class MPNetEmbeddings extends AnnotatorModel[MPNetEmbeddings] with HasBatchedAnnotate[MPNetEmbeddings] with WriteTensorflowModel with WriteOnnxModel with WriteOpenvinoModel with HasEmbeddingsProperties with HasStorageRef with HasCaseSensitiveProperties with HasEngine
Sentence embeddings using MPNet.
The MPNet model was proposed in MPNet: Masked and Permuted Pre-training for Language Understanding by Kaitao Song, Xu Tan, Tao Qin, Jianfeng Lu, Tie-Yan Liu. MPNet adopts a novel pre-training method, named masked and permuted language modeling, to inherit the advantages of masked language modeling and permuted language modeling for natural language understanding.
Note that this annotator is only supported for Spark Versions 3.4 and up.
Pretrained models can be loaded with pretrained
of the companion object:
val embeddings = MPNetEmbeddings.pretrained() .setInputCols("document") .setOutputCol("mpnet_embeddings")
The default model is "all_mpnet_base_v2"
, if no name is provided.
For available pretrained models please see the Models Hub.
For extended examples of usage, see MPNetEmbeddingsTestSpec.
Sources :
MPNet: Masked and Permuted Pre-training for Language Understanding
Paper abstract
BERT adopts masked language modeling (MLM) for pre-training and is one of the most successful pre-training models. Since BERT neglects dependency among predicted tokens, XLNet introduces permuted language modeling (PLM) for pre-training to address this problem. However, XLNet does not leverage the full position information of a sentence and thus suffers from position discrepancy between pre-training and fine-tuning. In this paper, we propose MPNet, a novel pre-training method that inherits the advantages of BERT and XLNet and avoids their limitations. MPNet leverages the dependency among predicted tokens through permuted language modeling (vs. MLM in BERT), and takes auxiliary position information as input to make the model see a full sentence and thus reducing the position discrepancy (vs. PLM in XLNet). We pre-train MPNet on a large-scale dataset (over 160GB text corpora) and fine-tune on a variety of down-streaming tasks (GLUE, SQuAD, etc). Experimental results show that MPNet outperforms MLM and PLM by a large margin, and achieves better results on these tasks compared with previous state-of-the-art pre-trained methods (e.g., BERT, XLNet, RoBERTa) under the same model setting.
Example
import spark.implicits._ import com.johnsnowlabs.nlp.base.DocumentAssembler import com.johnsnowlabs.nlp.annotators.Tokenizer import com.johnsnowlabs.nlp.embeddings.MPNetEmbeddings import com.johnsnowlabs.nlp.EmbeddingsFinisher import org.apache.spark.ml.Pipeline val documentAssembler = new DocumentAssembler() .setInputCol("text") .setOutputCol("document") val embeddings = MPNetEmbeddings.pretrained("all_mpnet_base_v2", "en") .setInputCols("document") .setOutputCol("mpnet_embeddings") val embeddingsFinisher = new EmbeddingsFinisher() .setInputCols("mpnet_embeddings") .setOutputCols("finished_embeddings") .setOutputAsVector(true) val pipeline = new Pipeline().setStages(Array( documentAssembler, embeddings, embeddingsFinisher )) val data = Seq("This is an example sentence", "Each sentence is converted").toDF("text") val result = pipeline.fit(data).transform(data) result.selectExpr("explode(finished_embeddings) as result").show(1, 80) +--------------------------------------------------------------------------------+ | result| +--------------------------------------------------------------------------------+ |[[0.022502584, -0.078291744, -0.023030775, -0.0051000593, -0.080340415, 0.039...| |[[0.041702367, 0.0010974605, -0.015534201, 0.07092203, -0.0017729357, 0.04661...| +--------------------------------------------------------------------------------+
- See also
Annotators Main Page for a list of transformer based embeddings
- Grouped
- Alphabetic
- By Inheritance
- MPNetEmbeddings
- HasEngine
- HasCaseSensitiveProperties
- HasStorageRef
- HasEmbeddingsProperties
- HasProtectedParams
- WriteOpenvinoModel
- WriteOnnxModel
- WriteTensorflowModel
- HasBatchedAnnotate
- AnnotatorModel
- CanBeLazy
- RawAnnotator
- HasOutputAnnotationCol
- HasInputAnnotationCols
- HasOutputAnnotatorType
- ParamsAndFeaturesWritable
- HasFeatures
- DefaultParamsWritable
- MLWritable
- Model
- Transformer
- PipelineStage
- Logging
- Params
- Serializable
- Serializable
- Identifiable
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Parameters
A list of (hyper-)parameter keys this annotator can take. Users can set and get the parameter values through setters and getters, respectively.
-
val
batchSize: IntParam
Size of every batch (Default depends on model).
Size of every batch (Default depends on model).
- Definition Classes
- HasBatchedAnnotate
-
val
caseSensitive: BooleanParam
Whether to ignore case in index lookups (Default depends on model)
Whether to ignore case in index lookups (Default depends on model)
- Definition Classes
- HasCaseSensitiveProperties
-
val
configProtoBytes: IntArrayParam
ConfigProto from tensorflow, serialized into byte array.
ConfigProto from tensorflow, serialized into byte array. Get with
config_proto.SerializeToString()
-
val
dimension: ProtectedParam[Int]
Number of embedding dimensions (Default depends on model)
Number of embedding dimensions (Default depends on model)
- Definition Classes
- HasEmbeddingsProperties
-
val
engine: Param[String]
This param is set internally once via loadSavedModel.
This param is set internally once via loadSavedModel. That's why there is no setter
- Definition Classes
- HasEngine
-
val
maxSentenceLength: IntParam
Max sentence length to process (Default:
128
) -
val
signatures: MapFeature[String, String]
It contains TF model signatures for the laded saved model
-
val
storageRef: Param[String]
Unique identifier for storage (Default:
this.uid
)Unique identifier for storage (Default:
this.uid
)- Definition Classes
- HasStorageRef
-
val
vocabulary: MapFeature[String, Int]
Vocabulary used to encode the words to ids with WordPieceEncoder
Members
-
implicit
class
ProtectedParam[T] extends Param[T]
- Definition Classes
- HasProtectedParams
-
type
AnnotatorType = String
- Definition Classes
- HasOutputAnnotatorType
-
def
batchAnnotate(batchedAnnotations: Seq[Array[Annotation]]): Seq[Seq[Annotation]]
takes a document and annotations and produces new annotations of this annotator's annotation type
takes a document and annotations and produces new annotations of this annotator's annotation type
- batchedAnnotations
Annotations that correspond to inputAnnotationCols generated by previous annotators if any
- returns
any number of annotations processed for every input annotation. Not necessary one to one relationship
- Definition Classes
- MPNetEmbeddings → HasBatchedAnnotate
-
def
batchProcess(rows: Iterator[_]): Iterator[Row]
- Definition Classes
- HasBatchedAnnotate
-
final
def
clear(param: Param[_]): MPNetEmbeddings.this.type
- Definition Classes
- Params
-
def
copy(extra: ParamMap): MPNetEmbeddings
requirement for annotators copies
requirement for annotators copies
- Definition Classes
- RawAnnotator → Model → Transformer → PipelineStage → Params
-
def
createDatabaseConnection(database: Name): RocksDBConnection
- Definition Classes
- HasStorageRef
-
def
explainParam(param: Param[_]): String
- Definition Classes
- Params
-
def
explainParams(): String
- Definition Classes
- Params
-
final
def
extractParamMap(): ParamMap
- Definition Classes
- Params
-
final
def
extractParamMap(extra: ParamMap): ParamMap
- Definition Classes
- Params
-
val
features: ArrayBuffer[Feature[_, _, _]]
- Definition Classes
- HasFeatures
-
final
def
get[T](param: Param[T]): Option[T]
- Definition Classes
- Params
-
final
def
getDefault[T](param: Param[T]): Option[T]
- Definition Classes
- Params
-
def
getInputCols: Array[String]
- returns
input annotations columns currently used
- Definition Classes
- HasInputAnnotationCols
-
def
getLazyAnnotator: Boolean
- Definition Classes
- CanBeLazy
-
final
def
getOrDefault[T](param: Param[T]): T
- Definition Classes
- Params
-
final
def
getOutputCol: String
Gets annotation column name going to generate
Gets annotation column name going to generate
- Definition Classes
- HasOutputAnnotationCol
-
def
getParam(paramName: String): Param[Any]
- Definition Classes
- Params
-
def
getStorageRef: String
- Definition Classes
- HasStorageRef
-
final
def
hasDefault[T](param: Param[T]): Boolean
- Definition Classes
- Params
-
def
hasParam(paramName: String): Boolean
- Definition Classes
- Params
-
def
hasParent: Boolean
- Definition Classes
- Model
-
val
inputAnnotatorTypes: Array[String]
Annotator reference id.
Annotator reference id. Used to identify elements in metadata or to refer to this annotator type
- Definition Classes
- MPNetEmbeddings → HasInputAnnotationCols
-
final
def
isDefined(param: Param[_]): Boolean
- Definition Classes
- Params
-
final
def
isSet(param: Param[_]): Boolean
- Definition Classes
- Params
-
val
lazyAnnotator: BooleanParam
- Definition Classes
- CanBeLazy
-
def
onWrite(path: String, spark: SparkSession): Unit
- Definition Classes
- MPNetEmbeddings → ParamsAndFeaturesWritable
-
val
optionalInputAnnotatorTypes: Array[String]
- Definition Classes
- HasInputAnnotationCols
-
val
outputAnnotatorType: AnnotatorType
- Definition Classes
- MPNetEmbeddings → HasOutputAnnotatorType
-
lazy val
params: Array[Param[_]]
- Definition Classes
- Params
-
var
parent: Estimator[MPNetEmbeddings]
- Definition Classes
- Model
-
def
save(path: String): Unit
- Definition Classes
- MLWritable
- Annotations
- @Since( "1.6.0" ) @throws( ... )
- def sentenceStartTokenId: Int
-
def
set[T](param: ProtectedParam[T], value: T): MPNetEmbeddings.this.type
Sets the value for a protected Param.
Sets the value for a protected Param.
If the parameter was already set, it will not be set again. Default values do not count as a set value and can be overridden.
- T
Type of the parameter
- param
Protected parameter to set
- value
Value for the parameter
- returns
This object
- Definition Classes
- HasProtectedParams
-
final
def
set[T](param: Param[T], value: T): MPNetEmbeddings.this.type
- Definition Classes
- Params
-
final
def
setInputCols(value: String*): MPNetEmbeddings.this.type
- Definition Classes
- HasInputAnnotationCols
-
def
setInputCols(value: Array[String]): MPNetEmbeddings.this.type
Overrides required annotators column if different than default
Overrides required annotators column if different than default
- Definition Classes
- HasInputAnnotationCols
-
def
setLazyAnnotator(value: Boolean): MPNetEmbeddings.this.type
- Definition Classes
- CanBeLazy
-
final
def
setOutputCol(value: String): MPNetEmbeddings.this.type
Overrides annotation column name when transforming
Overrides annotation column name when transforming
- Definition Classes
- HasOutputAnnotationCol
-
def
setParent(parent: Estimator[MPNetEmbeddings]): MPNetEmbeddings
- Definition Classes
- Model
-
def
setStorageRef(value: String): MPNetEmbeddings.this.type
- Definition Classes
- HasStorageRef
-
def
toString(): String
- Definition Classes
- Identifiable → AnyRef → Any
- def tokenize(sentences: Seq[Annotation]): Seq[WordpieceTokenizedSentence]
-
final
def
transform(dataset: Dataset[_]): DataFrame
Given requirements are met, this applies ML transformation within a Pipeline or stand-alone Output annotation will be generated as a new column, previous annotations are still available separately metadata is built at schema level to record annotations structural information outside its content
Given requirements are met, this applies ML transformation within a Pipeline or stand-alone Output annotation will be generated as a new column, previous annotations are still available separately metadata is built at schema level to record annotations structural information outside its content
- dataset
Dataset[Row]
- Definition Classes
- AnnotatorModel → Transformer
-
def
transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame
- Definition Classes
- Transformer
- Annotations
- @Since( "2.0.0" )
-
def
transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame
- Definition Classes
- Transformer
- Annotations
- @Since( "2.0.0" ) @varargs()
-
final
def
transformSchema(schema: StructType): StructType
requirement for pipeline transformation validation.
requirement for pipeline transformation validation. It is called on fit()
- Definition Classes
- RawAnnotator → PipelineStage
-
val
uid: String
- Definition Classes
- MPNetEmbeddings → Identifiable
-
def
validateStorageRef(dataset: Dataset[_], inputCols: Array[String], annotatorType: String): Unit
- Definition Classes
- HasStorageRef
-
def
write: MLWriter
- Definition Classes
- ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable
-
def
writeOnnxModel(path: String, spark: SparkSession, onnxWrapper: OnnxWrapper, suffix: String, fileName: String): Unit
- Definition Classes
- WriteOnnxModel
-
def
writeOnnxModels(path: String, spark: SparkSession, onnxWrappersWithNames: Seq[(OnnxWrapper, String)], suffix: String): Unit
- Definition Classes
- WriteOnnxModel
-
def
writeOpenvinoModel(path: String, spark: SparkSession, openvinoWrapper: OpenvinoWrapper, suffix: String, fileName: String): Unit
- Definition Classes
- WriteOpenvinoModel
-
def
writeOpenvinoModels(path: String, spark: SparkSession, ovWrappersWithNames: Seq[(OpenvinoWrapper, String)], suffix: String): Unit
- Definition Classes
- WriteOpenvinoModel
-
def
writeTensorflowHub(path: String, tfPath: String, spark: SparkSession, suffix: String = "_use"): Unit
- Definition Classes
- WriteTensorflowModel
-
def
writeTensorflowModel(path: String, spark: SparkSession, tensorflow: TensorflowWrapper, suffix: String, filename: String, configProtoBytes: Option[Array[Byte]] = None): Unit
- Definition Classes
- WriteTensorflowModel
-
def
writeTensorflowModelV2(path: String, spark: SparkSession, tensorflow: TensorflowWrapper, suffix: String, filename: String, configProtoBytes: Option[Array[Byte]] = None, savedSignatures: Option[Map[String, String]] = None): Unit
- Definition Classes
- WriteTensorflowModel
Parameter setters
- def sentenceEndTokenId: Int
-
def
setBatchSize(size: Int): MPNetEmbeddings.this.type
Size of every batch.
Size of every batch.
- Definition Classes
- HasBatchedAnnotate
-
def
setCaseSensitive(value: Boolean): MPNetEmbeddings.this.type
Whether to lowercase tokens or not
Whether to lowercase tokens or not
- Definition Classes
- MPNetEmbeddings → HasCaseSensitiveProperties
- def setConfigProtoBytes(bytes: Array[Int]): MPNetEmbeddings.this.type
-
def
setDimension(value: Int): MPNetEmbeddings.this.type
Set Embeddings dimensions for the BERT model Only possible to set this when the first time is saved dimension is not changeable, it comes from BERT config file
Set Embeddings dimensions for the BERT model Only possible to set this when the first time is saved dimension is not changeable, it comes from BERT config file
- Definition Classes
- MPNetEmbeddings → HasEmbeddingsProperties
- def setMaxSentenceLength(value: Int): MPNetEmbeddings.this.type
- def setModelIfNotSet(spark: SparkSession, tensorflowWrapper: Option[TensorflowWrapper], onnxWrapper: Option[OnnxWrapper], openvinoWrapper: Option[OpenvinoWrapper]): MPNetEmbeddings
- def setSignatures(value: Map[String, String]): MPNetEmbeddings.this.type
- def setVocabulary(value: Map[String, Int]): MPNetEmbeddings.this.type
Parameter getters
-
def
getBatchSize: Int
Size of every batch.
Size of every batch.
- Definition Classes
- HasBatchedAnnotate
-
def
getCaseSensitive: Boolean
- Definition Classes
- HasCaseSensitiveProperties
- def getConfigProtoBytes: Option[Array[Byte]]
-
def
getDimension: Int
- Definition Classes
- HasEmbeddingsProperties
-
def
getEngine: String
- Definition Classes
- HasEngine
- def getMaxSentenceLength: Int
- def getModelIfNotSet: MPNet
- def getSignatures: Option[Map[String, String]]