sparknlp.annotator.classifier_dl.bert_for_question_answering#

Classes#

class BertForQuestionAnswering(classname='com.johnsnowlabs.nlp.annotators.classifier.dl.BertForQuestionAnswering', java_model=None)[source]#

BertForQuestionAnswering can load BERT Models with a span classification head on top for extractive question-answering tasks like SQuAD (a linear layer on top of the hidden-states output to compute span start logits and span end logits).

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

>>> spanClassifier = BertForQuestionAnswering.pretrained() \
...     .setInputCols(["document_question", "document_context"]) \
...     .setOutputCol("answer")

The default model is "bert_base_cased_qa_squad2", if no name is provided.

For available pretrained models please see the Models Hub.

To see which models are compatible and how to import them see Import Transformers into Spark NLP 🚀.

Input Annotation types	Output Annotation type
DOCUMENT, DOCUMENT	CHUNK

Parameters:

batchSize

Batch size. Large values allows faster processing but requires more memory, by default 8

caseSensitive

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

configProtoBytes

ConfigProto from tensorflow, serialized into byte array.

maxSentenceLength

Max sentence length to process, by default 128

Examples

>>> import sparknlp
>>> from sparknlp.base import *
>>> from sparknlp.annotator import *
>>> from pyspark.ml import Pipeline
>>> documentAssembler = MultiDocumentAssembler() \
...     .setInputCols(["question", "context"]) \
...     .setOutputCols(["document_question", "document_context"])
>>> questionAnswering = BertForQuestionAnswering.pretrained() \
...     .setInputCols(["document_question", "document_context"]) \
...     .setOutputCol("answer") \
...     .setCaseSensitive(False)
>>> pipeline = Pipeline().setStages([
...     documentAssembler,
...     questionAnswering
... ])
>>> data = spark.createDataFrame([["What's my name?", "My name is Clara and I live in Berkeley."]]).toDF("question", "context")
>>> result = pipeline.fit(data).transform(data)
>>> result.select("answer.result").show(truncate=False)
+--------------------+
|result              |
+--------------------+
|[Clara]             |
+--------------------+

setConfigProtoBytes(b)[source]#

Sets configProto from tensorflow, serialized into byte array.

Parameters:

bList[int]

ConfigProto from tensorflow, serialized into byte array

static loadSavedModel(folder, spark_session)[source]#

Loads a locally saved model.

Parameters:

folderstr

Folder of the saved model

spark_sessionpyspark.sql.SparkSession

The current SparkSession

Returns:

BertForQuestionAnswering

The restored model

static pretrained(name='bert_base_cased_qa_squad2', lang='en', remote_loc=None)[source]#

Downloads and loads a pretrained model.

Parameters:

namestr, optional

Name of the pretrained model, by default “bert_base_cased_qa_squad2”

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:

BertForQuestionAnswering

The restored model