Extract relations between effects of using multiple drugs (ReDL)

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

val sentencer = new SentenceDetector()
    .setInputCols("document")
    .setOutputCol("sentences")

val tokenizer = new Tokenizer()
    .setInputCols("sentences")
    .setOutputCol("tokens")

val pos_tagger = PerceptronModel()
    .pretrained("pos_clinical", "en", "clinical/models") 
    .setInputCols(Array("sentences", "tokens"))
    .setOutputCol("pos_tags")

val words_embedder = WordEmbeddingsModel()
    .pretrained("embeddings_clinical", "en", "clinical/models")
    .setInputCols(Array("sentences", "tokens"))
    .setOutputCol("embeddings")

val ner_tagger = MedicalNerModel.pretrained("ner_posology", "en", "clinical/models")
    .setInputCols(Array("sentences", "tokens", "embeddings"))
    .setOutputCol("ner_tags") 

val ner_converter = new NerConverterInternal()
    .setInputCols(Array("sentences", "tokens", "ner_tags"))
    .setOutputCol("ner_chunks")

val dependency_parser = DependencyParserModel()
    .pretrained("dependency_conllu", "en")
    .setInputCols(Array("sentences", "pos_tags", "tokens"))
    .setOutputCol("dependencies")

// Set a filter on pairs of named entities which will be treated as relation candidates
val re_ner_chunk_filter = new RENerChunksFilter()
    .setInputCols(Array("ner_chunks", "dependencies"))
    .setMaxSyntacticDistance(10)
    .setOutputCol("re_ner_chunks")
    // .setRelationPairs(Array('SYMPTOM-EXTERNAL_BODY_PART_OR_REGION'))

// The dataset this model is trained to is sentence-wise. 
// This model can also be trained on document-level relations - in which case, while predicting, use "document" instead of "sentence" as input.
val re_model = RelationExtractionDLModel()
    .pretrained("redl_drug_drug_interaction_biobert", "en", "clinical/models")
    .setPredictionThreshold(0.5)
    .setInputCols(Array("re_ner_chunks", "sentences"))
    .setOutputCol("relations")

val pipeline = new Pipeline().setStages(Array(documenter, sentencer, tokenizer, pos_tagger, words_embedder, ner_tagger, ner_converter, dependency_parser, re_ner_chunk_filter, re_model))

val data = Seq("""When carbamazepine is withdrawn from the combination therapy, aripiprazole dose should then be reduced. If additional adrenergic drugs are to be administered by any route, they should be used with caution because the pharmacologically predictable sympathetic effects of Metformin may be potentiated""").toDS.toDF("text")

val result = pipeline.fit(data).transform(data)