sparknlp.annotator.embeddings.deberta_embeddings#

Classes#

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

The DeBERTa model was proposed in DeBERTa: Decoding-enhanced BERT with Disentangled Attention by Pengcheng He, Xiaodong Liu, Jianfeng Gao, Weizhu Chen It is based on Google’s BERT model released in 2018 and Facebook’s RoBERTa model released in 2019.

This model requires input tokenization with SentencePiece model, which is provided by Spark NLP (See tokenizers package).

It builds on RoBERTa with disentangled attention and enhanced mask decoder training with half of the data used in RoBERTa.

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

>>> embeddings = DeBertaEmbeddings.pretrained() \
...    .setInputCols(["sentence", "token"]) \
...    .setOutputCol("embeddings")

The default model is "deberta_v3_base", if no name is provided.

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

Input Annotation types	Output Annotation type
DOCUMENT, TOKEN	WORD_EMBEDDINGS

Parameters:

batchSize

Size of every batch, by default 8

dimension

Number of embedding dimensions, by default 768

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

References

microsoft/DeBERTa

https://www.microsoft.com/en-us/research/blog/microsoft-deberta-surpasses-human-performance-on-the-superglue-benchmark/

Paper abstract:

Paper abstract: Recent progress in pre-trained neural language models has significantly improved the performance of many natural language processing (NLP) tasks. In this paper we propose a new model architecture DeBERTa ( Decoding-enhanced BERT with disentangled attention) that improves the BERT and RoBERTa models using two novel techniques. The first is the disentangled attention mechanism, where each word is represented using two vectors that encode its content and position, respectively, and the attention weights among words are computed using disentangled matrices on their contents and relative positions. Second, an enhanced mask decoder is used to replace the output softmax layer to predict the masked tokens for model pretraining. We show that these two techniques significantly improve the efficiency of model pretraining and performance of downstream tasks. Compared to RoBERTa-Large, a DeBERTa model trained on half of the training data performs consistently better on a wide range of NLP tasks, achieving improvements on MNLI by +0.9% (90.2% vs. 91.1%), on SQuAD v2.0 by +2.3% (88.4% vs. 90.7%) and RACE by +3.6% (83.2% vs. 86.8%). The DeBERTa code and pre-trained models will be made publicly available at https://github.com/microsoft/DeBERTa.

Examples

>>> import sparknlp
>>> from sparknlp.base import *
>>> from sparknlp.annotator import *
>>> from pyspark.ml import Pipeline
>>> documentAssembler = DocumentAssembler() \
...     .setInputCol("text") \
...     .setOutputCol("document")
>>> tokenizer = Tokenizer() \
...     .setInputCols(["document"]) \
>>> embeddings = DeBertaEmbeddings.pretrained() \
...     .setInputCols(["token", "document"]) \
...     .setOutputCol("embeddings")
>>> embeddingsFinisher = EmbeddingsFinisher() \
...     .setInputCols(["embeddings"]) \
...     .setOutputCols("finished_embeddings") \
...     .setOutputAsVector(True) \
...     .setCleanAnnotations(False)
>>> pipeline = Pipeline().setStages([
...     documentAssembler,
...     tokenizer,
...     embeddings,
...     embeddingsFinisher
... ])
>>> data = spark.createDataFrame([["This is a sentence."]]).toDF("text")
>>> result = pipeline.fit(data).transform(data)
>>> result.selectExpr("explode(finished_embeddings) as result").show(5, 80)
+--------------------------------------------------------------------------------+
|                                                                          result|
+--------------------------------------------------------------------------------+
|[1.1342473030090332,-1.3855540752410889,0.9818322062492371,-0.784737348556518...|
|[0.847029983997345,-1.047153353691101,-0.1520637571811676,-0.6245765686035156...|
|[-0.009860038757324219,-0.13450059294700623,2.707749128341675,1.2916892766952...|
|[-0.04192575812339783,-0.5764210224151611,-0.3196685314178467,-0.527840495109...|
|[0.15583214163780212,-0.1614152491092682,-0.28423872590065,-0.135491415858268...|
+--------------------------------------------------------------------------------+

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:

DeBertaEmbeddings

The restored model

static pretrained(name='deberta_v3_base', lang='en', remote_loc=None)[source]#

Downloads and loads a pretrained model.

Parameters:

namestr, optional

Name of the pretrained model, by default “deberta_v3_base”

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:

DeBertaEmbeddings

The restored model