NLP applications in Legal Tech

We talk a lot about Artificial Intelligence, but in the end we don't really look at its concrete benefits for the company. Today we are exploring concrete applications of NLP (the branch of AI aimed at understanding and processing human language) in the Legal Tech.

Artificial Intelligence in business is still a fantasy for many of us. For some, Artificial Intelligence frees humans from dull tasks; for others, it would alienate us and destroy jobs. But what few of us know is that AI and Machine Learning are already very present in our companies, and that we use them every day!

NLP (Natural Language Processing) is one of the most prolific fields of application of AI. It is the branch of Artificial Intelligence which involves understanding and processing human language.

Its uses in business are very numerous: NLP offers a wealth of opportunities to increase productivity, reliability, and make better decisions.

Having explored the use cases of NLP in Marketing and Customer Relations, and then in the HR sector, we now turn to the applications of language processing for Legal professionals.

Indeed, if there is a professional field where textual data is numerous and very important, it is the Legal industry! Legal texts, contracts, case law… all the key data is written in Natural Language, and the devil is in the details. Let’s see how AI can save Legal professionals a huge amount of time.

1- Legal watch and Case Law research

Semantic Analysis helps legal professionals save time and manage ongoing legal information without spending nights there.

Law is a particularly favorable subject for the implementation of an analysis and semantic search engine because, as on the Web, the texts of laws and court decisions are based on a close mesh of links and references.

However, unlike the pages indexed by Google, these links are not clickable, explicit links that can be easily used in the HTML code of a web page: they are quotes, references, data incorporated into the body of the texts of law or in court decisions, and written in natural language. The development of a relevant search engine depends not only on identifying the links between legal texts and decisions, but also on understanding the context by the machine.

Concrete case: Doctrine or NLP to save Lawyers’ time

Doctrine, the legal search engine, has established itself in a few months as a benchmark in this universe. In the same way that Google’s algorithms understand the underlying links between different information, those of the French startup help lawyers and jurists to understand the texts of laws and court decisions in order to be able to index them in a relevant way.

Nlp legal text > Dassault Systèmes

Doctrine indexes, classifies and summarizes legal texts and judgment comments using Automatic Language Processing.

Thanks to NLP, legal professionals can:

  • Structure legal information
  • Build winning strategies in litigation
  • Save time and relevance to optimize the relationship with the customer

“If the lawyer wants to refocus on his client relationship, he must first save time on his legal research, which is often time consuming and difficult to justify to the client. AI makes this possible by rebuilding the ecosystem of a court decision or law and making them immediately available. By doing so, the lawyer can find key information, every time and in a minimum of time. 

Extract from the book “Traitement automatique des langues, comprendre les textes grâce à l’intelligence artificielle” (“Automatic Language Processing, understanding texts using Artificial Intelligence”), by François-Régis Chaumartin and Pirmin Lemberger.

2- Virtual data room

A data room is a secure storage space with strictly controlled access where an organization provides users with a large volume of confidential documents.

It responds to situations requiring a business audit (due diligence): mergers & acquisitions, fundraising, restructuring, strategic partnerships … This audit is a long procedure that can last several weeks when the number of documents is large. This procedure mobilizes high-level professionals: lawyers, accountants, human resources specialists, etc. Partial automation can save time and money, and thus improve the quality and security of the analysis while minimizing the risk of human error.

In this context, Semantic Analysis makes it possible to find the answer to a question asked in a document. For example, if in a set of confidentiality agreements one seeks the geographic locations of the courts designated to adjudicate disputes, these requests will isolate the relevant passages.

3- Analysis of Calls for Tenders and contracts with the NLP

In the area of ​​contract and tender management, the return on investment of NLP technologies has also become significant.

In large companies, the examination of legal and contractual documents mobilizes several thousand man-days each year on expert profiles. Semantic Analysis makes the job of corporate lawyers easier by helping them quickly identify points of attention in a tender or contract, reducing document processing time and pain.

Feedback: Thales automates the reading of calls for tenders with NLP

The Thales group receives thousands of tenders per year, each averaging 500 pages. Lawyers are responsible for studying them and synthesizing them in the form of a 5 or 6 page legal memo which allows managers to decide whether or not they respond to the Call for Tenders. A pilot project has been set up, validating the value of Semantic Analysis to partly automate this task.

To read in MagIT: Thalès is testing a junior Digital Lawyer to respond to calls for tenders. (Article in French)

NLP and law: endless use cases!

These are just a few examples of Automatic Language Processing applications for the legal profession.

Whenever a task involves reading and understanding written or spoken text, AI can be of service to humans, especially with new Deep Learning technologies.