Introducing CamemBertEmbeddings to support CamemBERT models

docs/.vscode/settings.json

@@ -0,0 +1,3 @@
+{
+    "git.ignoreLimitWarning": true
+}

docs/_includes/demomenu.html

@@ -70,15 +70,31 @@
       <li {% if _section.secheader %} {% for child in _section.secheader %} {% if child.activemenu == "analyze_medical_text_german" %} class="active"  {% endif %} {% endfor %} {% endif %} >
         <a href="/analyze_medical_text_german">Analyze Medical Texts in German</a>
       </li>
-      <li {% if _section.secheader %} {% for child in _section.secheader %} {% if child.activemenu == "analyze_financial_models" %} class="active"  {% endif %} {% endfor %} {% endif %} >
-        <a href="/analyze_financial_models">Analyze Financial Models</a>
-      </li>
       <li {% if _section.secheader %} {% for child in _section.secheader %} {% if child.activemenu == "medical_risk_scoring" %} class="active"  {% endif %} {% endfor %} {% endif %} >
         <a href="/medical_risk_scoring">Medical Risk Scoring</a>
       </li>
       <li {% if _section.secheader %} {% for child in _section.secheader %} {% if child.activemenu == "classify_medical_texts" %} class="active"  {% endif %} {% endfor %} {% endif %} >
         <a href="/classify_medical_texts">Classify Medical Texts</a>
       </li>
+      <li><strong>Spark NLP for Finance and Legal</strong></li>
+      <li {% if _section.secheader %} {% for child in _section.secheader %} {% if child.activemenu == "entity_recognition" %} class="active"  {% endif %} {% endfor %} {% endif %} >
+        <a href="/entity_recognition">Entity Recognition</a>
+      </li>
+      <li {% if _section.secheader %} {% for child in _section.secheader %} {% if child.activemenu == "sentiment_analysis" %} class="active"  {% endif %} {% endfor %} {% endif %} >
+        <a href="/sentiment_analysis">Sentiment Analysis</a>
+      </li>
+      <li data-hide="hide" {% if _section.secheader %} {% for child in _section.secheader %} {% if child.activemenu == "deidentification_legal" %} class="active"  {% endif %} {% endfor %} {% endif %} >
+        <a href="/deidentification_legal">De-identification</a>
+      </li>
+      <li data-hide="hide" {% if _section.secheader %} {% for child in _section.secheader %} {% if child.activemenu == "relation_extraction" %} class="active"  {% endif %} {% endfor %} {% endif %} >
+        <a href="/relation_extraction">Relation Extraction</a>
+      </li>
+      <li data-hide="hide" {% if _section.secheader %} {% for child in _section.secheader %} {% if child.activemenu == "table_extraction" %} class="active"  {% endif %} {% endfor %} {% endif %} >
+        <a href="/table_extraction">Table Extraction</a>
+      </li>
+      <li {% if _section.secheader %} {% for child in _section.secheader %} {% if child.activemenu == "text_classification" %} class="active"  {% endif %} {% endfor %} {% endif %} >
+        <a href="/text_classification">Text Classification</a>
+      </li>
       <li><strong>Spark OCR</strong></li>
       <li {% if _section.secheader %} {% for child in _section.secheader %} {% if child.activemenu == "extract_text_from_documents" %} class="active"  {% endif %} {% endfor %} {% endif %} >
         <a href="/extract_text_from_documents">Extract Text from Documents</a>

docs/_posts/Ahmetemintek/2022-03-21-w2v_cc_300d_de_2_4.md

@@ -35,12 +35,12 @@ Word Embeddings lookup annotator that maps tokens to vectors.
 <div class="tabs-box" markdown="1">
 {% include programmingLanguageSelectScalaPythonNLU.html %}
 ```python
-model = WordEmbeddingsModel.pretrained("w2v_cc_300d","de","clinical/models")\
+model = WordEmbeddingsModel.pretrained("w2v_cc_300d","de")\
 	            .setInputCols(["document","token"])\
 	            .setOutputCol("word_embeddings")
 ```
 ```scala
-val model = WordEmbeddingsModel.pretrained("w2v_cc_300d","de","clinical/models")
+val model = WordEmbeddingsModel.pretrained("w2v_cc_300d","de")
 	                .setInputCols("document","token")
 	                .setOutputCol("word_embeddings")
 ```
@@ -71,4 +71,4 @@ Word2Vec feature vectors based on `w2v_cc_300d`.
 
 ## References
 
-FastText common crawl word embeddings for Germany https://fasttext.cc/docs/en/crawl-vectors.html
+FastText common crawl word embeddings for Germany https://fasttext.cc/docs/en/crawl-vectors.html

docs/_posts/C-K-Loan/2021-03-23-onto_recognize_entities_electra_large_en.md

@@ -34,9 +34,9 @@ The onto_recognize_entities_electra_large is a pretrained pipeline that we can u
 {% include programmingLanguageSelectScalaPythonNLU.html %}
 ```python
 
-from sparknlp.pretrained import PretrainedPipelinein
+from sparknlp.pretrained import PretrainedPipeline
 pipeline = PretrainedPipeline('onto_recognize_entities_electra_large', lang = 'en')
-annotations =  pipeline.fullAnnotate(""Hello from John Snow Labs ! "")[0]
+annotations =  pipeline.fullAnnotate("Hello from John Snow Labs!")[0]
 annotations.keys()
 
 ```

docs/_posts/Cabir40/2022-04-25-sbiobertresolve_rxnorm_action_treatment_en_2_4.md

@@ -0,0 +1,103 @@
+---
+layout: model
+title: Sentence Entity Resolver for RxNorm (Action / Treatment)
+author: John Snow Labs
+name: sbiobertresolve_rxnorm_action_treatment
+date: 2022-04-25
+tags: [licensed, en, entity_resolution, clinical, rxnorm]
+task: Entity Resolution
+language: en
+edition: Spark NLP for Healthcare 3.5.1
+spark_version: 2.4
+supported: true
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+This model maps clinical entities and concepts (like drugs/ingredients) to RxNorm codes using `sbiobert_base_cased_mli` Sentence Bert Embeddings. Additionally, this model returns actions and treatments of the drugs in `all_k_aux_labels` column.
+
+## Predicted Entities
+
+`RxNorm Codes`, `Action`, `Treatment`
+
+{:.btn-box}
+<button class="button button-orange" disabled>Live Demo</button>
+<button class="button button-orange" disabled>Open in Colab</button>
+[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/clinical/models/sbiobertresolve_rxnorm_action_treatment_en_3.5.1_2.4_1650899853599.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+
+## How to use
+
+
+
+<div class="tabs-box" markdown="1">
+{% include programmingLanguageSelectScalaPythonNLU.html %}
+```python
+documentAssembler = DocumentAssembler()\
+    .setInputCol("text")\
+    .setOutputCol("ner_chunk")
+
+sbert_embedder = BertSentenceEmbeddings.pretrained("sbiobert_base_cased_mli", "en", "clinical/models")\
+    .setInputCols(["ner_chunk"])\
+    .setOutputCol("sbert_embeddings")
+
+rxnorm_resolver = SentenceEntityResolverModel.pretrained("sbiobertresolve_rxnorm_action_treatment", "en", "clinical/models")\
+    .setInputCols(["ner_chunk", "sbert_embeddings"])\
+    .setOutputCol("rxnorm_code")\
+    .setDistanceFunction("EUCLIDEAN")
+
+pipelineModel = PipelineModel( stages = [ documentAssembler, sbert_embedder, rxnorm_resolver ])
+
+light_model = LightPipeline(pipelineModel)
+
+result = light_model.fullAnnotate(["Zita 200 mg", "coumadin 5 mg", "avandia 4 mg"])
+```
+```scala
+val documentAssembler = new DocumentAssembler()
+      .setInputCol("text")
+      .setOutputCol("ner_chunk")
+
+val sbert_embedder = BertSentenceEmbeddings.pretrained("sbiobert_base_cased_mli", "en","clinical/models")
+      .setInputCols(Array("ner_chunk"))
+      .setOutputCol("sbert_embeddings")
+
+val rxnorm_resolver = SentenceEntityResolverModel.pretrained("sbiobertresolve_rxnorm_action_treatment", "en", "clinical/models")
+      .setInputCols(Array("ner_chunk", "sbert_embeddings"))
+      .setOutputCol("rxnorm_code")
+      .setDistanceFunction("EUCLIDEAN")
+
+val rxnorm_pipelineModel = new PipelineModel().setStages(Array(documentAssembler, sbert_embedder, rxnorm_resolver))
+
+val light_model = LightPipeline(rxnorm_pipelineModel)
+
+val result = light_model.fullAnnotate(Array("Zita 200 mg", "coumadin 5 mg", "avandia 4 mg"))
+```
+</div>
+
+## Results
+
+```bash
+|    | ner_chunk     |   rxnorm_code | action                                                   | treatment                                                                                                                                                       |
+|---:|:--------------|--------------:|:---------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------|
+|  0 | Zita 200 mg   |        104080 | ['Analgesic', 'Antacid', 'Antipyretic', 'Pain Reliever'] | ['Backache', 'Pain', 'Sore Throat', 'Headache', 'Influenza', 'Toothache', 'Heartburn', 'Migraine', 'Muscular Aches And Pains', 'Neuralgia', 'Cold', 'Weakness'] |
+|  1 | coumadin 5 mg |        855333 | ['Anticoagulant']                                        | ['Cerebrovascular Accident', 'Pulmonary Embolism', 'Heart Attack', 'AF', 'Embolization']                                                                        |
+|  2 | avandia 4 mg  |        261242 | ['Drugs Used In Diabets', 'Hypoglycemic']                | ['Diabetes Mellitus', 'Type 1 Diabetes Mellitus', 'Type 2 Diabetes']                                                                                            |
+
+```
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|sbiobertresolve_rxnorm_action_treatment|
+|Compatibility:|Spark NLP for Healthcare 3.5.1+|
+|License:|Licensed|
+|Edition:|Official|
+|Input Labels:|[sentence_embeddings]|
+|Output Labels:|[rxnorm_code]|
+|Language:|en|
+|Size:|918.7 MB|
+|Case sensitive:|false|

docs/_posts/gadde5300/2022-04-24-rct_binary_classifier_use_en_3_0.md

@@ -0,0 +1,120 @@
+---
+layout: model
+title: RCT Binary Classifier (USE)
+author: John Snow Labs
+name: rct_binary_classifier_use
+date: 2022-04-24
+tags: [licensed, clinical, rct, classifier, en]
+task: Text Classification
+language: en
+edition: Spark NLP for Healthcare 3.5.0
+spark_version: 3.0
+supported: true
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+This model is a USE based classifier that can classify if an article is a randomized clinical trial (RCT) or not.
+
+## Predicted Entities
+
+`true`, `false`
+
+{:.btn-box}
+<button class="button button-orange" disabled>Live Demo</button>
+<button class="button button-orange" disabled>Open in Colab</button>
+[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/clinical/models/rct_binary_classifier_use_en_3.5.0_3.0_1650806861149.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+
+## How to use
+
+
+
+<div class="tabs-box" markdown="1">
+{% include programmingLanguageSelectScalaPythonNLU.html %}
+```python
+
+document_assembler = DocumentAssembler()\
+        .setInputCol("text")\
+        .setOutputCol("document")
+
+use = UniversalSentenceEncoder.pretrained()\
+        .setInputCols("document")\
+        .setOutputCol("sentence_embeddings")
+
+classifier_dl = ClassifierDLModel.pretrained("rct_binary_classifier_use", "en", "clinical/models")\
+        .setInputCols(["sentence_embeddings"])\
+        .setOutputCol("class")
+
+use_clf_pipeline = Pipeline(
+    stages = [
+        document_assembler,
+        use,
+        classifier_dl
+    ])
+
+data = spark.createDataFrame([["""Abstract:Based on the American Society of Anesthesiologists' Practice Guidelines for Sedation and Analgesia by Non-Anesthesiologists (ASA-SED), a sedation training course aimed at improving medical safety was developed by the Japanese Association for Medical Simulation in 2011. This study evaluated the effect of debriefing on participants' perceptions of the essential points of the ASA-SED. A total of 38 novice doctors participated in the sedation training course during the research period. Of these doctors, 18 participated in the debriefing group, and 20 participated in non-debriefing group. Scoring of participants' guideline perceptions was conducted using an evaluation sheet (nine items, 16 points) created based on the ASA-SED. The debriefing group showed a greater perception of the ASA-SED, as reflected in the significantly higher scores on the evaluation sheet (median, 16 points) than the control group (median, 13 points; p < 0.05). No significant differences were identified before or during sedation, but the difference after sedation was significant (p < 0.05). Debriefing after sedation training courses may contribute to better perception of the ASA-SED, and may lead to enhanced attitudes toward medical safety during sedation and analgesia. """]]).toDF("text")
+
+result = use_clf_pipeline.fit(data).transform(data)
+```
+```scala
+val documenter = new DocumentAssembler() 
+    .setInputCol("text") 
+    .setOutputCol("document")
+
+val use = new UniversalSentenceEncoder.pretrained()
+    .setInputCols("document")
+    .setOutputCol("sentence_embeddings")
+
+val classifier_dl = new ClassifierDLModel.pretrained("rct_binary_classifier_use", "en", "clinical/models")
+        .setInputCols(Array("sentence_embeddings"))
+        .setOutputCol("class")
+
+val use_clf_pipeline = new Pipeline().setStages(Array(documenter, use, classifier_dl))
+
+val data = Seq("""Abstract:Based on the American Society of Anesthesiologists' Practice Guidelines for Sedation and Analgesia by Non-Anesthesiologists (ASA-SED), a sedation training course aimed at improving medical safety was developed by the Japanese Association for Medical Simulation in 2011. This study evaluated the effect of debriefing on participants' perceptions of the essential points of the ASA-SED. A total of 38 novice doctors participated in the sedation training course during the research period. Of these doctors, 18 participated in the debriefing group, and 20 participated in non-debriefing group. Scoring of participants' guideline perceptions was conducted using an evaluation sheet (nine items, 16 points) created based on the ASA-SED. The debriefing group showed a greater perception of the ASA-SED, as reflected in the significantly higher scores on the evaluation sheet (median, 16 points) than the control group (median, 13 points; p < 0.05). No significant differences were identified before or during sedation, but the difference after sedation was significant (p < 0.05). Debriefing after sedation training courses may contribute to better perception of the ASA-SED, and may lead to enhanced attitudes toward medical safety during sedation and analgesia. """).toDF("text")
+
+val result = use_clf_pipeline.fit(data).transform(data)
+```
+</div>
+
+## Results
+
+```bash
+| text                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      | rct  |
+|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------|
+|    Abstract:Based on the American Society of Anesthesiologists' Practice Guidelines for Sedation and Analgesia by Non-Anesthesiologists (ASA-SED), a sedation training course aimed at improving medical safety was developed by the Japanese Association for Medical Simulation in 2011. This study evaluated the effect of debriefing on participants' perceptions of the essential points of the ASA-SED. A total of 38 novice doctors participated in the sedation training course during the research period. Of these doctors, 18 participated in the debriefing group, and 20 participated in non-debriefing group. Scoring of participants' guideline perceptions was conducted using an evaluation sheet (nine items, 16 points) created based on the ASA-SED. The debriefing group showed a greater perception of the ASA-SED, as reflected in the significantly higher scores on the evaluation sheet (median, 16 points) than the control group (median, 13 points; p < 0.05). No significant differences were identified before or during sedation, but the difference after sedation was significant (p < 0.05). Debriefing after sedation training courses may contribute to better perception of the ASA-SED, and may lead to enhanced attitudes toward medical safety during sedation and analgesia.     | true |
+```
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|rct_binary_classifier_use|
+|Compatibility:|Spark NLP for Healthcare 3.5.0+|
+|License:|Licensed|
+|Edition:|Official|
+|Input Labels:|[sentence_embeddings]|
+|Output Labels:|[class]|
+|Language:|en|
+|Size:|20.9 MB|
+
+## References
+
+https://arxiv.org/abs/1710.06071
+
+## Benchmarking
+
+```bash
+              precision    recall  f1-score   support
+
+       false       0.84      0.80      0.82      2915
+        true       0.78      0.82      0.80      2545
+
+    accuracy                           0.81      5460
+   macro avg       0.81      0.81      0.81      5460
+weighted avg       0.81      0.81      0.81      5460
+```