Legal NLP releases new Contract NLI model and more

The latest 1.16.0 version of Legal NLP releases a new Contract NLI model and added new demonstration apps for Question Answering and Summarization

Contract NLI model

The new model is based on Flan T5 (LLM model released by Google) and finetuned on the Stanford Contract NLI dataset. This model can apply Natural Language Inference (NLI) in legal contracts, meaning that it can classify whether a hypothesis is an entailment, contradiction or neutral (not related to or not clear) to the premise (context).

See the following examples:

• Not clear if hypothesis is related to premise:

• Contradiction:

• Entailment:

New demo apps

We release new demo apps for Question Answering and for Summarization, showing examples using the latest models of the library.

• New Flan T5 based model for Question Answering:

• New Flan T5 based model for Summarization:

Showing the capabilities of the pretrained models can help practitioners understand how to use Legal NLP for their specific use cases.

Fancy trying?

We’ve got 30-days free licenses for you with technical support from our legal team of technical and SME. 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!

Don’t forget to check our notebooks and demos.

How to run

Legal NLP is extremely easy to run on both clusters and driver-only environments using johnsnowlabs library:

! pip install johnsnowlabs

from johnsnowlabs import nlp


nlp.install(force_browser=True)

# Start Spark Session
spark = nlp.start()