Demos
We are happy to announce the Legal NLP 1.7.0 is out!
Legal NLP is a John Snow Lab’s product, launched 2022 to provide state-of-the-art, autoscalable, domain-specific NLP on top of Spark.
With more than 600 models, featuring Deep Learning and Transformer-based architectures, Legal NLP includes:
- Annotators to carry out Name Entity Recognition, Relation Extraction, Assertion Status / Understanding Entities in Context, Data Mapping to external sources, Deidentification, Question Answering, Table Question Answering, Sentiment Analysis, Summarization and much more, both training andinference!
- Zero-shotName Entity Recognition and Relation extraction;
- 600+ pretrained Deep Learning / Transformer-based models;
- Fully integration with Databricks, AWS or Azure;
- 33+ notebooks and 25+ demos ready to showcase its features.
- Full integration with NLP Lab (former NLP Annotation Lab) for managing your annotation projects and train your legal models in a zero-code fashion.
- Compatiblity with Visual NLP, to combine OCR/Visual capabilities, as Signature Extraction, Form Recognition or Table detection, to Legal NLP.
New 60 Clause and Document Classifiers
- Documents: Identify Sales, Acquisition, LLC Company Operation, Non-competition , Compesation, AdoptionAgreements, and many more!
- Clauses:Identify sections talking about Disclosure, Indemnification Procedures, Absence of Litigation, Tax Treatments, Subcontractors, CUSIP numbers, Non-exclusivity, Reimbursement of expenses, and many more!
Check our more than 400 models in Models Hub.
New 3 Legal Roberta For Question Answering in Legal NLP 1.7
Trained on a QA dataset (SQUADv2) and finetuned on CUAD dataset (commercial agreements), these three models can help you to identify chunks of information answering to your natural language questions.
Models: legqa_roberta_cuad_large, legqa_roberta_cuad_base and legqa_roberta_cuad_small.
New 3 Legal Zero-shot NER
RobertaForSequenceClassification based models, finetuned on CUAD dataset (commercial agreements) to extract NER chunks from your texts using questions.
Models: legner_roberta_zeroshot_cuad_base, legner_roberta_zeroshot_cuad_small, legner_roberta_zeroshot_cuad_large
‘Highlight the parts (if any) of this contract related to “Parties” that should be reviewed by a lawyer. Details: The two or more parties who signed the contract’
New classifier for Merge Agreements
legclf_bert_maud: This is a Bert-based model, which can be used to classify texts into 7 classes. This is a Multiclass model, meaning only one label will be returned as an output. This dataset includes 152 merger agreements with 39,000 multiple-choice reading comprehension samples that have been manually tagged by lawyers. The following classes are included:
Conditions to Closing, Deal Protection and Related Provisions, General Information, Knowledge, Material Adverse Effect, Operating and Efforts Covenant, Remedies
New Legal Pipeline for Introductory (Parties) clause in Legal NLP 1.7
A mixed pipeline with improved NER, and a hybrid NER+ZeroShotNER has been released, including capabilities of extracting DOC_TYPE, PARTY, ALIAS, FORMER_NAME, EFFDATE from agreements: legpipe_ner_contract_doc_parties_alias_former
MNDA Multilabel Classifier
This model ( legmulticlf_mnda_sections) should be run on each paragraph of NDA clauses, and will retrieve a series of 1..N labels for each of them. The possible clause types detected my this model in NDA / MNDA aggrements are:
- Parties to the Agreement — Names of the Parties Clause
- Identification of What Information Is Confidential — Definition of onfidential Information Clause
- Use of Confidential Information: Permitted Use Clause and Obligations of the Recipient
- Time Frame of the Agreement — Termination Clause
- Return of Confidential Information Clause
- Remedies for Breaches of Agreement — Remedies Clause
- Non-Solicitation Clause
- Dispute Resolution Clause
- Exceptions Clause
- Non-competition clause
Merge Agreements Understanding (MAUD dataset) in Legal NLP 1.7
The legclf_bert_maud allows you to classify different sections of Merge Agreements as Conditions to Closing, Deal Protection and Related Provisions, General Information, Knowledge, Material Adverse Effect, Operating and Efforts Covenant, Remedies.
New Document Splitting Demo
See how you can carry out page, section, sentence, subsentence splitting with our TextSplitter Annotator, released in 4.2.9 version of johnsnowlabs.
Certification Training slides
If you have missed our certification trainings, take a look at our slides about NLP for law.
How to run
Legal NLP is very easy to run on both clusters and driver-only environments using johnsnowlabs library:
!pip install johnsnowlabs
nlp.install(force_browser=True) nlp.start()
Fancy trying?
We’ve got 30-days free licenses for you with technical support from our legal team of technical and SME. Just go to https://www.johnsnowlabs.com/install/ and follow the instructions!
