Package

com.johnsnowlabs.nlp.annotators

resolution

Permalink

package resolution

Visibility
  1. Public
  2. All

Type Members

  1. class BigChunkEntityResolverApproach extends AnnotatorApproach[BigChunkEntityResolverModel] with HasStorage with HasStorageReader with Licensed

    Permalink
  2. class BigChunkEntityResolverModel extends AnnotatorModel[BigChunkEntityResolverModel] with HasStorageModel with HasEmbeddingsProperties with Licensed

    Permalink
  3. case class BigFoundData(distance: Double, probability: Double, code: String, trained: Array[String], normalized: String) extends Product with Serializable

    Permalink
  4. class ChunkEntityResolverApproach extends AnnotatorApproach[ChunkEntityResolverModel] with Licensed

    Permalink
  5. class ChunkEntityResolverModel extends AnnotatorModel[ChunkEntityResolverModel] with HasStorageModel with HasEmbeddingsProperties with Licensed

    Permalink

    Contains all the parameters to transform a dataset with two Input Annotations of types TOKEN and WORD_EMBEDDINGS, coming from ChunkTokenizer and ChunkEmbeddings Annotators and return the Normalized Entity for a particular trained ontology / curated dataset.

  6. case class DistanceResult(distance: Double, weightedDistance: Double) extends Product with Serializable

    Permalink

    Class that contains distance in both representations: weighted and non-weighted, for using later in DistancePooling

  7. class EnsembleEntityResolverApproach extends AnnotatorApproach[EnsembleEntityResolverModel] with Licensed with EnsembleApproachClassifierParams with EnsembleModelResolverParams with EnsembleApproachResolverParams with StringFunctions

    Permalink

    Trains a model given two Input Annotators of types TOKEN and WORD_EMBEDDINGS, coming from ChunkTokenizer and ChunkEmbeddings Annotators

    Trains a model given two Input Annotators of types TOKEN and WORD_EMBEDDINGS, coming from ChunkTokenizer and ChunkEmbeddings Annotators

    The returned EnsembleEntityResolverModel consists of two layers: - First a TFIDF + OvrLogRegClassifier on top of the TOKEN Annotations - Second a set of ChunkEntityResolversModels, one per each different class from the first layer

    This approach allows Spark NLP's Entity Resolution Architecture to scale to a few millions of rows [codes]

  8. class EnsembleEntityResolverModel extends Model[EnsembleEntityResolverModel] with RawAnnotator[EnsembleEntityResolverModel] with EnsembleModelResolverParams with EnsembleModelParams with StringFunctions with CanBeLazy with Licensed

    Permalink

    Contains all the parameters to transform a dataset with two Input Annotations of types TOKEN and WORD_EMBEDDINGS, coming from ChunkTokenizer and ChunkEmbeddings Annotators and return the Normalized Entity for a particular trained ontology / curated dataset.

    Contains all the parameters to transform a dataset with two Input Annotations of types TOKEN and WORD_EMBEDDINGS, coming from ChunkTokenizer and ChunkEmbeddings Annotators and return the Normalized Entity for a particular trained ontology / curated dataset.

    This EnsembleChunkEntityResolverModel consists of two layers: First a TFIDF + OvrLogRegClassifier on top of the TOKEN Annotations Second a set of ChunkEntityResolversModels, one per each different class from the first layer

    This architecture allows Spark NLP's Entity Resolution Architecture to scale to a few millions of rows [codes]

  9. class JDataReader extends AnyRef

    Permalink
  10. case class JTreeComponent(embeddings: Array[Float], data: JTreeData) extends Product with Serializable

    Permalink
  11. case class JTreeData(code: String, trained: Array[String], normalized: String) extends Product with Serializable

    Permalink
  12. class JTreeReader extends StorageReader[JTreeComponent]

    Permalink
  13. class JTreeWriter extends StorageBatchWriter[JTreeComponent]

    Permalink
  14. trait ReadablePretrainedBigChunkEntityResolver extends StorageReadable[BigChunkEntityResolverModel] with HasPretrained[BigChunkEntityResolverModel] with EvalEntityResolver

    Permalink
  15. trait ReadablePretrainedChunkEntityResolver extends ParamsAndFeaturesReadable[ChunkEntityResolverModel] with HasPretrained[ChunkEntityResolverModel] with EvalEntityResolver

    Permalink
  16. trait ReadablePretrainedEnsembleEntityResolver extends ParamsAndFeaturesReadable[EnsembleEntityResolverModel] with EvalEntityResolver with HasPretrained[EnsembleEntityResolverModel]

    Permalink
  17. case class TreeData(code: String, trained: Array[String], normalized: String) extends Product with Serializable

    Permalink

Value Members

  1. object BigChunkEntityResolverModel extends ReadablePretrainedBigChunkEntityResolver with Serializable

    Permalink
  2. object ChunkEntityResolverModel extends ReadablePretrainedChunkEntityResolver with Serializable

    Permalink
  3. object DistanceFunction

    Permalink

    Helper object to use while setting distanceFunction parameter

  4. object EnsembleEntityResolverModel extends ReadablePretrainedEnsembleEntityResolver with Serializable

    Permalink
  5. object PoolingStrategy

    Permalink

    Helper object to use while setting poolingStrategy parameter

  6. package ensemble

    Permalink

Ungrouped