The newest version of the library comes with an extended visualization of the contract NLI pretrained model.
Contract NLI demo app
The new demo app shows the capabilities of the pretrained model to perform NLI on legal contracts. This model was previously released and can classify statements based on context as one of the following categories:
- Entailment: the statement agrees with the context
- Contradiction: the statement is contradictory to the context
- Neutral: There is no clear relation between the context and the statement
For example, the hypothesis “Receiving Party shall not use any Confidential Information for any purpose other than the purposes stated in Agreement.” given the context below, is classified as Entailment.
Each Recipient shall use the Evaluation Material solely for the purpose of evaluating a Possible Transaction and, subject to Section 5, will not disclose any of the Evaluation Material in any manner whatsoever; provided, however, that any of such information may be disclosed to the Recipient’s Representatives for the purpose of helping the Recipient evaluate a Possible Transaction.
We’ve got 30-day free licenses for you with technical support from our legal team of technical and SMEs. This trial includes complete access to more than 926 models, including Classification, NER, Relation Extraction, Similarity Search, Summarization, Sentiment Analysis, Question Answering, etc., and 120+ legal language models.
Just go to https://www.johnsnowlabs.com/install/ and follow the instructions!
How to run
Legal NLP is extremely easy to run on both clusters and driver-only environments using
Install the johnsnowlabs library:
pip install johnsnowlabs
Then, in Python, install Legal NLP with:
from johnsnowlabs import nlp nlp.install(force_browser=True)
You are ready to use all the capabilities of the library. You can start a spar session and start analyzing legal texts.
from johnsnowlabs import nlp, legal # Start Spark Session spark = nlp.start()
For alternative installation methods of how to install in specific environments, please check the docs.