nlp_sentence_entity_resolver: Spark NLP SentenceEntityResolverApproach

In r-spark/sparknlp: R Interface to John Snow Labs Spark NLP

Spark NLP SentenceEntityResolverApproach

Description

Spark ML estimator that assigns a standard code (ICD10 CM, PCS, ICDO; CPT) to sentence embeddings pooled over chunks from TextMatchers or the NER Models. This annotator is particularly handy when working with BertSentenceEmbeddings from the upstream chunks.

Usage

nlp_sentence_entity_resolver(
  x,
  input_cols,
  output_col,
  label_column = NULL,
  normalized_col = NULL,
  neighbors = NULL,
  threshold = NULL,
  miss_as_empty = NULL,
  case_sensitive = NULL,
  confidence_function = NULL,
  distance_function = NULL,
  uid = random_string("sentence_entity_resolver_")
)

Arguments

x	A spark_connection, ml_pipeline, or a tbl_spark.
input_cols	Input columns. String array.
output_col	Output column. String.
label_column	column name for the value we are trying to resolve
normalized_col	column name for the original, normalized description
neighbors	number of neighbors to consider in the KNN query to calculate WMD
threshold	threshold value for the aggregated distance
miss_as_empty	whether or not to return an empty annotation on unmatched chunks
case_sensitive	whether the entity should be considered using case sensitivity
confidence_function	what function to use to calculate confidence: INVERSE or SOFTMAX
distance_function	what distance function to use for KNN: 'EUCLIDEAN' or 'COSINE'
uid	A character string used to uniquely identify the ML estimator.

Details

See https://nlp.johnsnowlabs.com/docs/en/licensed_annotators#sentenceentityresolver

Value

The object returned depends on the class of x.

• spark_connection: When x is a spark_connection, the function returns an instance of a ml_estimator object. The object contains a pointer to a Spark Estimator object and can be used to compose Pipeline objects.

• ml_pipeline: When x is a ml_pipeline, the function returns a ml_pipeline with the NLP estimator appended to the pipeline.

• tbl_spark: When x is a tbl_spark, an estimator is constructed then immediately fit with the input tbl_spark, returning an NLP model.

r-spark/sparknlp documentation built on Oct. 15, 2022, 10:50 a.m.