

The most widely used NLP library in Legal
As with last year’s survey, Spark NLP is the most popular library for production use
Which NLP Libraries does your organization use?
Spark NLP
spaCy
Allen NLP
nltk
Stanford CoreNLP
Gensim
Hugging Face
Other
Rasa NLU
How Vakilsearch Understands Scanned Legal & Tax Forms with Legal NLP

- The document classification pipeline outperformed the comparable pipelines by 9% and attained 96% accuracy.
- The identity card information extraction pipeline achieved 87% accuracy
- The mailing address resolution pipeline achieved 89% accuracy
What’s in the Box
State-of-the-art software + pre-trained legal-specific models

Legal NLP in Action

Extract Legal Relationships
Automatically identify relationships even when they are mentioned using aliases.


Normalization & Data Augmentation
Enrich extracted company names with additional EDGAR information.


Information Extraction on Clauses
Use a Q&A model to retrieve the piece of valuable information with less length limitations than NER.
Legal De-identification
De-identify and mask sensitive personal information in documents and images.

Get Started with Legal NLP