sparknlp.annotator.embeddings.bert_sentence_embeddings#

Classes#

class BertSentenceEmbeddings(classname='com.johnsnowlabs.nlp.embeddings.BertSentenceEmbeddings', java_model=None)[source]#

Sentence-level embeddings using BERT. BERT (Bidirectional Encoder Representations from Transformers) provides dense vector representations for natural language by using a deep, pre-trained neural network with the Transformer architecture.

Pretrained models can be loaded with pretrained() of the companion object:

>>>embeddings = BertSentenceEmbeddings.pretrained() … .setInputCols([“sentence”]) … .setOutputCol(“sentence_bert_embeddings”)

The default model is "sent_small_bert_L2_768", if no name is provided.

For available pretrained models please see the Models Hub.

For extended examples of usage, see the Examples.

Input Annotation types	Output Annotation type
DOCUMENT	SENTENCE_EMBEDDINGS

Parameters:

batchSize

Size of every batch, by default 8

caseSensitive

Whether to ignore case in tokens for embeddings matching, by default False

dimension

Number of embedding dimensions, by default 768

maxSentenceLength

Max sentence length to process, by default 128

isLong

Use Long type instead of Int type for inputs buffer - Some Bert models require Long instead of Int.

configProtoBytes

ConfigProto from tensorflow, serialized into byte array.

References

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

google-research/bert

Paper abstract

We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT model can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial task-specific architecture modifications. BERT is conceptually simple and empirically powerful. It obtains new state-of-the-art results on eleven natural language processing tasks, including pushing the GLUE score to 80.5% (7.7% point absolute improvement), MultiNLI accuracy to 86.7% (4.6% absolute improvement), SQuAD v1.1 question answering Test F1 to 93.2 (1.5 point absolute improvement) and SQuAD v2.0 Test F1 to 83.1 (5.1 point absolute improvement).

Examples

>>> import sparknlp
>>> from sparknlp.base import *
>>> from sparknlp.annotator import *
>>> from pyspark.ml import Pipeline
>>> documentAssembler = DocumentAssembler() \
...     .setInputCol("text") \
...     .setOutputCol("document")
>>> sentence = SentenceDetector() \
...     .setInputCols(["document"]) \
...     .setOutputCol("sentence")
>>> embeddings = BertSentenceEmbeddings.pretrained("sent_small_bert_L2_128") \
...     .setInputCols(["sentence"]) \
...     .setOutputCol("sentence_bert_embeddings")
>>> embeddingsFinisher = EmbeddingsFinisher() \
...     .setInputCols(["sentence_bert_embeddings"]) \
...     .setOutputCols("finished_embeddings") \
...     .setOutputAsVector(True)
>>> pipeline = Pipeline().setStages([
...     documentAssembler,
...     sentence,
...     embeddings,
...     embeddingsFinisher
... ])
>>> data = spark.createDataFrame([["John loves apples. Mary loves oranges. John loves Mary."]]).toDF("text")
>>> result = pipeline.fit(data).transform(data)
>>> result.selectExpr("explode(finished_embeddings) as result").show(5, 80)
+--------------------------------------------------------------------------------+
|                                                                          result|
+--------------------------------------------------------------------------------+
|[-0.8951074481010437,0.13753940165042877,0.3108254075050354,-1.65693199634552...|
|[-0.6180210709571838,-0.12179657071828842,-0.191165953874588,-1.4497021436691...|
|[-0.822715163230896,0.7568016648292542,-0.1165061742067337,-1.59048593044281,...|
+--------------------------------------------------------------------------------+

setConfigProtoBytes(b)[source]#

Sets configProto from tensorflow, serialized into byte array.

Parameters:

bList[int]

ConfigProto from tensorflow, serialized into byte array

setIsLong(value)[source]#

Sets whether to use Long type instead of Int type for inputs buffer.

Some Bert models require Long instead of Int.

Parameters:

valuebool

Whether to use Long type instead of Int type for inputs buffer

static loadSavedModel(folder, spark_session, use_openvino=False)[source]#

Loads a locally saved model.

Parameters:

folderstr

Folder of the saved model

spark_sessionpyspark.sql.SparkSession

The current SparkSession

use_openvino: bool

Use OpenVINO backend

Returns:

BertSentenceEmbeddings

The restored model

static pretrained(name='sent_small_bert_L2_768', lang='en', remote_loc=None)[source]#

Downloads and loads a pretrained model.

Parameters:

namestr, optional

Name of the pretrained model, by default “sent_small_bert_L2_768”

langstr, optional

Language of the pretrained model, by default “en”

remote_locstr, optional

Optional remote address of the resource, by default None. Will use Spark NLPs repositories otherwise.

Returns:

BertSentenceEmbeddings

The restored model