Merge remote-tracking branch 'origin/main' into release/4411

# Conflicts:
#	docs/en/jsl/jsl_release_notes.md
#	johnsnowlabs/settings.py

docs/_includes/article-list.html

@@ -37,7 +37,7 @@
 
     {%- if include.type == 'item' -%}
       {%- if include.article_type == 'BlogPosting' -%}
-        <article class="item" itemscope itemtype="http://schema.org/BlogPosting">
+        <article class="item" itemscope itemtype="https://schema.org/BlogPosting">
       {%- else -%}
         <article class="item">
       {%- endif -%}
@@ -99,7 +99,7 @@
         {%- endif -%}
       {%- endif -%}
       {%- include snippets/get-locale-string.html key='ARTICLE_LIST_DATE_FORMAT' -%}
-      <li class="item" itemscope itemtype="http://schema.org/BlogPosting" data-tags="{{ _tags }}">
+      <li class="item" itemscope itemtype="https://schema.org/BlogPosting" data-tags="{{ _tags }}">
         <div class="item__content">
           {%- if include.show_info -%}
             <span class="item__meta">{{ _article.date | date: __return }}</span>

docs/_includes/article/footer/author-profile.html

@@ -1,9 +1,9 @@
 {%- assign _author = include.author -%}
 
 {%- if _author.type == 'organization' -%}
-  {%- assign _author_itemtype = 'http://schema.org/Organization' -%}
+  {%- assign _author_itemtype = 'https://schema.org/Organization' -%}
 {%- else -%}
-  {%- assign _author_itemtype = 'http://schema.org/Person' -%}
+  {%- assign _author_itemtype = 'https://schema.org/Person' -%}
 {%- endif -%}
 
 <div itemscope itemtype="{{ _author_itemtype }}" class="author-profile card card--flat item">

docs/_includes/demomenu.html

@@ -234,6 +234,9 @@
           <li {% if _section.secheader %} {% for child in _section.secheader %} {% if child.activemenu == "long_document_splitting" %} class="active"  {% endif %} {% endfor %} {% endif %} >
             <a href="/long_document_splitting">Long Document Splitting</a>
           </li>
+          <li {% if _section.secheader %} {% for child in _section.secheader %} {% if child.activemenu == "legal_text_summarization" %} class="active"  {% endif %} {% endfor %} {% endif %} >
+            <a href="/legal_text_summarization">Text Summarization</a>
+          </li>
           <li {% if _section.secheader %} {% for child in _section.secheader %} {% if child.activemenu == "legal_question_answering" %} class="active"  {% endif %} {% endfor %} {% endif %} >
             <a href="/legal_question_answering">Legal Question Answering</a>
           </li>

docs/_includes/docs-annotation-pagination.html

@@ -10,6 +10,7 @@
   </li>
 </ul>
 <ul class="pagination owl-carousel pagination_big">
+  <li><a href="release_notes_5_1_1">5.1.1</a></li>
   <li><a href="release_notes_5_1_0">5.1.0</a></li>
   <li><a href="release_notes_4_10_1">4.10.1</a></li>
   <li><a href="release_notes_4_10_0">4.10.0</a></li>

docs/_includes/footer.html

@@ -4,9 +4,9 @@
 
     {%- assign _site_author = site.author -%}
     {%- if _site_author.type == 'organization' -%}
-      {%- assign _site_author_itemtype = 'http://schema.org/Organization' -%}
+      {%- assign _site_author_itemtype = 'https://schema.org/Organization' -%}
     {%- else -%}
-      {%- assign _site_author_itemtype = 'http://schema.org/Person' -%}
+      {%- assign _site_author_itemtype = 'https://schema.org/Person' -%}
     {%- endif -%}
 
     <div itemscope itemtype="{{ _site_author_itemtype }}">

docs/_includes/head.html

@@ -15,6 +15,8 @@
 
 {%- if page.layout == "landing" -%}
 <title>John Snow Labs - State of the Art NLP in Python</title>
+{%- elsif page.layout == "model" -%}
+<title>{%- include snippets/get-article-modeltitle.html article=page -%}</title>
 {%- elsif _pagetitle -%}
 <title>{%- if __return -%}{{ __return }}{%- endif -%}</title>
 {%- else -%}

docs/_includes/snippets/get-article-modeltitle.html

@@ -0,0 +1,9 @@
+{%- assign _modelname = include.article.name -%}
+{%- assign _modeledition = include.article.edition -%}
+{%- assign _title = include.article.title -%}
+
+{%- if _title -%}
+{{ _title }} | {% if _modelname %}{{ _modelname }}{% endif %}{% if _modeledition %} | {{ _modeledition }}{% endif %}
+{%- else -%}
+  {%- assign __return = nil -%}
+{%- endif -%}

docs/_layouts/menulist.html

@@ -203,9 +203,9 @@
               <div class="col-main cell cell--auto">
                 {%- include main/top/custom.html -%}
                 {%- if _page_type == 'article' -%}
-                  <article itemscope itemtype="http://schema.org/Article">
+                  <article itemscope itemtype="https://schema.org/Article">
                 {%- elsif _page_type == 'webpage' -%}
-                  <article itemscope itemtype="http://schema.org/WebPage">
+                  <article itemscope itemtype="https://schema.org/WebPage">
                 {%- else -%}
                   <article>
                 {%- endif -%}

docs/_layouts/page.html

@@ -207,9 +207,9 @@
               <div class="col-main cell cell--auto">
                 {%- include main/top/custom.html -%}
                 {%- if _page_type == 'article' -%}
-                  <article itemscope itemtype="http://schema.org/Article">
+                  <article itemscope itemtype="https://schema.org/Article">
                 {%- elsif _page_type == 'webpage' -%}
-                  <article itemscope itemtype="http://schema.org/WebPage">
+                  <article itemscope itemtype="https://schema.org/WebPage">
                 {%- else -%}
                   <article>
                 {%- endif -%}

docs/_layouts/pagenew.html

@@ -203,9 +203,9 @@
               <div class="col-main cell cell--auto">
                 {%- include main/top/custom.html -%}
                 {%- if _page_type == 'article' -%}
-                  <article itemscope itemtype="http://schema.org/Article">
+                  <article itemscope itemtype="https://schema.org/Article">
                 {%- elsif _page_type == 'webpage' -%}
-                  <article itemscope itemtype="http://schema.org/WebPage">
+                  <article itemscope itemtype="https://schema.org/WebPage">
                 {%- else -%}
                   <article>
                 {%- endif -%}

docs/_posts/2020-01-28-ner_crf_en.md

@@ -70,5 +70,5 @@ val model = NerCrfModel.pretrained("ner_crf","en","clinical/models")
 
 {:.h2_title}
 ## Data Source
-Trained on i2b2 augmented data with `clinical_embeddings`
+Trained with augmented version of i2b2 dataset with`clinical_embeddings`
 FILLUP

docs/_posts/2020-01-30-assertion_dl_en.md

@@ -157,7 +157,7 @@ The output is a dataframe with a sentence per row and an ``"assertion"`` column
 
 
 ## Data Source
-Trained on 2010 i2b2/VA challenge on concepts, assertions, and relations in clinical text with 'embeddings_clinical'.
+Trained with augmented version of 2010 i2b2/VA dataset on concepts, assertions, and relations in clinical text with 'embeddings_clinical'.
 https://portal.dbmi.hms.harvard.edu/projects/n2c2-nlp/
 
 

docs/_posts/2020-01-30-assertion_ml_en.md

@@ -115,5 +115,5 @@ The output is a dataframe with a sentence per row and an "assertion" column cont
 
 {:.h2_title}
 ## Data Source
-Trained on 2010 i2b2/VA challenge on concepts, assertions, and relations in clinical text with 'embeddings_clinical'.
+Trained with augmented version of 2010 i2b2/VA dataset on concepts, assertions, and relations in clinical text with 'embeddings_clinical'.
 https://portal.dbmi.hms.harvard.edu/projects/n2c2-nlp/

docs/_posts/2020-01-30-ner_clinical_en.md

@@ -142,7 +142,7 @@ The output is a dataframe with a sentence per row and a ``"ner"`` column contain
 
 {:.h2_title}
 ## Data Source
-Trained on 2010 i2b2 challenge data with `embeddings_clinical`.
+Trained with augmented version of i2b2 dataset with `embeddings_clinical`.
 https://portal.dbmi.hms.harvard.edu/projects/n2c2-nlp/
 
 {:.h2_title}

docs/_posts/2020-03-25-ner_diseases_en.md

@@ -121,7 +121,7 @@ The output is a dataframe with a sentence per row and a ``"ner"`` column contain
 
 {:.h2_title}
 ## Data Source
-Trained on i2b2 with ``embeddings_clinical``.
+Trained with augmented version of i2b2 dataset with ``embeddings_clinical``.
 https://portal.dbmi.hms.harvard.edu/projects/n2c2-nlp/
 
 {:.h2_title}

docs/_posts/2020-03-26-ner_healthcare_en.md

@@ -108,7 +108,7 @@ The output is a dataframe with a sentence per row and a ``"ner"`` column contain
 
 {:.h2_title}
 ## Data Source
-Trained on 2010 i2b2 challenge data with 'embeddings_healthcare_100d'.
+Trained with augmented version of i2b2 dataset with 'embeddings_healthcare_100d'.
 https://portal.dbmi.hms.harvard.edu/projects/n2c2-nlp/
 
 {:.h2_title}

docs/_posts/2020-04-15-ner_posology_en.md

@@ -121,7 +121,7 @@ The output is a dataframe with a sentence per row and a ``"ner"`` column contain
 
 {:.h2_title}
 ## Data Source
-Trained on the 2018 i2b2 dataset and FDA Drug datasets with ``embeddings_clinical``.
+Trained with augmented version of 2018 i2b2 dataset and FDA Drug datasets with ``embeddings_clinical``.
 https://open.fda.gov/
 
 

docs/_posts/2020-04-17-spellcheck_clinical_en.md

@@ -71,4 +71,4 @@ nlu.load("en.spell.clinical").predict("""Put your text here.""")
 
 {:.h2_title}
 ## Data Source
-Trained with PubMed and i2b2 datasets.
+Trained with augmented version of i2b2 and PubMed datasets.

docs/_posts/2020-04-21-ner_posology_small_en.md

@@ -158,7 +158,7 @@ nlu.load("en.med_ner.posology.small").predict("""The patient is a 30-year-old fe
 
 {:.h2_title}
 ## Data Source
-Trained on the 2018 i2b2 dataset (no FDA) with ``embeddings_clinical``.
+Trained with augmented version of i2b2 dataset (no FDA) with ``embeddings_clinical``.
 https://www.i2b2.org/NLP/Medication
 
 {:.h2_title}

docs/_posts/2020-04-22-ner_anatomy_en.md

@@ -112,7 +112,7 @@ The output is a dataframe with a sentence per row and a ``"ner"`` column contain
 {:.h2_title}
 ## Data Source
 Trained on the Anatomical Entity Mention (AnEM) corpus with ``'embeddings_clinical'``.
-http://www.nactem.ac.uk/anatomy/
+[https://www.nactem.ac.uk/anatomy/](https://www.nactem.ac.uk/anatomy/)
 
 {:.h2_title}
 ## Benchmarking

docs/_posts/2020-04-22-ner_cellular_en.md

@@ -120,7 +120,7 @@ The output is a dataframe with a sentence per row and a ``"ner"`` column contain
 {:.h2_title}
 ## Data Source
 Trained on the JNLPBA corpus containing more than 2.404 publication abstracts with ``'embeddings_clinical'``.
-http://www.geniaproject.org/
+[https://www.geniaproject.org/](https://www.geniaproject.org/)
 
 {:.h2_title}
 ## Benchmarking

docs/_posts/2020-04-22-ner_jsl_en.md

@@ -30,15 +30,15 @@ Definitions of Predicted Entities:
 - `Procedure`: All mentions of invasive medical or surgical procedures or treatments.
 - `Symptom`: All the symptoms mentioned in the document, of a patient or someone else.
 - `Substance`: All mentions of substance use related to the patient or someone else (recreational drugs, illicit drugs).
-- `Route`: Drug and medication administration routes available described by [FDA](http://wayback.archive-it.org/7993/20171115111313/https:/www.fda.gov/Drugs/DevelopmentApprovalProcess/FormsSubmissionRequirements/ElectronicSubmissions/DataStandardsManualmonographs/ucm071667.htm).
+- `Route`: Drug and medication administration routes available described by [FDA](https://wayback.archive-it.org/7993/20171115111313/https:/www.fda.gov/Drugs/DevelopmentApprovalProcess/FormsSubmissionRequirements/ElectronicSubmissions/DataStandardsManualmonographs/ucm071667.htm).
 - `Blood_Pressure`: Systemic blood pressure, mean arterial pressure, systolic and/or diastolic are extracted.
 - `Allergen`: Allergen related extractions mentioned in the document.
 - `Gender`: Gender-specific nouns and pronouns.
 - `Pulse`: Peripheral heart rate, without advanced information like measurement location.
 - `Modifier`: Terms that modify the symptoms, diseases or risk factors. If a modifier is included in ICD-10 name of a specific disease, the respective modifier is not extracted separately.
 - `Frequency`: Frequency of administration for a dose prescribed.
 - `Weight`: All mentions related to a patients weight.
-- `Dosage`: Quantity prescribed by the physician for an active ingredient; measurement units are available described by [FDA](http://wayback.archive-it.org/7993/20171115111313/https:/www.fda.gov/Drugs/DevelopmentApprovalProcess/FormsSubmissionRequirements/ElectronicSubmissions/DataStandardsManualmonographs/ucm071667.htm).
+- `Dosage`: Quantity prescribed by the physician for an active ingredient; measurement units are available described by [FDA](https://wayback.archive-it.org/7993/20171115111313/https:/www.fda.gov/Drugs/DevelopmentApprovalProcess/FormsSubmissionRequirements/ElectronicSubmissions/DataStandardsManualmonographs/ucm071667.htm).
 - `Respiration`: Number of breaths per minute. 
 
 ## Predicted Entities 

docs/_posts/2020-04-22-ner_jsl_enriched_en.md

@@ -25,7 +25,7 @@ Pretrained named entity recognition deep learning model for clinical terminology
 Definitions of Predicted Entities:
 
 - `Age`: All mention of ages, past or present, related to the patient or with anybody else. 
-- `Dosage`: Quantity prescribed by the physician for an active ingredient; measurement units are available described by [FDA](http://wayback.archive-it.org/7993/20171115111313/https:/www.fda.gov/Drugs/DevelopmentApprovalProcess/FormsSubmissionRequirements/ElectronicSubmissions/DataStandardsManualmonographs/ucm071667.htm). 
+- `Dosage`: Quantity prescribed by the physician for an active ingredient; measurement units are available described by [FDA](https://wayback.archive-it.org/7993/20171115111313/https:/www.fda.gov/Drugs/DevelopmentApprovalProcess/FormsSubmissionRequirements/ElectronicSubmissions/DataStandardsManualmonographs/ucm071667.htm). 
 - `Drug_Name`: Commercial labeling name chosen by the labeler or the drug manufacturer for a drug containing a single or multiple drug active ingredients. 
 - `Frequency`: Frequency of administration for a dose prescribed. 
 - `Gender`: Gender-specific nouns and pronouns. 
@@ -37,7 +37,7 @@ Definitions of Predicted Entities:
 - `Procedure`: All mentions of invasive medical or surgical procedures or treatments. 
 - `Pulse`: Peripheral heart rate, without advanced information like measurement location. 
 - `Respiration`: Number of breaths per minute. 
-- `Route`: Drug and medication administration routes available described by [FDA](http://wayback.archive-it.org/7993/20171115111313/https:/www.fda.gov/Drugs/DevelopmentApprovalProcess/FormsSubmissionRequirements/ElectronicSubmissions/DataStandardsManualmonographs/ucm071667.htm). 
+- `Route`: Drug and medication administration routes available described by [FDA](https://wayback.archive-it.org/7993/20171115111313/https:/www.fda.gov/Drugs/DevelopmentApprovalProcess/FormsSubmissionRequirements/ElectronicSubmissions/DataStandardsManualmonographs/ucm071667.htm). 
 - `Section_Header`: All the section headers present in the text  (Medical History, Family History, Social History, Physical Examination and Vital signs Headers are extracted separately with their specific labels). 
 - `Temperature`: All mentions that refer to body temperature. 
 - `Weight`: All mentions related to a patients weight. 

docs/_posts/2020-05-21-assertion_dl_large_en.md

@@ -148,7 +148,7 @@ The output is a dataframe with a sentence per row and an ``"assertion"`` column
 
 {:.h2_title}
 ## Data Source
-Trained on 2010 i2b2/VA challenge on concepts, assertions, and relations in clinical text with 'embeddings_clinical'.
+Trained with augmented version of 2010 i2b2/VA dataset on concepts, assertions, and relations in clinical text with 'embeddings_clinical'.
 https://portal.dbmi.hms.harvard.edu/projects/n2c2-nlp/
 
 {:.h2_title}

docs/_posts/2020-05-23-ner_clinical_large_en.md

@@ -117,7 +117,7 @@ The output is a dataframe with a sentence per row and a ``"ner"`` column contain
 
 {:.h2_title}
 ## Data Source
-Trained on augmented 2010 i2b2 challenge data with 'embeddings_clinical'.
+Trained with augmented version of 2010 i2b2 dataset with 'embeddings_clinical'.
 https://portal.dbmi.hms.harvard.edu/projects/n2c2-nlp/
 
 {:.h2_title}

docs/_posts/2020-06-20-chunkresolve_snomed_findings_clinical_en.md

@@ -115,4 +115,4 @@ val result = pipeline.fit(Seq.empty[String]).transform(data)
 {:.h2_title}
 ## Data Source
 Trained on SNOMED CT Findings
-http://www.snomed.org/
+[https://www.snomed.org/](https://www.snomed.org/)

docs/_posts/2020-06-24-chunkresolve_rxnorm_xsmall_clinical_en.md

@@ -103,4 +103,4 @@ val result = pipeline.fit(data).transform(data)
 {:.h2_title}
 ## Data Source
 Trained on December 2019 RxNorm Subset
-http://www.snomed.org/
+[https://www.snomed.org/](https://www.snomed.org/)

docs/_posts/2020-09-23-assertion_dl_healthcare_en.md

@@ -123,7 +123,8 @@ nlu.load("en.assert.healthcare").predict("""Patient has a headache for the last
 
 {:.h2_title}
 ## Data Source
-Trained using ``embeddings_clinical`` on 2010 i2b2/VA challenge on concepts, assertions, and relations in clinical text from https://portal.dbmi.hms.harvard.edu/projects/n2c2-nlp/
+Trained with augmented version of 2010 i2b2/VA dataset on concepts, assertions, and relations in clinical text with ``embeddings_clinical``.
+https://portal.dbmi.hms.harvard.edu/projects/n2c2-nlp/
 
 {:.h2_title}
 ## Benchmarking

docs/_posts/2020-09-28-ner_healthcare_de.md

@@ -116,7 +116,7 @@ nlu.load("de.med_ner.healthcare").predict("""Das Kleinzellige Bronchialkarzinom
 
 {:.h2_title}
 ## Data Source
-Trained on 2010 i2b2/VA challenge on concepts, assertions, and relations in clinical text with *w2v_cc_300d*.
+Trained with augmented version of 2010 i2b2/VA dataset on concepts, assertions, and relations in clinical text with ``w2v_cc_300d``.
 
 {:.h2_title}
 ## Benchmarking

docs/_posts/2020-11-27-sbiobertresolve_snomed_auxConcepts_en.md

@@ -119,4 +119,4 @@ val result = pipeline.fit(data).transform(data)
 {:.h2_title}
 ## Data Source
 Trained on SNOMED (CT version) Findings with ``sbiobert_base_cased_mli`` sentence embeddings.
-http://www.snomed.org/
+[https://www.snomed.org/](https://www.snomed.org/)

docs/_posts/2020-11-27-sbiobertresolve_snomed_auxConcepts_int_en.md

@@ -120,4 +120,4 @@ val result = pipeline.fit(data).transform(data)
 {:.h2_title}
 ## Data Source
 Trained on SNOMED (INT version) Findings with ``sbiobert_base_cased_mli`` sentence embeddings.
-http://www.snomed.org/
+[https://www.snomed.org/](https://www.snomed.org/)

docs/_posts/2020-11-27-sbiobertresolve_snomed_findings_en.md

@@ -124,4 +124,4 @@ val result = pipeline.fit(data).transform(data)
 {:.h2_title}
 ## Data Source
 Trained on SNOMED (CT version) Findings with ``sbiobert_base_cased_mli`` sentence embeddings.
-http://www.snomed.org/
+[https://www.snomed.org/](https://www.snomed.org/)

docs/_posts/2020-11-27-sbiobertresolve_snomed_findings_int_en.md

@@ -125,4 +125,4 @@ val result = pipeline.fit(data).transform(data)
 {:.h2_title}
 ## Data Source
 Trained on SNOMED (INT version) Findings with ``sbiobert_base_cased_mli`` sentence embeddings.
-http://www.snomed.org/
+[https://www.snomed.org/](https://www.snomed.org/)

docs/_posts/2021-01-18-jsl_assertion_wip_en.md

@@ -155,7 +155,7 @@ The output is a dataframe with a sentence per row and an ``"assertion"`` column
 
 {:.h2_title}
 ## Data Source
-Trained on 2010 i2b2/VA challenge on concepts, assertions, and relations in clinical text with 'embeddings_clinical'.
+Trained with augmented version of 2010 i2b2/VA dataset on concepts, assertions, and relations in clinical text with ``embeddings_clinical``.
 https://portal.dbmi.hms.harvard.edu/projects/n2c2-nlp/
 
 

docs/_posts/2021-01-18-jsl_assertion_wip_large_en.md

@@ -19,7 +19,7 @@ use_language_switcher: "Python-Scala-Java"
 ## Description
 
 
-The deep neural network architecture for assertion status detection in Spark NLP is based on a BiLSTM framework, and is a modified version of the architecture proposed by Fancellu et.al. (Fancellu, Lopez, and Webber 2016). Its goal is to classify the assertions made on given medical concepts as being present, absent, or possible in the patient, conditionally present in the patient under certain circumstances, hypothetically present in the patient at some future point, and mentioned in the patient report but associated with someone- else (Uzuner et al. 2011). Apart from what we released in other assertion models, an in-house annotations on a curated dataset (6K clinical notes) is used to augment the base assertion dataset (2010 i2b2/VA).
+The deep neural network architecture for assertion status detection in Spark NLP is based on a BiLSTM framework, and is a modified version of the architecture proposed by Fancellu et.al. (Fancellu, Lopez, and Webber 2016). Its goal is to classify the assertions made on given medical concepts as being present, absent, or possible in the patient, conditionally present in the patient under certain circumstances, hypothetically present in the patient at some future point, and mentioned in the patient report but associated with someone- else (Uzuner et al. 2011). Apart from what we released in other assertion models, an in-house annotations on a curated dataset (6K clinical notes) is used to augment the base assertion dataset (augmented version of 2010 i2b2/VA).
 
 
 {:.h2_title}
@@ -175,7 +175,7 @@ The output is a dataframe with a sentence per row and an ``"assertion"`` column
 
 {:.h2_title}
 ## Data Source
-Trained on 2010 i2b2/VA challenge on concepts, assertions, and relations in clinical text with 'embeddings_clinical'.
+Trained with augmented version of 2010 i2b2/VA dataset on concepts, assertions, and relations in clinical text with ``embeddings_clinical``.
 https://portal.dbmi.hms.harvard.edu/projects/n2c2-nlp/
 
 

docs/_posts/Ahmetemintek/2022-02-26-sbiobertresolve_snomed_findings_aux_concepts_en_3_0.md

@@ -35,8 +35,6 @@ In the metadata, the `all_k_aux_labels` can be divided to get further informatio
 
 ## How to use
 
-
-
 <div class="tabs-box" markdown="1">
 {% include programmingLanguageSelectScalaPythonNLU.html %}
 ```python