How to Build a Private ChatGPT Using Open-Source Technology? Download our free white paper.

Identify Named Entities in a document by using Lettria's technology

Documentation is accumulated by many companies. This stored data is a goldmine on which they can capitalize: names of customers, partners, contracts, etc. Here's how to leverage it.

Named Entity Recognition (NER) identifies the key semantic elements of a sentence. A named entity must designate a perceptible reality and represent an element essential to the understanding of a text such as, for example: a name, an address, an email, a phone number, a city, a date, etc.

How to deal with a wide range of documents?

Documentation is one of the main assets accumulated by companies and administrations. The stored data is a treasure trove of information on which these entities must capitalize: names of customers, partners, contracts, etc.

However, the manual analysis, processing and archiving of documents are long and tedious tasks. The diversity of documents that have their own specificities (contracts, customer files, product files, etc.) makes their management more complex, and they are often neglected because of their human and financial cost.

Many legal teams want to have quick access to specific information in a contract, such as the payment date, in order to avoid missing a deadline, for example.

Want to learn how to build a private ChatGPT using open-source technology?

Automate the extraction and classification of named entities from a document

Lettria's technology offers a dual approach that combines machine learning with regular expressions.

Our solution, applied to a company's legal department for example, enables the rapid and automatic isolation of key information from a contract (dates, stakeholders, etc.) via a named entity detection tool, making it easier to process priority deadlines.

Essential information is automatically extracted and classified, making it easier to find and archive. The time savings are enormous and allow the process to be optimized by reducing processing costs.

Lettria's offer allows you to eliminate non-productive tasks with little added value, and also to gain efficiency by facilitating access to information.

What are the advantages of an integrated solution?

  • Back office automation;
  • Process optimization and cost reduction;
  • Improved document processing efficiency.

Let's zoom in on our partners' use cases

  • Retail: Our solution allows you to tag and classify a wide range of documents such as product sheets and extract all the essential key information such as price, name, quantity available, delivery times, etc.
  • Insurance: The analysis of contracts and offers is facilitated by the detection of named entities. Contracts can be automatically analyzed to extract the names of the parties involved, the validity dates, the main clauses, etc.
  • HR: The identification of key information in a document, applied to a CV for example, facilitates screening tasks thanks to the extraction of essential data.


Build your NLP pipeline for free
Get started ->