SPARKNLP-942: MPNet Classifiers

docs/en/annotators.md

@@ -147,6 +147,8 @@ Additionally, these transformers are available.
 {% include templates/anno_table_entry.md path="./transformers" name="LongformerForTokenClassification" summary="LongformerForTokenClassification can load Longformer Models with a token classification head on top (a linear layer on top of the hidden-states output) e.g. for Named-Entity-Recognition (NER) tasks."%}
 {% include templates/anno_table_entry.md path="./transformers" name="MarianTransformer" summary="Marian is an efficient, free Neural Machine Translation framework written in pure C++ with minimal dependencies."%}
 {% include templates/anno_table_entry.md path="./transformers" name="MPNetEmbeddings" summary="Sentence embeddings using MPNet."%}
+{% include templates/anno_table_entry.md path="./transformers" name="MPNetForQuestionAnswering" summary="MPNet Models with a span classification head on top for extractive question-answering tasks like SQuAD."%}
+{% include templates/anno_table_entry.md path="./transformers" name="MPNetForSequenceClassification" summary="MPNet Models with sequence classification/regression head on top e.g. for multi-class document classification tasks."%}
 {% include templates/anno_table_entry.md path="./transformers" name="OpenAICompletion" summary="Transformer that makes a request for OpenAI Completion API for each executor."%}
 {% include templates/anno_table_entry.md path="./transformers" name="RoBertaEmbeddings" summary="RoBERTa: A Robustly Optimized BERT Pretraining Approach"%}
 {% include templates/anno_table_entry.md path="./transformers" name="RoBertaForQuestionAnswering" summary="RoBertaForQuestionAnswering can load RoBERTa Models with a span classification head on top for extractive question-answering tasks like SQuAD."%}

docs/en/transformer_entries/MPNetForQuestionAnswering.md

@@ -0,0 +1,121 @@
+{%- capture title -%}
+MPNetForQuestionAnswering
+{%- endcapture -%}
+
+{%- capture description -%}
+MPNetForQuestionAnswering can load MPNet 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:
+
+```scala
+val spanClassifier = MPNetForQuestionAnswering.pretrained()
+  .setInputCols(Array("document_question", "document_context"))
+  .setOutputCol("answer")
+```
+
+The default model is `"mpnet_base_question_answering_squad2"`, if no name is provided.
+
+For available pretrained models please see the
+[Models Hub](https://sparknlp.org/models?task=Question+Answering).
+
+To see which models are compatible and how to import them see
+https://github.com/JohnSnowLabs/spark-nlp/discussions/5669 and to see more extended
+examples, see
+[MPNetForQuestionAnsweringTestSpec](https://github.com/JohnSnowLabs/spark-nlp/blob/master/src/test/scala/com/johnsnowlabs/nlp/annotators/classifier/dl/MPNetForQuestionAnsweringTestSpec.scala).
+{%- endcapture -%}
+
+{%- capture input_anno -%}
+
+{%- endcapture -%}
+
+{%- capture output_anno -%}
+CHUNK
+{%- endcapture -%}
+
+{%- capture python_example -%}
+import sparknlp
+from sparknlp.base import *
+from sparknlp.annotator import *
+from pyspark.ml import Pipeline
+
+documentAssembler = MultiDocumentAssembler() \
+    .setInputCols(["question", "context"]) \
+    .setOutputCol(["document_question", "document_context"])
+
+spanClassifier = MPNetForQuestionAnswering.pretrained() \
+    .setInputCols(["document_question", "document_context"]) \
+    .setOutputCol("answer") \
+    .setCaseSensitive(False)
+
+pipeline = Pipeline().setStages([
+    documentAssembler,
+    spanClassifier
+])
+
+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]              |
+++--------------------+
+{%- endcapture -%}
+
+{%- capture scala_example -%}
+import spark.implicits._
+import com.johnsnowlabs.nlp.base._
+import com.johnsnowlabs.nlp.annotator._
+import org.apache.spark.ml.Pipeline
+
+val document = new MultiDocumentAssembler()
+  .setInputCols("question", "context")
+  .setOutputCols("document_question", "document_context")
+
+val questionAnswering = MPNetForQuestionAnswering.pretrained()
+  .setInputCols(Array("document_question", "document_context"))
+  .setOutputCol("answer")
+  .setCaseSensitive(true)
+
+val pipeline = new Pipeline().setStages(Array(
+  document,
+  questionAnswering
+))
+
+val data = Seq("What's my name?", "My name is Clara and I live in Berkeley.").toDF("question", "context")
+val result = pipeline.fit(data).transform(data)
+
+result.select("label.result").show(false)
++---------------------+
+|result               |
++---------------------+
+|[Clara]              |
+++--------------------+
+
+{%- endcapture -%}
+
+{%- capture api_link -%}
+[MPNetForQuestionAnswering](/api/com/johnsnowlabs/nlp/annotators/classifier/dl/MPNetForQuestionAnswering)
+{%- endcapture -%}
+
+{%- capture python_api_link -%}
+[MPNetForQuestionAnswering](/api/python/reference/autosummary/sparknlp/annotator/classifier_dl/mpnet_for_question_answering/index.html#sparknlp.annotator.classifier_dl.mpnet_for_question_answering.MPNetForQuestionAnswering)
+{%- endcapture -%}
+
+{%- capture source_link -%}
+[MPNetForQuestionAnswering](https://github.com/JohnSnowLabs/spark-nlp/tree/master/src/main/scala/com/johnsnowlabs/nlp/annotators/classifier/dl/MPNetForQuestionAnswering.scala)
+{%- endcapture -%}
+
+{% include templates/anno_template.md
+title=title
+description=description
+input_anno=input_anno
+output_anno=output_anno
+python_example=python_example
+scala_example=scala_example
+api_link=api_link
+python_api_link=python_api_link
+source_link=source_link
+%}

docs/en/transformer_entries/MPNetForSequenceClassification.md

@@ -0,0 +1,139 @@
+{%- capture title -%}
+MPNetForSequenceClassification
+{%- endcapture -%}
+
+{%- capture description -%}
+MPNetForSequenceClassification can load MPNet Models with sequence classification/regression
+head on top (a linear layer on top of the pooled output) e.g. for multi-class document
+classification tasks.
+
+Note that currently, only SetFit models can be imported.
+
+Pretrained models can be loaded with `pretrained` of the companion object:
+
+```scala
+val sequenceClassifier = MPNetForSequenceClassification.pretrained()
+  .setInputCols("token", "document")
+  .setOutputCol("label")
+```
+
+The default model is `"mpnet_sequence_classifier_ukr_message"`, if no name is provided.
+
+For available pretrained models please see the
+[Models Hub](https://sparknlp.org/models?task=Text+Classification).
+
+To see which models are compatible and how to import them see
+https://github.com/JohnSnowLabs/spark-nlp/discussions/5669 and to see more extended
+examples, see
+[MPNetForSequenceClassificationTestSpec](https://github.com/JohnSnowLabs/spark-nlp/blob/master/src/test/scala/com/johnsnowlabs/nlp/annotators/classifier/dl/MPNetForSequenceClassificationTestSpec.scala).
+{%- endcapture -%}
+
+{%- capture input_anno -%}
+DOCUMENT, TOKEN
+{%- endcapture -%}
+
+{%- capture output_anno -%}
+CATEGORY
+{%- endcapture -%}
+
+{%- capture python_example -%}
+import sparknlp
+from sparknlp.base import *
+from sparknlp.annotator import *
+from pyspark.ml import Pipeline
+
+document = DocumentAssembler() \
+    .setInputCol("text") \
+    .setOutputCol("document")
+
+tokenizer = Tokenizer() \
+    .setInputCols(["document"]) \
+    .setOutputCol("token")
+
+sequenceClassifier = MPNetForSequenceClassification \
+    .pretrained() \
+    .setInputCols(["document", "token"]) \
+    .setOutputCol("label")
+
+data = spark.createDataFrame([
+    ["I love driving my car."],
+    ["The next bus will arrive in 20 minutes."],
+    ["pineapple on pizza is the worst 🤮"],
+]).toDF("text")
+
+pipeline = Pipeline().setStages([document, tokenizer, sequenceClassifier])
+pipelineModel = pipeline.fit(data)
+results = pipelineModel.transform(data)
+results.select("label.result").show()
++--------------------+
+|              result|
++--------------------+
+|     [TRANSPORT/CAR]|
+|[TRANSPORT/MOVEMENT]|
+|              [FOOD]|
++--------------------+
+{%- endcapture -%}
+
+{%- capture scala_example -%}
+import com.johnsnowlabs.nlp.base._
+import com.johnsnowlabs.nlp.annotator._
+import org.apache.spark.ml.Pipeline
+import spark.implicits._
+
+val document = new DocumentAssembler()
+  .setInputCol("text")
+  .setOutputCol("document")
+
+val tokenizer = new Tokenizer()
+  .setInputCols(Array("document"))
+  .setOutputCol("token")
+
+val sequenceClassifier = MPNetForSequenceClassification
+  .pretrained()
+  .setInputCols(Array("document", "token"))
+  .setOutputCol("label")
+
+val texts = Seq(
+  "I love driving my car.",
+  "The next bus will arrive in 20 minutes.",
+  "pineapple on pizza is the worst 🤮")
+val data = texts.toDF("text")
+
+val pipeline = new Pipeline().setStages(Array(document, tokenizer, sequenceClassifier))
+val pipelineModel = pipeline.fit(data)
+val results = pipelineModel.transform(data)
+
+results.select("label.result").show()
++--------------------+
+|              result|
++--------------------+
+|     [TRANSPORT/CAR]|
+|[TRANSPORT/MOVEMENT]|
+|              [FOOD]|
++--------------------+
+
+{%- endcapture -%}
+
+{%- capture api_link -%}
+[MPNetForSequenceClassification](/api/com/johnsnowlabs/nlp/annotators/classifier/dl/MPNetForSequenceClassification)
+{%- endcapture -%}
+
+{%- capture python_api_link -%}
+[MPNetForSequenceClassification](/api/python/reference/autosummary/sparknlp/annotator/classifier_dl/mpnet_for_sequence_classification/index.html#sparknlp.annotator.classifier_dl.mpnet_for_sequence_classification.MPNetForSequenceClassification)
+{%- endcapture -%}
+
+{%- capture source_link -%}
+[MPNetForSequenceClassification](https://github.com/JohnSnowLabs/spark-nlp/tree/master/src/main/scala/com/johnsnowlabs/nlp/annotators/classifier/dl/MPNetForSequenceClassification.scala)
+{%- endcapture -%}
+
+{% include templates/anno_template.md
+title=title
+description=description
+input_anno=input_anno
+output_anno=output_anno
+python_example=python_example
+scala_example=scala_example
+api_link=api_link
+python_api_link=python_api_link
+source_link=source_link
+%}