com.johnsnowlabs.nlp.embeddings
internal types to show Rows as a relevant StructType Should be deleted once Spark releases UserDefinedTypes to @developerAPI
internal types to show Rows as a relevant StructType Should be deleted once Spark releases UserDefinedTypes to @developerAPI
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
Annotations that correspond to inputAnnotationCols generated by previous annotators if any
any number of annotations processed for every input annotation. Not necessary one to one relationship
Batch size.
Batch size. Large values allows faster processing but requires more memory.
ConfigProto from tensorflow, serialized into byte array.
ConfigProto from tensorflow, serialized into byte array. Get with config_proto.SerializeToString()
requirement for annotators copies
requirement for annotators copies
Wraps annotate to happen inside SparkSQL user defined functions in order to act with org.apache.spark.sql.Column
Wraps annotate to happen inside SparkSQL user defined functions in order to act with org.apache.spark.sql.Column
udf function to be applied to inputCols using this annotator's annotate function as part of ML transformation
Override for additional custom schema checks
Override for additional custom schema checks
input annotations columns currently used
Gets annotation column name going to generate
Gets annotation column name going to generate
Function used to set the embedding output layer of the ELMO model word_emb: the character-based word representations with shape [batch_size, max_length, 512].
Function used to set the embedding output layer of the ELMO model word_emb: the character-based word representations with shape [batch_size, max_length, 512]. == word_emb lstm_outputs1: the first LSTM hidden state with shape [batch_size, max_length, 1024]. === lstm_outputs1 lstm_outputs2: the second LSTM hidden state with shape [batch_size, max_length, 1024]. === lstm_outputs2 elmo: the weighted sum of the 3 layers, where the weights are trainable. This tensor has shape [batch_size, max_length, 1024] == elmo
Output annotator type : TOKEN
Output annotator type : TOKEN
columns that contain annotations necessary to run this annotator AnnotatorType is used both as input and output columns if not specified
columns that contain annotations necessary to run this annotator AnnotatorType is used both as input and output columns if not specified
Output annotator type : WORD_EMBEDDINGS
Output annotator type : WORD_EMBEDDINGS
Set ELMO pooling layer to: word_emb, lstm_outputs1, lstm_outputs2, or elmo
Large values allows faster processing but requires more memory.
ConfigProto from tensorflow, serialized into byte array.
ConfigProto from tensorflow, serialized into byte array. Get with config_proto.SerializeToString()
Set Dimension of pooling layer.
Set Dimension of pooling layer. This is meta for the annotation and will not affect the actual embedding calculation.
Overrides required annotators column if different than default
Overrides required annotators column if different than default
Overrides annotation column name when transforming
Overrides annotation column name when transforming
Function used to set the embedding output layer of the ELMO model word_emb: the character-based word representations with shape [batch_size, max_length, 512].
Function used to set the embedding output layer of the ELMO model word_emb: the character-based word representations with shape [batch_size, max_length, 512]. == word_emb lstm_outputs1: the first LSTM hidden state with shape [batch_size, max_length, 1024]. === lstm_outputs1 lstm_outputs2: the second LSTM hidden state with shape [batch_size, max_length, 1024]. === lstm_outputs2 elmo: the weighted sum of the 3 layers, where the weights are trainable. This tensor has shape [batch_size, max_length, 1024] == elmo
Layer specification
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[Row]
requirement for pipeline transformation validation.
requirement for pipeline transformation validation. It is called on fit()
takes a Dataset and checks to see if all the required annotation types are present.
takes a Dataset and checks to see if all the required annotation types are present.
to be validated
True if all the required types are present, else false
Required input and expected output annotator types
Embeddings from a language model trained on the 1 Billion Word Benchmark.
Note that this is a very computationally expensive module compared to word embedding modules that only perform embedding lookups. The use of an accelerator is recommended.
word_emb: the character-based word representations with shape [batch_size, max_length, 512]. == word_emb
lstm_outputs1: the first LSTM hidden state with shape [batch_size, max_length, 1024]. === lstm_outputs1
lstm_outputs2: the second LSTM hidden state with shape [batch_size, max_length, 1024]. === lstm_outputs2
elmo: the weighted sum of the 3 layers, where the weights are trainable. This tensor has shape [batch_size, max_length, 1024] == elmo
See https://github.com/JohnSnowLabs/spark-nlp/blob/master/src/test/scala/com/johnsnowlabs/nlp/embeddings/ElmoEmbeddingsTestSpec.scala for further reference on how to use this API.
Sources :
https://tfhub.dev/google/elmo/3
https://arxiv.org/abs/1802.05365
Paper abstract :
We introduce a new type of deep contextualized word representation that models both (1) complex characteristics of word use (e.g., syntax and semantics), and (2) how these uses vary across linguistic contexts (i.e., to model polysemy). Our word vectors are learned functions of the internal states of a deep bidirectional language model (biLM), which is pre-trained on a large text corpus. We show that these representations can be easily added to existing models and significantly improve the state of the art across six challenging NLP problems, including question answering, textual entailment and sentiment analysis. We also present an analysis showing that exposing the deep internals of the pre-trained network is crucial, allowing downstream models to mix different types of semi-supervision signals.