Relation Extraction Between Body Parts and Procedures

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

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

val tokenizer = new Tokenizer()
.setInputCols(Array("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_jsl_greedy", "en", "clinical/models")
.setInputCols(Array("sentences", "tokens", "embeddings"))
.setOutputCol("ner_tags") 

val ner_converter = new NerConverter()
.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 = RENerChunksFilter()
.setInputCols(Array("ner_chunks", "dependencies"))
.setMaxSyntacticDistance(10)
.setOutputCol("re_ner_chunks").
setRelationPairs(Array("external_body_part_or_region-test"))

// 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_bodypart_procedure_test_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("""TECHNIQUE IN DETAIL: After informed consent was obtained from the patient and his mother, the chest was scanned with portable ultrasound.""").toDS.toDF("text")

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