-
Notifications
You must be signed in to change notification settings - Fork 718
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
2023-01-29-legclf_master_administrative_services_agreement_bert_en (#…
…13427) * Add model 2023-01-29-legclf_master_administrative_services_agreement_bert_en * Add model 2023-01-29-legclf_standstill_agreement_bert_en * Add model 2023-01-29-legclf_adoption_agreement_bert_en * Add model 2023-01-29-legclf_compensation_agreement_bert_en * Add model 2023-01-29-legclf_investment_advisory_and_management_agreement_bert_en * Add model 2023-01-29-legclf_sublicense_agreement_bert_en * Add model 2023-01-29-legclf_retirement_agreement_bert_en * Add model 2023-01-29-legclf_noncompetition_agreement_bert_en * Add model 2023-01-29-legclf_arrangement_agreement_bert_en * Add model 2023-01-29-legclf_performance_share_award_agreement_bert_en * Update 2023-01-29-legclf_standstill_agreement_bert_en.md * Update 2023-01-29-legclf_adoption_agreement_bert_en.md * Update 2023-01-29-legclf_arrangement_agreement_bert_en.md * Update 2023-01-29-legclf_compensation_agreement_bert_en.md * Update 2023-01-29-legclf_investment_advisory_and_management_agreement_bert_en.md * Update 2023-01-29-legclf_master_administrative_services_agreement_bert_en.md * Update 2023-01-29-legclf_noncompetition_agreement_bert_en.md * Update 2023-01-29-legclf_performance_share_award_agreement_bert_en.md * Update 2023-01-29-legclf_retirement_agreement_bert_en.md * Update 2023-01-29-legclf_sublicense_agreement_bert_en.md --------- Co-authored-by: Mary-Sci <meryemyildiz366@gmail.com> Co-authored-by: Merve Ertas Uslu <67653613+Mary-Sci@users.noreply.github.com>
- Loading branch information
3 people
authored
Jan 29, 2023
1 parent
058526d
commit fc09276
Showing
10 changed files
with
1,130 additions
and
0 deletions.
There are no files selected for viewing
113 changes: 113 additions & 0 deletions
113
docs/_posts/Mary-Sci/2023-01-29-legclf_adoption_agreement_bert_en.md
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,113 @@ | ||
| --- | ||
| layout: model | ||
| title: Legal Adoption Agreement Document Classifier (Bert Sentence Embeddings) | ||
| author: John Snow Labs | ||
| name: legclf_adoption_agreement_bert | ||
| date: 2023-01-29 | ||
| tags: [en, legal, classification, adoption, agreement, licensed, bert, tensorflow] | ||
| task: Text Classification | ||
| language: en | ||
| edition: Legal NLP 1.0.0 | ||
| spark_version: 3.0 | ||
| supported: true | ||
| engine: tensorflow | ||
| annotator: LegalClassifierDLModel | ||
| article_header: | ||
| type: cover | ||
| use_language_switcher: "Python-Scala-Java" | ||
| --- | ||
|
|
||
| ## Description | ||
|
|
||
| The `legclf_adoption_agreement_bert` model is a Bert Sentence Embeddings Document Classifier used to classify if the document belongs to the class `adoption-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 | ||
|
|
||
| `adoption-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_adoption_agreement_bert_en_1.0.0_3.0_1674990271078.zip){:.button.button-orange} | ||
| [Copy S3 URI](s3://auxdata.johnsnowlabs.com/legal/models/legclf_adoption_agreement_bert_en_1.0.0_3.0_1674990271078.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} | ||
|
|
||
| ## 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_adoption_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| | ||
| +-------+ | ||
| |[adoption-agreement]| | ||
| |[other]| | ||
| |[other]| | ||
| |[adoption-agreement]| | ||
|
|
||
| ``` | ||
|
|
||
| {:.model-param} | ||
| ## Model Information | ||
|
|
||
| {:.table-model} | ||
| |---|---| | ||
| |Model Name:|legclf_adoption_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 | ||
| label precision recall f1-score support | ||
| other 0.91 0.97 0.94 98 | ||
| standstill-agreement 0.93 0.82 0.87 51 | ||
| accuracy - - 0.92 149 | ||
| macro-avg 0.92 0.90 0.91 149 | ||
| weighted-avg 0.92 0.92 0.92 149 | ||
| ``` |
113 changes: 113 additions & 0 deletions
113
docs/_posts/Mary-Sci/2023-01-29-legclf_arrangement_agreement_bert_en.md
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,113 @@ | ||
| --- | ||
| layout: model | ||
| title: Legal Arrangement Agreement Document Classifier (Bert Sentence Embeddings) | ||
| author: John Snow Labs | ||
| name: legclf_arrangement_agreement_bert | ||
| date: 2023-01-29 | ||
| tags: [en, legal, classification, arrangement, agreement, licensed, bert, tensorflow] | ||
| task: Text Classification | ||
| language: en | ||
| edition: Legal NLP 1.0.0 | ||
| spark_version: 3.0 | ||
| supported: true | ||
| engine: tensorflow | ||
| annotator: LegalClassifierDLModel | ||
| article_header: | ||
| type: cover | ||
| use_language_switcher: "Python-Scala-Java" | ||
| --- | ||
|
|
||
| ## Description | ||
|
|
||
| The `legclf_arrangement_agreement_bert` model is a Bert Sentence Embeddings Document Classifier used to classify if the document belongs to the class `arrangement-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 | ||
|
|
||
| `arrangement-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_arrangement_agreement_bert_en_1.0.0_3.0_1674990701764.zip){:.button.button-orange} | ||
| [Copy S3 URI](s3://auxdata.johnsnowlabs.com/legal/models/legclf_arrangement_agreement_bert_en_1.0.0_3.0_1674990701764.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} | ||
|
|
||
| ## 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_arrangement_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| | ||
| +-------+ | ||
| |[arrangement-agreement]| | ||
| |[other]| | ||
| |[other]| | ||
| |[arrangement-agreement]| | ||
|
|
||
| ``` | ||
|
|
||
| {:.model-param} | ||
| ## Model Information | ||
|
|
||
| {:.table-model} | ||
| |---|---| | ||
| |Model Name:|legclf_arrangement_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 | ||
| label precision recall f1-score support | ||
| arrangement-agreement 0.97 0.95 0.96 39 | ||
| other 0.97 0.98 0.97 57 | ||
| accuracy - - 0.97 96 | ||
| macro-avg 0.97 0.97 0.97 96 | ||
| weighted-avg 0.97 0.97 0.97 96 | ||
| ``` |
113 changes: 113 additions & 0 deletions
113
docs/_posts/Mary-Sci/2023-01-29-legclf_compensation_agreement_bert_en.md
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,113 @@ | ||
| --- | ||
| layout: model | ||
| title: Legal Compensation Agreement Document Classifier (Bert Sentence Embeddings) | ||
| author: John Snow Labs | ||
| name: legclf_compensation_agreement_bert | ||
| date: 2023-01-29 | ||
| tags: [en, legal, classification, compensation, agreement, licensed, bert, tensorflow] | ||
| task: Text Classification | ||
| language: en | ||
| edition: Legal NLP 1.0.0 | ||
| spark_version: 3.0 | ||
| supported: true | ||
| engine: tensorflow | ||
| annotator: LegalClassifierDLModel | ||
| article_header: | ||
| type: cover | ||
| use_language_switcher: "Python-Scala-Java" | ||
| --- | ||
|
|
||
| ## Description | ||
|
|
||
| The `legclf_compensation_agreement_bert` model is a Bert Sentence Embeddings Document Classifier used to classify if the document belongs to the class `compensation-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 | ||
|
|
||
| `compensation-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_compensation_agreement_bert_en_1.0.0_3.0_1674990338214.zip){:.button.button-orange} | ||
| [Copy S3 URI](s3://auxdata.johnsnowlabs.com/legal/models/legclf_compensation_agreement_bert_en_1.0.0_3.0_1674990338214.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} | ||
|
|
||
| ## 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_compensation_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| | ||
| +-------+ | ||
| |[compensation-agreement]| | ||
| |[other]| | ||
| |[other]| | ||
| |[compensation-agreement]| | ||
|
|
||
| ``` | ||
|
|
||
| {:.model-param} | ||
| ## Model Information | ||
|
|
||
| {:.table-model} | ||
| |---|---| | ||
| |Model Name:|legclf_compensation_agreement_bert| | ||
| |Compatibility:|Legal NLP 1.0.0+| | ||
| |License:|Licensed| | ||
| |Edition:|Official| | ||
| |Input Labels:|[sentence_embeddings]| | ||
| |Output Labels:|[class]| | ||
| |Language:|en| | ||
| |Size:|22.2 MB| | ||
|
|
||
| ## References | ||
|
|
||
| Legal documents, scrapped from the Internet, and classified in-house + SEC documents + Lawinsider categorization | ||
|
|
||
| ## Benchmarking | ||
|
|
||
| ```bash | ||
| label precision recall f1-score support | ||
| compensation-agreement 1.00 0.95 0.97 40 | ||
| other 0.96 1.00 0.98 55 | ||
| accuracy - - 0.98 95 | ||
| macro-avg 0.98 0.97 0.98 95 | ||
| weighted-avg 0.98 0.98 0.98 95 | ||
| ``` |
Oops, something went wrong.