Training

import spark.implicits._
import com.johnsnowlabs.nlp.base.DocumentAssembler
import com.johnsnowlabs.nlp.annotators.sbd.pragmatic.SentenceDetector
import com.johnsnowlabs.nlp.annotators.Tokenizer
import com.johnsnowlabs.nlp.annotators.pos.perceptron.PerceptronModel
import com.johnsnowlabs.nlp.annotators.parser.dep.DependencyParserApproach
import org.apache.spark.ml.Pipeline

val documentAssembler = new DocumentAssembler()
  .setInputCol("text")
  .setOutputCol("document")

val sentence = new SentenceDetector()
  .setInputCols("document")
  .setOutputCol("sentence")

val tokenizer = new Tokenizer()
  .setInputCols("sentence")
  .setOutputCol("token")

val posTagger = PerceptronModel.pretrained()
  .setInputCols("sentence", "token")
  .setOutputCol("pos")

val dependencyParserApproach = new DependencyParserApproach()
  .setInputCols("sentence", "pos", "token")
  .setOutputCol("dependency")
  .setDependencyTreeBank("src/test/resources/parser/unlabeled/dependency_treebank")

val pipeline = new Pipeline().setStages(Array(
  documentAssembler,
  sentence,
  tokenizer,
  posTagger,
  dependencyParserApproach
))

// Additional training data is not needed, the dependency parser relies on the dependency tree bank / CoNLL-U only.
val emptyDataSet = Seq.empty[String].toDF("text")
val pipelineModel = pipeline.fit(emptyDataSet)

// In this example, the lemma dictionary `lemmas_small.txt` has the form of
//
// ...
// pick	->	pick	picks	picking	picked
// peck	->	peck	pecking	pecked	pecks
// pickle	->	pickle	pickles	pickled	pickling
// pepper	->	pepper	peppers	peppered	peppering
// ...
//
// where each key is delimited by `->` and values are delimited by `\t`

import spark.implicits._
import com.johnsnowlabs.nlp.DocumentAssembler
import com.johnsnowlabs.nlp.annotator.Tokenizer
import com.johnsnowlabs.nlp.annotator.SentenceDetector
import com.johnsnowlabs.nlp.annotators.Lemmatizer
import org.apache.spark.ml.Pipeline

val documentAssembler = new DocumentAssembler()
  .setInputCol("text")
  .setOutputCol("document")

val sentenceDetector = new SentenceDetector()
  .setInputCols(Array("document"))
  .setOutputCol("sentence")

val tokenizer = new Tokenizer()
  .setInputCols(Array("sentence"))
  .setOutputCol("token")

val lemmatizer = new Lemmatizer()
  .setInputCols(Array("token"))
  .setOutputCol("lemma")
  .setDictionary("src/test/resources/lemma-corpus-small/lemmas_small.txt", "->", "\t")

val pipeline = new Pipeline()
  .setStages(Array(
    documentAssembler,
    sentenceDetector,
    tokenizer,
    lemmatizer
  ))

val data = Seq("Peter Pipers employees are picking pecks of pickled peppers.")
  .toDF("text")

val result = pipeline.fit(data).transform(data)
result.selectExpr("lemma.result").show(false)
+------------------------------------------------------------------+
|result                                                            |
+------------------------------------------------------------------+
|[Peter, Pipers, employees, are, pick, peck, of, pickle, pepper, .]|
+------------------------------------------------------------------+

import spark.implicits._
import com.johnsnowlabs.nlp.base.DocumentAssembler
import com.johnsnowlabs.nlp.annotator.SentenceDetector
import com.johnsnowlabs.nlp.annotators.Tokenizer
import com.johnsnowlabs.nlp.training.POS
import com.johnsnowlabs.nlp.annotators.pos.perceptron.PerceptronApproach
import org.apache.spark.ml.Pipeline

val documentAssembler = new DocumentAssembler()
  .setInputCol("text")
  .setOutputCol("document")

val sentence = new SentenceDetector()
  .setInputCols("document")
  .setOutputCol("sentence")

val tokenizer = new Tokenizer()
  .setInputCols("sentence")
  .setOutputCol("token")

val datasetPath = "src/test/resources/anc-pos-corpus-small/test-training.txt"
val trainingPerceptronDF = POS().readDataset(spark, datasetPath)

val trainedPos = new PerceptronApproach()
  .setInputCols("document", "token")
  .setOutputCol("pos")
  .setPosColumn("tags")
  .fit(trainingPerceptronDF)

val pipeline = new Pipeline().setStages(Array(
  documentAssembler,
  sentence,
  tokenizer,
  trainedPos
))

val data = Seq("To be or not to be, is this the question?").toDF("text")
val result = pipeline.fit(data).transform(data)

result.selectExpr("pos.result").show(false)
+--------------------------------------------------+
|result                                            |
+--------------------------------------------------+
|[NNP, NNP, CD, JJ, NNP, NNP, ,, MD, VB, DT, CD, .]|
+--------------------------------------------------+

// The training process needs data, where each data point is a sentence.
// In this example the `train.txt` file has the form of
//
// ...
// Slightly more moderate language would make our present situation – namely the lack of progress – a little easier.
// His political successors now have great responsibilities to history and to the heritage of values bequeathed to them by Nelson Mandela.
// ...
//
// where each line is one sentence.
// Training can then be started like so:

import com.johnsnowlabs.nlp.base.DocumentAssembler
import com.johnsnowlabs.nlp.annotators.sentence_detector_dl.SentenceDetectorDLApproach
import org.apache.spark.ml.Pipeline

val trainingData = spark.read.text("train.txt").toDF("text")

val documentAssembler = new DocumentAssembler()
  .setInputCol("text")
  .setOutputCol("document")

val sentenceDetector = new SentenceDetectorDLApproach()
  .setInputCols(Array("document"))
  .setOutputCol("sentences")
  .setEpochsNumber(100)

val pipeline = new Pipeline().setStages(Array(documentAssembler, sentenceDetector))

val model = pipeline.fit(trainingData)

import spark.implicits._
import com.johnsnowlabs.nlp.base.DocumentAssembler
import com.johnsnowlabs.nlp.annotators.sbd.pragmatic.SentenceDetector
import com.johnsnowlabs.nlp.annotators.Tokenizer
import com.johnsnowlabs.nlp.annotators.pos.perceptron.PerceptronModel
import com.johnsnowlabs.nlp.annotators.parser.dep.DependencyParserModel
import com.johnsnowlabs.nlp.annotators.parser.typdep.TypedDependencyParserApproach
import org.apache.spark.ml.Pipeline

val documentAssembler = new DocumentAssembler()
  .setInputCol("text")
  .setOutputCol("document")

val sentence = new SentenceDetector()
  .setInputCols("document")
  .setOutputCol("sentence")

val tokenizer = new Tokenizer()
  .setInputCols("sentence")
  .setOutputCol("token")

val posTagger = PerceptronModel.pretrained()
  .setInputCols("sentence", "token")
  .setOutputCol("pos")

val dependencyParser = DependencyParserModel.pretrained()
  .setInputCols("sentence", "pos", "token")
  .setOutputCol("dependency")

val typedDependencyParser = new TypedDependencyParserApproach()
  .setInputCols("dependency", "pos", "token")
  .setOutputCol("dependency_type")
  .setConllU("src/test/resources/parser/labeled/train_small.conllu.txt")
  .setNumberOfIterations(1)

val pipeline = new Pipeline().setStages(Array(
  documentAssembler,
  sentence,
  tokenizer,
  posTagger,
  dependencyParser,
  typedDependencyParser
))

// Additional training data is not needed, the dependency parser relies on CoNLL-U only.
val emptyDataSet = Seq.empty[String].toDF("text")
val pipelineModel = pipeline.fit(emptyDataSet)

// In this example, `"chinese_train.utf8"` is in the form of
//
// 十|LL 四|RR 不|LL 是|RR 四|LL 十|RR
//
// and is loaded with the `POS` class to create a dataframe of `"POS"` type Annotations.

import com.johnsnowlabs.nlp.base.DocumentAssembler
import com.johnsnowlabs.nlp.annotators.ws.WordSegmenterApproach
import com.johnsnowlabs.nlp.training.POS
import org.apache.spark.ml.Pipeline

val documentAssembler = new DocumentAssembler()
  .setInputCol("text")
  .setOutputCol("document")

val wordSegmenter = new WordSegmenterApproach()
  .setInputCols("document")
  .setOutputCol("token")
  .setPosColumn("tags")
  .setNIterations(5)

val pipeline = new Pipeline().setStages(Array(
  documentAssembler,
  wordSegmenter
))

val trainingDataSet = POS().readDataset(
  ResourceHelper.spark,
  "src/test/resources/word-segmenter/chinese_train.utf8"
)

val pipelineModel = pipeline.fit(trainingDataSet)

// For this example, we use the first Sherlock Holmes book as the training dataset.

import spark.implicits._
import com.johnsnowlabs.nlp.base.DocumentAssembler
import com.johnsnowlabs.nlp.annotators.Tokenizer
import com.johnsnowlabs.nlp.annotators.spell.context.ContextSpellCheckerApproach

import org.apache.spark.ml.Pipeline

val documentAssembler = new DocumentAssembler()
  .setInputCol("text")
  .setOutputCol("document")


val tokenizer = new Tokenizer()
  .setInputCols("document")
  .setOutputCol("token")

val spellChecker = new ContextSpellCheckerApproach()
  .setInputCols("token")
  .setOutputCol("corrected")
  .setWordMaxDistance(3)
  .setBatchSize(24)
  .setEpochs(8)
  .setLanguageModelClasses(1650)  // dependant on vocabulary size
  // .addVocabClass("_NAME_", names) // Extra classes for correction could be added like this

val pipeline = new Pipeline().setStages(Array(
  documentAssembler,
  tokenizer,
  spellChecker
))

val path = "src/test/resources/spell/sherlockholmes.txt"
val dataset = spark.sparkContext.textFile(path)
  .toDF("text")
val pipelineModel = pipeline.fit(dataset)

import com.johnsnowlabs.nlp.base.DocumentAssembler
import com.johnsnowlabs.nlp.annotators.Tokenizer
import com.johnsnowlabs.nlp.annotators.spell.norvig.NorvigSweetingApproach
import org.apache.spark.ml.Pipeline

val documentAssembler = new DocumentAssembler()
  .setInputCol("text")
  .setOutputCol("document")

val tokenizer = new Tokenizer()
  .setInputCols("document")
  .setOutputCol("token")

val spellChecker = new NorvigSweetingApproach()
  .setInputCols("token")
  .setOutputCol("spell")
  .setDictionary("src/test/resources/spell/words.txt")

val pipeline = new Pipeline().setStages(Array(
  documentAssembler,
  tokenizer,
  spellChecker
))

val pipelineModel = pipeline.fit(trainingData)

import com.johnsnowlabs.nlp.base.DocumentAssembler
import com.johnsnowlabs.nlp.annotators.Tokenizer
import com.johnsnowlabs.nlp.annotators.spell.symmetric.SymmetricDeleteApproach
import org.apache.spark.ml.Pipeline

val documentAssembler = new DocumentAssembler()
  .setInputCol("text")
  .setOutputCol("document")

val tokenizer = new Tokenizer()
  .setInputCols("document")
  .setOutputCol("token")

val spellChecker = new SymmetricDeleteApproach()
  .setInputCols("token")
  .setOutputCol("spell")
  .setDictionary("src/test/resources/spell/words.txt")

val pipeline = new Pipeline().setStages(Array(
  documentAssembler,
  tokenizer,
  spellChecker
))

val pipelineModel = pipeline.fit(trainingData)

// This CoNLL dataset already includes the sentence, token, pos and label column with their respective annotator types.
// If a custom dataset is used, these need to be defined.

import com.johnsnowlabs.nlp.base.DocumentAssembler
import com.johnsnowlabs.nlp.embeddings.WordEmbeddingsModel
import com.johnsnowlabs.nlp.annotator.NerCrfApproach
import com.johnsnowlabs.nlp.training.CoNLL
import org.apache.spark.ml.Pipeline

val documentAssembler = new DocumentAssembler()
  .setInputCol("text")
  .setOutputCol("document")

val embeddings = WordEmbeddingsModel.pretrained()
  .setInputCols("sentence", "token")
  .setOutputCol("embeddings")
  .setCaseSensitive(false)

val nerTagger = new NerCrfApproach()
  .setInputCols("sentence", "token", "pos", "embeddings")
  .setLabelColumn("label")
  .setMinEpochs(1)
  .setMaxEpochs(3)
  .setC0(34)
  .setL2(3.0)
  .setOutputCol("ner")

val pipeline = new Pipeline().setStages(Array(
  documentAssembler,
  embeddings,
  nerTagger
))


val conll = CoNLL()
val trainingData = conll.readDataset(spark, "src/test/resources/conll2003/eng.train")

val pipelineModel = pipeline.fit(trainingData)

import com.johnsnowlabs.nlp.base.DocumentAssembler
import com.johnsnowlabs.nlp.annotators.Tokenizer
import com.johnsnowlabs.nlp.annotators.sbd.pragmatic.SentenceDetector
import com.johnsnowlabs.nlp.embeddings.BertEmbeddings
import com.johnsnowlabs.nlp.annotators.ner.dl.NerDLApproach
import com.johnsnowlabs.nlp.training.CoNLL
import org.apache.spark.ml.Pipeline

// First extract the prerequisites for the NerDLApproach
val documentAssembler = new DocumentAssembler()
  .setInputCol("text")
  .setOutputCol("document")

val sentence = new SentenceDetector()
  .setInputCols("document")
  .setOutputCol("sentence")

val tokenizer = new Tokenizer()
  .setInputCols("sentence")
  .setOutputCol("token")

val embeddings = BertEmbeddings.pretrained()
  .setInputCols("sentence", "token")
  .setOutputCol("embeddings")

// Then the training can start
val nerTagger = new NerDLApproach()
.setInputCols("sentence", "token", "embeddings")
.setLabelColumn("label")
.setOutputCol("ner")
.setMaxEpochs(1)
.setRandomSeed(0)
.setVerbose(0)

val pipeline = new Pipeline().setStages(Array(
  documentAssembler,
  sentence,
  tokenizer,
  embeddings,
  nerTagger
))

// We use the text and labels from the CoNLL dataset
val conll = CoNLL()
val trainingData = conll.readDataset(spark, "src/test/resources/conll2003/eng.train")

val pipelineModel = pipeline.fit(trainingData)

// In this example, the training data `"sentiment.csv"` has the form of
//
// text,label
// This movie is the best movie I have wached ever! In my opinion this movie can win an award.,0
// This was a terrible movie! The acting was bad really bad!,1
// ...
//
// Then traning can be done like so:

import com.johnsnowlabs.nlp.base.DocumentAssembler
import com.johnsnowlabs.nlp.embeddings.UniversalSentenceEncoder
import com.johnsnowlabs.nlp.annotators.classifier.dl.ClassifierDLApproach
import org.apache.spark.ml.Pipeline

val smallCorpus = spark.read.option("header","true").csv("src/test/resources/classifier/sentiment.csv")

val documentAssembler = new DocumentAssembler()
  .setInputCol("text")
  .setOutputCol("document")

val useEmbeddings = UniversalSentenceEncoder.pretrained()
  .setInputCols("document")
  .setOutputCol("sentence_embeddings")

val docClassifier = new ClassifierDLApproach()
  .setInputCols("sentence_embeddings")
  .setOutputCol("category")
  .setLabelColumn("label")
  .setBatchSize(64)
  .setMaxEpochs(20)
  .setLr(5e-3f)
  .setDropout(0.5f)

val pipeline = new Pipeline()
  .setStages(
    Array(
      documentAssembler,
      useEmbeddings,
      docClassifier
    )
  )

val pipelineModel = pipeline.fit(smallCorpus)

// In this example, the training data has the form (Note: labels can be arbitrary)
//
// mr,ref
// "name[Alimentum], area[city centre], familyFriendly[no], near[Burger King]",Alimentum is an adult establish found in the city centre area near Burger King.
// "name[Alimentum], area[city centre], familyFriendly[yes]",Alimentum is a family-friendly place in the city centre.
// ...
//
// It needs some pre-processing first, so the labels are of type `Array[String]`. This can be done like so:

import spark.implicits._
import com.johnsnowlabs.nlp.annotators.classifier.dl.MultiClassifierDLApproach
import com.johnsnowlabs.nlp.base.DocumentAssembler
import com.johnsnowlabs.nlp.embeddings.UniversalSentenceEncoder
import org.apache.spark.ml.Pipeline
import org.apache.spark.sql.functions.{col, udf}

// Process training data to create text with associated array of labels
def splitAndTrim = udf { labels: String =>
  labels.split(", ").map(x=>x.trim)
}

val smallCorpus = spark.read
  .option("header", true)
  .option("inferSchema", true)
  .option("mode", "DROPMALFORMED")
  .csv("src/test/resources/classifier/e2e.csv")
  .withColumn("labels", splitAndTrim(col("mr")))
  .withColumn("text", col("ref"))
  .drop("mr")

smallCorpus.printSchema()
// root
// |-- ref: string (nullable = true)
// |-- labels: array (nullable = true)
// |    |-- element: string (containsNull = true)

// Then create pipeline for training
val documentAssembler = new DocumentAssembler()
  .setInputCol("text")
  .setOutputCol("document")
  .setCleanupMode("shrink")

val embeddings = UniversalSentenceEncoder.pretrained()
  .setInputCols("document")
  .setOutputCol("embeddings")

val docClassifier = new MultiClassifierDLApproach()
  .setInputCols("embeddings")
  .setOutputCol("category")
  .setLabelColumn("labels")
  .setBatchSize(128)
  .setMaxEpochs(10)
  .setLr(1e-3f)
  .setThreshold(0.5f)
  .setValidationSplit(0.1f)

val pipeline = new Pipeline()
  .setStages(
    Array(
      documentAssembler,
      embeddings,
      docClassifier
    )
  )

val pipelineModel = pipeline.fit(smallCorpus)

// In this example, the training data has the form (Note: labels can be arbitrary)
//
// mr,ref
// "name[Alimentum], area[city centre], familyFriendly[no], near[Burger King]",Alimentum is an adult establish found in the city centre area near Burger King.
// "name[Alimentum], area[city centre], familyFriendly[yes]",Alimentum is a family-friendly place in the city centre.
// ...
//
// It needs some pre-processing first, so the labels are of type `Array[String]`. This can be done like so:

import spark.implicits._
import com.johnsnowlabs.nlp.annotators.classifier.dl.MultiClassifierDLApproach
import com.johnsnowlabs.nlp.base.DocumentAssembler
import com.johnsnowlabs.nlp.embeddings.UniversalSentenceEncoder
import org.apache.spark.ml.Pipeline
import org.apache.spark.sql.functions.{col, udf}

// Process training data to create text with associated array of labels
def splitAndTrim = udf { labels: String =>
  labels.split(", ").map(x=>x.trim)
}

val smallCorpus = spark.read
  .option("header", true)
  .option("inferSchema", true)
  .option("mode", "DROPMALFORMED")
  .csv("src/test/resources/classifier/e2e.csv")
  .withColumn("labels", splitAndTrim(col("mr")))
  .withColumn("text", col("ref"))
  .drop("mr")

smallCorpus.printSchema()
// root
// |-- ref: string (nullable = true)
// |-- labels: array (nullable = true)
// |    |-- element: string (containsNull = true)

// Then create pipeline for training
val documentAssembler = new DocumentAssembler()
  .setInputCol("text")
  .setOutputCol("document")
  .setCleanupMode("shrink")

val embeddings = UniversalSentenceEncoder.pretrained()
  .setInputCols("document")
  .setOutputCol("embeddings")

val docClassifier = new MultiClassifierDLApproach()
  .setInputCols("embeddings")
  .setOutputCol("category")
  .setLabelColumn("labels")
  .setBatchSize(128)
  .setMaxEpochs(10)
  .setLr(1e-3f)
  .setThreshold(0.5f)
  .setValidationSplit(0.1f)

val pipeline = new Pipeline()
  .setStages(
    Array(
      documentAssembler,
      embeddings,
      docClassifier
    )
  )

val pipelineModel = pipeline.fit(smallCorpus)

import spark.implicits._
import com.johnsnowlabs.nlp.base.DocumentAssembler
import com.johnsnowlabs.nlp.annotators.Tokenizer
import com.johnsnowlabs.nlp.annotators.Normalizer
import com.johnsnowlabs.nlp.annotators.sda.vivekn.ViveknSentimentApproach
import com.johnsnowlabs.nlp.Finisher
import org.apache.spark.ml.Pipeline

val document = new DocumentAssembler()
  .setInputCol("text")
  .setOutputCol("document")

val token = new Tokenizer()
  .setInputCols("document")
  .setOutputCol("token")

val normalizer = new Normalizer()
  .setInputCols("token")
  .setOutputCol("normal")

val vivekn = new ViveknSentimentApproach()
  .setInputCols("document", "normal")
  .setSentimentCol("train_sentiment")
  .setOutputCol("result_sentiment")

val finisher = new Finisher()
  .setInputCols("result_sentiment")
  .setOutputCols("final_sentiment")

val pipeline = new Pipeline().setStages(Array(document, token, normalizer, vivekn, finisher))

val training = Seq(
  ("I really liked this movie!", "positive"),
  ("The cast was horrible", "negative"),
  ("Never going to watch this again or recommend it to anyone", "negative"),
  ("It's a waste of time", "negative"),
  ("I loved the protagonist", "positive"),
  ("The music was really really good", "positive")
).toDF("text", "train_sentiment")
val pipelineModel = pipeline.fit(training)

val data = Seq(
  "I recommend this movie",
  "Dont waste your time!!!"
).toDF("text")
val result = pipelineModel.transform(data)

result.select("final_sentiment").show(false)
+---------------+
|final_sentiment|
+---------------+
|[positive]     |
|[negative]     |
+---------------+

// The model needs to be trained with the transformers library.
// Afterwards it can be loaded into the scala version of Spark NLP.

import spark.implicits._
import com.johnsnowlabs.nlp.base._
import com.johnsnowlabs.nlp.annotator._
import org.apache.spark.ml.Pipeline

val documentAssembler = new DocumentAssembler()
  .setInputCol("text")
  .setOutputCol("document")

val tokenizer = new Tokenizer()
  .setInputCols("document")
  .setOutputCol("token")

val modelName = "dslim/bert-base-NER"
var tokenClassifier = BertForTokenClassification.loadSavedModel(s"$modelName/saved_model/1", spark)
  .setInputCols("token", "document")
  .setOutputCol("label")
  .setCaseSensitive(true)
  .setMaxSentenceLength(128)

// Optionally the classifier can be saved to load it more conveniently into Spark NLP
tokenClassifier.write.overwrite.save(s"${modelName}_spark_nlp")

tokenClassifier = BertForTokenClassification.load(s"${modelName}_spark_nlp")
  .setInputCols("token", "document")
  .setOutputCol("label")
  .setCaseSensitive(true)

val pipeline = new Pipeline().setStages(Array(
  documentAssembler,
  tokenizer,
  tokenClassifier
))

val data = Seq("John Lenon was born in London and lived in Paris. My name is Sarah and I live in London").toDF("text")
val result = pipeline.fit(data).transform(data)

result.select("label.result").show(false)
+------------------------------------------------------------------------------------+
|result                                                                              |
+------------------------------------------------------------------------------------+
|[B-PER, I-PER, O, O, O, B-LOC, O, O, O, B-LOC, O, O, O, O, B-PER, O, O, O, O, B-LOC]|
+------------------------------------------------------------------------------------+

// The model needs to be trained with the transformers library.
// Afterwards it can be loaded into the scala version of Spark NLP.

import spark.implicits._
import com.johnsnowlabs.nlp.base._
import com.johnsnowlabs.nlp.annotator._
import org.apache.spark.ml.Pipeline

val documentAssembler = new DocumentAssembler()
  .setInputCol("text")
  .setOutputCol("document")

val tokenizer = new Tokenizer()
  .setInputCols("document")
  .setOutputCol("token")

val modelName = "elastic/distilbert-base-cased-finetuned-conll03-english"
var tokenClassifier = DistilBertForTokenClassification.loadSavedModel(s"$modelName/saved_model/1", spark)
  .setInputCols("token", "document")
  .setOutputCol("label")
  .setCaseSensitive(true)
  .setMaxSentenceLength(128)

// Optionally the classifier can be saved to load it more conveniently into Spark NLP
tokenClassifier.write.overwrite.save(s"${modelName}_spark_nlp")

tokenClassifier = DistilBertForTokenClassification.load(s"${modelName}_spark_nlp")
  .setInputCols("token", "document")
  .setOutputCol("label")
  .setCaseSensitive(true)

val pipeline = new Pipeline().setStages(Array(
  documentAssembler,
  tokenizer,
  tokenClassifier
))

val data = Seq("John Lenon was born in London and lived in Paris. My name is Sarah and I live in London").toDF("text")
val result = pipeline.fit(data).transform(data)

result.select("label.result").show(false)
+------------------------------------------------------------------------------------+
|result                                                                              |
+------------------------------------------------------------------------------------+
|[B-PER, I-PER, O, O, O, B-LOC, O, O, O, B-LOC, O, O, O, O, B-PER, O, O, O, O, B-LOC]|
+------------------------------------------------------------------------------------+