0.15385,0.12826,0.074839,0.00071542,-0.106,0.14678,0.28431,0.61777,-0.15263,0.36078,-0.64462,-0.17524,0.25269,-0.30756,-0.071689,0.087817,1.0129,1.6403,0.72108,-2.3364,0.01927,-0.17663,-0.055044,0.30303,0.42514,1.4098,-0.35703,0.25565,1.5807,-0.36794,0.64496,-0.084393,0.030454,0.6586,-0.09907,-0.066467,-0.063636,-0.060706,0.53333,0.092229,-0.14248,0.15896,-0.12885,-0.27333,-0.76738,0.13256,-0.205,-0.16149,-1.5769,-0.031601,-0.74795,-0.22234,0.31041,-0.71075,-0.19467,0.29785,0.21059,0.31695,0.054587,-0.076512,-0.44174,-1.1054,-0.14803,0.30275],"sentence_embeddings":[]},{"annotatorType":"word_embeddings","begin":80,"end":82,"result":"can","metadata":{"sentence":"1","token":"can","pieceId":"-1","isWordStart":"true"},"embeddings":[-0.71766,0.80871,0.31868,-0.53589,-0.31998,0.18929,-0.23241,0.44233,0.25649,-0.32093,-0.16951,0.14993,0.55681,0.33992,0.028335,-0.38295,0.43366,0.73026,-0.79863,0.2954,0.017078,-0.39545,0.19967,0.081727,0.18943,0.095973,-0.033138,-0.69888,0.41562,-0.67422,-0.059873,1.23,-0.31391,0.15313,0.82508,0.49345,-0.051686,0.31035,0.25147,-0.36228,-0.14969,-0.39609,-0.73853,-1.0716,-0.21775,0.23018,0.078188,-0.48584,-0.082414,-1.0405,0.44389,-0.2964,0.036505,1.2115,0.50287,-2.2662,-0.073575,0.010925,1.7266,0.63332,-0.23215,1.2603,-0.43585,-0.082693,1.1903,0.34009,0.59365,0.20098,0.1016,-1.1757,-0.1187,-0.59569,0.34427,-0.48687,0.34953,-0.44521,-0.13131,-0.19316,-0.55304,0.075953,0.6893,-0.26706,-1.1425,-0.4221,-1.9038,0.028733,0.79527,-0.05133,-0.028824,-0.35704,-0.72769,0.19074,-0.026097,-0.48544,-0.225,0.025487,0.27732,-1.0023,0.8588,0.28583],"sentence_embeddings":[]},{"annotatorType":"word_embeddings","begin":84,"end":86,"result":"fly","metadata":{"sentence":"1","token":"fly","pieceId":"-1","isWordStart":"true"},"embeddings":[-0.61151,-0.089,0.57914,-0.37872,-0.076508,0.29628,-0.21965,0.07374,-0.51181,0.037768,-0.26224,0.024468,0.74008,0.62817,0.16576,-0.51124,0.34345,0.65455,-0.11617,0.05039,0.67468,0.33495,0.15105,-0.15252,0.97707,0.3057,-1.0304,-0.21503,0.72802,0.43026,-1.3456,0.19387,0.075721,0.50233,0.4213,1.1407,0.20326,0.66612,-0.084463,0.14062,-0.68388,-0.097316,-0.65039,0.012185,0.50693,0.12371,-0.16194,-0.23563,-0.29628,-0.54047,-0.078818,0.76777,-0.31455,0.98189,0.16235,-1.4505,0.020271,0.64522,2.0882,0.40768,0.21402,0.97949,0.45035,-0.21508,-0.20983,0.14151,-0.27174,0.053071,-0.81273,0.027876,-0.54709,-1.0026,-0.47008,-0.69509,0.48017,-0.18451,-0.18499,-0.43785,-0.021381,0.55532,0.13511,-0.31009,-0.37673,-0.17954,-0.55992,-0.35525,1.0957,0.090606,-0.17176,0.37433,-0.50994,-0.12213,0.18649,-1.0963,-0.4918,0.19419,-0.50474,0.36096,-0.19625,-0.57128],"sentence_embeddings":[]},{"annotatorType":"word_embeddings","begin":88,"end":90,"result":"and","metadata":{"sentence":"1","token":"and","pieceId":"-1","isWordStart":"true"},"embeddings":[-0.071953,0.23127,0.023731,-0.50638,0.33923,0.1959,-0.32943,0.18364,-0.18057,0.28963,0.20448,-0.5496,0.27399,0.58327,0.20468,-0.49228,0.19974,-0.070237,-0.88049,0.29485,0.14071,-0.1009,0.99449,0.36973,0.44554,0.28998,-0.1376,-0.56365,-0.029365,-0.4122,-0.25269,0.63181,-0.44767,0.24363,-0.10813,0.25164,0.46967,0.3755,-0.23613,-0.14129,-0.44537,-0.65737,-0.042421,-0.28636,-0.28811,0.063766,0.20281,-0.53542,0.41307,-0.59722,-0.38614,0.19389,-0.17809,1.6618,-0.011819,-2.3737,0.058427,-0.2698,1.2823,0.81925,-0.22322,0.72932,-0.053211,0.43507,0.85011,-0.42935,0.92664,0.39051,1.0585,-0.24561,-0.18265,-0.5328,0.059518,-0.66019,0.18991,0.28836,-0.2434,0.52784,-0.65762,-0.14081,1.0491,0.5134,-0.23816,0.69895,-1.4813,-0.2487,-0.17936,-0.059137,-0.08056,-0.48782,0.014487,-0.6259,-0.32367,0.41862,-1.0807,0.46742,-0.49931,-0.71895,0.86894,0.19539],"sentence_embeddings":[]},{"annotatorType":"word_embeddings","begin":92,"end":93,"result":"do","metadata":{"sentence":"1","token":"do","pieceId":"-1","isWordStart":"true"},"embeddings":[-0.17047,0.4037,0.21069,-0.89495,-1.0974,0.26637,-0.66438,0.43423,0.43604,-0.096505,0.17299,-0.043644,0.25197,0.37532,-0.3742,-0.31528,0.15621,1.0254,-0.69791,0.85064,0.29749,0.2582,0.037544,-0.29904,-0.48232,0.24501,-0.42231,-1.213,0.65729,-0.66008,-0.20341,0.49007,0.21975,-0.015368,0.2685,0.75017,0.066525,0.22781,0.36977,-0.43185,-0.17637,0.19282,-0.5611,-0.83103,-0.93903,-0.037231,0.20521,-0.67886,-0.75606,-1.4499,0.024081,0.13546,-0.33894,0.9505,0.023876,-2.3589,0.25861,0.027507,1.7216,0.45003,-0.38897,1.1423,-0.7378,-0.57465,1.2876,0.6925,0.93593,0.57175,-0.23874,-0.48673,0.090969,-0.51457,0.21292,-0.85689,-0.055736,-0.20015,-0.3957,0.061003,-0.45949,-0.057818,0.7602,-0.55281,-0.96297,-0.086508,-2.036,-0.2284,0.061782,0.1475,-0.19664,-0.50653,-0.16682,-0.29811,0.10284,-0.4235,-0.71824,0.045687,-0.21338,-0.67179,0.31645,0.50594],"sentence_embeddings":[]},{"annotatorType":"word_embeddings","begin":95,"end":101,"result":"various","metadata":{"sentence":"1","token":"various","pieceId":"-1","isWordStart":"true"},"embeddings":[-0.49297,0.2752,-0.80131,0.26926,0.99942,0.21687,-0.58925,0.089434,-0.47161,-0.09534,0.020152,-0.80302,0.60894,0.54874,0.090659,-0.05054,0.37754,0.049866,-0.47367,0.18486,-0.057358,-0.39049,0.39504,-0.29281,-0.45404,-0.86351,0.42128,-0.2282,-0.16796,0.6814,-0.065765,0.21618,-0.62611,-0.39768,0.11709,0.55839,-0.0086545,-0.17774,-0.60781,-0.21112,-0.6316,-0.13935,-0.28142,0.019121,-0.11791,0.10677,-0.46474,0.01648,-0.26065,-0.029701,0.063333,0.46482,0.17023,0.65027,0.38269,-1.6277,0.3127,-0.31413,1.5816,0.78071,-0.54155,1.71,0.12714,0.38656,0.88454,-0.26135,-0.047377,-0.38153,0.98745,-0.071359,-0.34679,-0.090094,0.1021,-0.18233,0.17389,0.11143,-0.29457,-0.21193,-0.83082,0.23943,0.95363,0.064688,0.35618,0.24718,-1.7764,0.41506,-0.49373,-0.38019,-0.16014,-0.14376,-0.56503,-0.08372,-0.37465,0.018586,-0.71158,-0.024712,-1.1489,-0.40395,1.4321,0.20582],"sentence_embeddings":[]},{"annotatorType":"word_embeddings","begin":103,"end":109,"result":"amazing","metadata":{"sentence":"1","token":"amazing","pieceId":"-1","isWordStart":"true"},"embeddings":[0.24904,0.23423,0.23476,-0.22316,-0.2316,0.028909,0.26808,0.60467,-0.52247,-0.46531,0.57831,-0.21542,-0.18651,-0.80568,0.0015249,0.57291,-0.31303,0.91597,-0.012571,1.0577,0.47094,0.27438,-0.36912,-0.83548,0.79462,0.5001,0.19319,0.27376,0.21519,-0.79754,-0.72414,0.078378,0.025171,-0.26574,-0.099393,-0.43234,-0.55377,0.35712,0.17956,-0.53916,0.38338,0.70359,0.076757,0.081165,-0.097816,0.30594,0.49879,-0.1069,0.057092,-0.6602,-0.15238,-0.098335,0.66284,0.65289,0.3196,-1.7919,0.30483,0.58955,0.30529,-0.01181,-0.36157,0.9317,-0.65981,-0.24784,0.43166,-0.038846,0.47463,-0.029135,0.38999,0.089294,0.72422,0.40294,-0.055704,0.16401,0.66226,0.66812,-0.14608,-0.31634,0.17365,0.29629,0.15788,0.31749,0.26991,-0.064028,-0.99376,-0.278,0.44937,-0.34077,-0.74536,-0.046839,0.26373,0.18334,0.3275,0.021991,-0.61047,-0.6746,-0.80762,-1.1873,-0.15702,0.9493],"sentence_embeddings":[]},{"annotatorType":"word_embeddings","begin":111,"end":116,"result":"things","metadata":{"sentence":"1","token":"things","pieceId":"-1","isWordStart":"true"},"embeddings":[0.002042,0.23462,0.56775,-0.52018,-0.44514,0.083055,-0.39646,-0.26854,0.21232,-0.3957,0.40598,-0.075455,0.41743,0.30452,0.036475,-0.14202,-0.55857,0.8598,-0.39588,0.69327,0.10008,0.25011,0.061503,-0.70228,-0.050894,-0.067051,-0.43496,-0.79233,-0.19579,-0.25287,-0.37155,0.3786,-0.017949,-0.48875,-0.34516,0.14967,-0.18105,-0.10146,0.055586,-0.56322,-0.39558,-0.27711,-0.020312,-0.71266,-1.2598,0.25123,0.13428,-0.05452,0.043982,-1.1873,0.59125,-0.11923,0.12641,0.92519,-0.109,-2.1719,0.41761,0.7192,1.3063,0.41463,-0.45811,1.5003,-0.69474,-0.19831,1.0513,0.26267,0.9528,0.11746,0.13683,-0.39173,0.35636,-0.23451,0.13939,-0.40334,0.51918,0.22309,-0.14831,-0.21447,-0.054055,0.46411,0.26464,-0.033298,-0.46443,0.11854,-1.8133,0.012966,-0.095972,-0.45995,-0.83393,-0.58897,-0.39032,-0.1973,0.031354,-0.27637,-0.68446,-0.22084,-0.38553,-0.095546,0.18837,0.76098],"sentence_embeddings":[]},{"annotatorType":"word_embeddings","begin":117,"end":117,"result":".","metadata":{"sentence":"1","token":".","pieceId":"-1","isWordStart":"true"},"embeddings":[-0.33979,0.20941,0.46348,-0.64792,-0.38377,0.038034,0.17127,0.15978,0.46619,-0.019169,0.41479,-0.34349,0.26872,0.04464,0.42131,-0.41032,0.15459,0.022239,-0.64653,0.25256,0.043136,-0.19445,0.46516,0.45651,0.68588,0.091295,0.21875,-0.70351,0.16785,-0.35079,-0.12634,0.66384,-0.2582,0.036542,-0.13605,0.40253,0.14289,0.38132,-0.12283,-0.45886,-0.25282,-0.30432,-0.11215,-0.26182,-0.22482,-0.44554,0.2991,-0.85612,-0.14503,-0.49086,0.0082973,-0.17491,0.27524,1.4401,-0.21239,-2.8435,-0.27958,-0.45722,1.6386,0.78808,-0.55262,0.65,0.086426,0.39012,1.0632,-0.35379,0.48328,0.346,0.84174,0.098707,-0.24213,-0.27053,0.045287,-0.40147,0.11395,0.0062226,0.036673,0.018518,-1.0213,-0.20806,0.64072,-0.068763,-0.58635,0.33476,-1.1432,-0.1148,-0.25091,-0.45907,-0.096819,-0.17946,-0.063351,-0.67412,-0.068895,0.53604,-0.87773,0.31802,-0.39242,-0.23394,0.47298,-0.028803],"sentence_embeddings":[]}] | [{"annotatorType":"named_entity","begin":0,"end":8,"result":"O","metadata":{"word":"Super-Man"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"named_entity","begin":10,"end":11,"result":"O","metadata":{"word":"is"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"named_entity","begin":13,"end":13,"result":"O","metadata":{"word":"a"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"named_entity","begin":15,"end":23,"result":"O","metadata":{"word":"superhero"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"named_entity","begin":25,"end":33,"result":"O","metadata":{"word":"character"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"named_entity","begin":35,"end":40,"result":"O","metadata":{"word":"played"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"named_entity","begin":42,"end":43,"result":"O","metadata":{"word":"by"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"named_entity","begin":45,"end":55,"result":"I-PER","metadata":{"word":"Christopher"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"named_entity","begin":57,"end":62,"result":"I-PER","metadata":{"word":"Reeves"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"named_entity","begin":63,"end":63,"result":"O","metadata":{"word":"."},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"named_entity","begin":65,"end":68,"result":"O","metadata":{"word":"This"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"named_entity","begin":70,"end":78,"result":"O","metadata":{"word":"character"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"named_entity","begin":80,"end":82,"result":"O","metadata":{"word":"can"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"named_entity","begin":84,"end":86,"result":"O","metadata":{"word":"fly"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"named_entity","begin":88,"end":90,"result":"O","metadata":{"word":"and"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"named_entity","begin":92,"end":93,"result":"O","metadata":{"word":"do"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"named_entity","begin":95,"end":101,"result":"O","metadata":{"word":"various"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"named_entity","begin":103,"end":109,"result":"O","metadata":{"word":"amazing"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"named_entity","begin":111,"end":116,"result":"O","metadata":{"word":"things"},"embeddings":[],"sentence_embeddings":[]},{"annotatorType":"named_entity","begin":117,"end":117,"result":"O","metadata":{"word":"."},"embeddings":[],"sentence_embeddings":[]}] | [{"annotatorType":"chunk","begin":45,"end":62,"result":"Christopher Reeves","metadata":{"entity":"PER","sentence":"0","chunk":"0"},"embeddings":[],"sentence_embeddings":[]}] |
text | document | sentence | token | embeddings | ner | ner_converter |
---|
Last refresh: Never
Command took 10.58 seconds
SDS-2.x, Scalable Data Engineering Science
This is a minor augnmentation/update of:
Last refresh: Never