Description
Extract key entities in financial contracts using pretrained NER model.
Predicted Entities
ORG, PER, MISC, LOC
How to use
document_assembler = DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("document")
sentenceDetector = SentenceDetectorDLModel.pretrained("sentence_detector_dl_healthcare","en","clinical/models")\
.setInputCols(["document"])\
.setOutputCol("sentence")
tokenizer = Tokenizer()\
.setInputCols(["sentence"])\
.setOutputCol("token")
embeddings = WordEmbeddingsModel.pretrained("glove_6B_300", "xx")\
.setInputCols("sentence", "token")\
.setOutputCol("embeddings")
clinical_ner = MedicalNerModel.pretrained("ner_financial_contract", "en", "clinical/models")\
.setInputCols(["sentence", "token", "embeddings"])\
.setOutputCol("ner")
ner_converter = NerConverter()\
.setInputCols(["sentence", "token", "ner"])\
.setOutputCol("ner_chunk")
nlpPipeline = Pipeline(stages=[document_assembler, sentenceDetector, tokenizer, embeddings, clinical_ner, ner_converter])
empty_data = spark.createDataFrame([[""]]).toDF("text")
model = nlpPipeline.fit(empty_data)
text = """Hans is a professor at the Norwegian University of Copenhagen, and he is a true Copenhagener."""
result = model.transform(spark.createDataFrame([[text]]).toDF("text"))
document_assembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
sentenceDetector = SentenceDetectorDLModel.pretrained("sentence_detector_dl_healthcare","en","clinical/models")
.setInputCols("document")
.setOutputCol("sentence")
tokenizer = new Tokenizer()
.setInputCols("sentence")
.setOutputCol("token")
embeddings = WordEmbeddingsModel.pretrained("glove_6B_300", "xx")
.setInputCols(Array("sentence", "token"))
.setOutputCol("embeddings")
clinical_ner = MedicalNerModel.pretrained("ner_financial_contract", "en", "clinical/models")
.setInputCols(Array("sentence", "token", "embeddings"))
.setOutputCol("ner")
ner_converter = new NerConverter()
.setInputCols(Array("sentence", "token", "ner"))
.setOutputCol("ner_chunk")
val pipeline = new Pipeline().setStages(Array(document_assembler, sentenceDetector, tokenizer, embeddings, clinical_ner, ner_converter))
val data = Seq("""Hans is a professor at the Norwegian University of Copenhagen, and he is a true Copenhagener.""").toDS.toDF("text")
val result = pipeline.fit(data).transform(data)
import nlu
nlu.load("en.med_ner.financial_contract").predict("""Put your text here.""")
Results
+--------------------+---------+
|chunk |ner_label|
+--------------------+---------+
|professor |PER |
|Norwegian University|PER |
|Copenhagen |LOC |
+--------------------+---------+
Model Information
| Model Name: | ner_financial_contract |
| Compatibility: | Healthcare NLP 3.0.0+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [sentence, token, embeddings] |
| Output Labels: | [ner] |
| Language: | en |