JohnSnowLabs
diff --git a/‎docs/_posts/bunyamin-polat/2022-11-10-legner_romanian_official_lg_ro.md
Lines changed: 1 addition & 1 deletion b/‎docs/_posts/bunyamin-polat/2022-11-10-legner_romanian_official_lg_ro.md
Lines changed: 1 addition & 1 deletion
diff --git a/‎docs/_posts/bunyamin-polat/2022-11-10-legner_romanian_official_md_ro.md
Lines changed: 1 addition & 1 deletion b/‎docs/_posts/bunyamin-polat/2022-11-10-legner_romanian_official_md_ro.md
Lines changed: 1 addition & 1 deletion
diff --git a/‎docs/_posts/bunyamin-polat/2022-11-10-legner_romanian_official_sm_ro.md
Lines changed: 1 addition & 1 deletion b/‎docs/_posts/bunyamin-polat/2022-11-10-legner_romanian_official_sm_ro.md
Lines changed: 1 addition & 1 deletion
diff --git a/‎docs/_posts/bunyamin-polat/2022-11-24-legclf_administration_agreement_bert_en.md
Lines changed: 115 additions & 0 deletions b/‎docs/_posts/bunyamin-polat/2022-11-24-legclf_administration_agreement_bert_en.md
Lines changed: 115 additions & 0 deletions
diff --git a/‎docs/_posts/bunyamin-polat/2022-11-24-legclf_administration_agreement_en.md
Lines changed: 127 additions & 0 deletions b/‎docs/_posts/bunyamin-polat/2022-11-24-legclf_administration_agreement_en.md
Lines changed: 127 additions & 0 deletions
diff --git a/‎docs/_posts/bunyamin-polat/2022-11-24-legclf_agreement_and_declaration_bert_en.md
Lines changed: 114 additions & 0 deletions b/‎docs/_posts/bunyamin-polat/2022-11-24-legclf_agreement_and_declaration_bert_en.md
Lines changed: 114 additions & 0 deletions
@@ -10,7 +10,7 @@ language: ro
 edition: Legal NLP 1.0.0
 spark_version: 3.0
 supported: true
-annotator: FinanceNerModel
+annotator: LegalNerModel
 article_header:
   type: cover
 use_language_switcher: "Python-Scala-Java"
 
@@ -10,7 +10,7 @@ language: ro
 edition: Legal NLP 1.0.0
 spark_version: 3.0
 supported: true
-annotator: FinanceNerModel
+annotator: LegalNerModel
 article_header:
   type: cover
 use_language_switcher: "Python-Scala-Java"
 
@@ -10,7 +10,7 @@ language: ro
 edition: Legal NLP 1.0.0
 spark_version: 3.0
 supported: true
-annotator: FinanceNerModel
+annotator: LegalNerModel
 article_header:
   type: cover
 use_language_switcher: "Python-Scala-Java"
 
@@ -0,0 +1,115 @@
+---
+layout: model
+title: Legal Administration Agreement Document Classifier (Bert Sentence Embeddings)
+author: John Snow Labs
+name: legclf_administration_agreement_bert
+date: 2022-11-24
+tags: [en, legal, classification, agreement, administration, licensed, bert]
+task: Text Classification
+language: en
+edition: Legal NLP 1.0.0
+spark_version: 3.0
+supported: true
+article_header:
+type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+The `legclf_administration_agreement_bert` model is a Bert Sentence Embeddings Document Classifier used to classify if the document belongs to the class `administration-agreement` (check [Lawinsider](https://www.lawinsider.com/tags) for similar document type classification) or not (Binary Classification).
+
+Unlike the Longformer model, this model is lighter in terms of inference time.
+
+## Predicted Entities
+
+`administration-agreement`, `other`
+
+{:.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/legal/models/legclf_administration_agreement_bert_en_1.0.0_3.0_1669300445143.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 = nlp.DocumentAssembler()\
+    .setInputCol("text")\
+    .setOutputCol("document")
+  
+embeddings = nlp.BertSentenceEmbeddings.pretrained("sent_bert_base_cased", "en")\
+    .setInputCols("document")\
+    .setOutputCol("sentence_embeddings")
+    
+doc_classifier = legal.ClassifierDLModel.pretrained("legclf_administration_agreement_bert", "en", "legal/models")\
+    .setInputCols(["sentence_embeddings"])\
+    .setOutputCol("category")
+    
+nlpPipeline = nlp.Pipeline(stages=[
+    document_assembler, 
+    embeddings,
+    doc_classifier])
+ 
+df = spark.createDataFrame([["YOUR TEXT HERE"]]).toDF("text")
+
+model = nlpPipeline.fit(df)
+
+result = model.transform(df)
+
+```
+
+</div>
+
+## Results
+
+```bash
+
++-------+
+|result|
++-------+
+|[administration-agreement]|
+|[other]|
+|[other]|
+|[administration-agreement]|
+
+```
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|legclf_administration_agreement_bert|
+|Compatibility:|Legal NLP 1.0.0+|
+|License:|Licensed|
+|Edition:|Official|
+|Input Labels:|[sentence_embeddings]|
+|Output Labels:|[class]|
+|Language:|en|
+|Size:|22.4 MB|
+
+## References
+
+Legal documents, scrapped from the Internet, and classified in-house + SEC documents + Lawinsider categorization
+
+## Benchmarking
+
+```bash
+
+                          precision    recall  f1-score   support
+
+administration-agreement       0.88      0.81      0.84        26
+                   other       0.93      0.95      0.94        65
+
+                accuracy                           0.91        91
+               macro-avg       0.90      0.88      0.89        91
+            weighted-avg       0.91      0.91      0.91        91
+
+
+```
@@ -0,0 +1,127 @@
+---
+layout: model
+title: Legal Administration Agreement Document Classifier (Longformer)
+author: John Snow Labs
+name: legclf_administration_agreement
+date: 2022-11-24
+tags: [en, legal, classification, agreement, administration, licensed]
+task: Text Classification
+language: en
+edition: Legal NLP 1.0.0
+spark_version: 3.0
+supported: true
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+The `legclf_administration_agreement` model is a Legal Longformer Document Classifier to classify if the document belongs to the class `administration-agreement` (check [Lawinsider](https://www.lawinsider.com/tags) for similar document type classification) or not (Binary Classification).
+
+Longformers have a restriction on 4096 tokens, so only the first 4096 tokens will be taken into account. We have realised that for the big majority of the documents in legal corpora, if they are clean and only contain the legal document without any extra information before, 4096 is enough to perform Document Classification.
+
+If not, let us know and we can carry out another approach for you: getting chunks of 4096 tokens and average the embeddings, training with the averaged version, what means all document will be taken into account. But this theoretically should not be required.
+
+## Predicted Entities
+
+`administration-agreement`, `other`
+
+{:.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/legal/models/legclf_administration_agreement_en_1.0.0_3.0_1669290751753.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 = nlp.DocumentAssembler()\
+     .setInputCol("text")\
+     .setOutputCol("document")\
+     
+tokenizer = nlp.Tokenizer()\
+     .setInputCols(["document"])\
+     .setOutputCol("token")
+     
+embeddings = nlp.LongformerEmbeddings.pretrained("legal_longformer_base", "en")\
+    .setInputCols("document", "token")\
+    .setOutputCol("embeddings")
+    
+sentence_embeddings = nlp.SentenceEmbeddings()\
+    .setInputCols(["document", "embeddings"])\
+    .setOutputCol("sentence_embeddings")\
+    .setPoolingStrategy("AVERAGE")
+    
+doc_classifier = legal.ClassifierDLModel.pretrained("legclf_administration_agreement", "en", "legal/models")\
+    .setInputCols(["sentence_embeddings"])\
+    .setOutputCol("category")
+    
+nlpPipeline = nlp.Pipeline(stages=[
+    document_assembler, 
+    tokenizer,
+    embeddings,
+    sentence_embeddings,
+    doc_classifier])
+ 
+df = spark.createDataFrame([["YOUR TEXT HERE"]]).toDF("text")
+
+model = nlpPipeline.fit(df)
+
+result = model.transform(df)
+
+```
+
+</div>
+
+## Results
+
+```bash
+
++-------+
+|result|
++-------+
+|[administration-agreement]|
+|[other]|
+|[other]|
+|[administration-agreement]|
+
+```
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|legclf_administration_agreement|
+|Compatibility:|Legal NLP 1.0.0+|
+|License:|Licensed|
+|Edition:|Official|
+|Input Labels:|[sentence_embeddings]|
+|Output Labels:|[class]|
+|Language:|en|
+|Size:|21.7 MB|
+
+## References
+
+Legal documents, scrapped from the Internet, and classified in-house + SEC documents + Lawinsider categorization
+
+## Benchmarking
+
+```bash
+
+                             precision    recall  f1-score   support
+
+administration-agreement       0.93      0.93      0.93        29
+                   other       0.98      0.98      0.98        90
+
+                accuracy                           0.97       119
+               macro-avg       0.95      0.95      0.95       119
+            weighted-avg       0.97      0.97      0.97       119
+
+```
@@ -0,0 +1,114 @@
+---
+layout: model
+title: Legal Agreement And Declaration Document Classifier (Bert Sentence Embeddings)
+author: John Snow Labs
+name: legclf_agreement_and_declaration_bert
+date: 2022-11-24
+tags: [en, legal, classification, agreement, declaration, licensed, bert]
+task: Text Classification
+language: en
+edition: Legal NLP 1.0.0
+spark_version: 3.0
+supported: true
+article_header:
+type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+The `legclf_agreement_and_declaration_bert` model is a Bert Sentence Embeddings Document Classifier used to classify if the document belongs to the class `agreement-and-declaration` (check [Lawinsider](https://www.lawinsider.com/tags) for similar document type classification) or not (Binary Classification).
+
+Unlike the Longformer model, this model is lighter in terms of inference time.
+
+## Predicted Entities
+
+`agreement-and-declaration`, `other`
+
+{:.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/legal/models/legclf_agreement_and_declaration_bert_en_1.0.0_3.0_1669301061858.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 = nlp.DocumentAssembler()\
+    .setInputCol("text")\
+    .setOutputCol("document")
+  
+embeddings = nlp.BertSentenceEmbeddings.pretrained("sent_bert_base_cased", "en")\
+    .setInputCols("document")\
+    .setOutputCol("sentence_embeddings")
+    
+doc_classifier = legal.ClassifierDLModel.pretrained("legclf_agreement_and_declaration_bert", "en", "legal/models")\
+    .setInputCols(["sentence_embeddings"])\
+    .setOutputCol("category")
+    
+nlpPipeline = nlp.Pipeline(stages=[
+    document_assembler, 
+    embeddings,
+    doc_classifier])
+ 
+df = spark.createDataFrame([["YOUR TEXT HERE"]]).toDF("text")
+
+model = nlpPipeline.fit(df)
+
+result = model.transform(df)
+
+```
+
+</div>
+
+## Results
+
+```bash
+
++-------+
+|result|
++-------+
+|[agreement-and-declaration]|
+|[other]|
+|[other]|
+|[agreement-and-declaration]|
+
+```
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|legclf_agreement_and_declaration_bert|
+|Compatibility:|Legal NLP 1.0.0+|
+|License:|Licensed|
+|Edition:|Official|
+|Input Labels:|[sentence_embeddings]|
+|Output Labels:|[class]|
+|Language:|en|
+|Size:|22.8 MB|
+
+## References
+
+Legal documents, scrapped from the Internet, and classified in-house + SEC documents + Lawinsider categorization
+
+## Benchmarking
+
+```bash
+
+                           precision    recall  f1-score   support
+
+agreement-and-declaration       1.00      0.98      0.99        43
+                    other       0.99      1.00      0.99        82
+
+                 accuracy                           0.99       125
+                macro-avg       0.99      0.99      0.99       125
+             weighted-avg       0.99      0.99      0.99       125
+
+```