“NLP – IA” Natural Language Processing, Disrupting Legal Document Classification

Project Description

The goal of the project is to conduct a market validation of our SaaS (Software as a Service) product, which is based on Natural Language Processing (NLP) and Artificial Intelligence, applied to the Tender Bidding Management. Our product will be capable of automatically interpreting and categorizing legal documents related to the Tender Bidding Management taking into consideration all peculiarities related to legal jargon.

In order to conduct the market validation, Ferrovial’s employees will use our product through a graphical user interface containing an intuitive workspace accessed by the internet browser. The client role is played by Ferrovial, and the technology providers are Fondanzione Bruno Kessler and Polytechnic University of Madrid. Indra Soluciones TI is the leader of the project and the Business Champion.

The expected outcome of our NLP solution is to be able to dramatically cut operational costs while processing tender bidding documents automatically, reducing manual cost up to 80% in document classification and 40% in metadata extraction.

Ferrovial’s legal department and bidding department has provided four use cases related to the Tender Bidding Management process in the construction industry:

1. The automatic classification of documents (both in Spanish and in English)
2. The automatic generation of the Legal Report in the tender process (both in Spanish and in English)
3. The automatic generation of the Project Report in the tender process (in English)
4. The automatic generation of a list including all the project Requirements that have an economic impact on the price calculation (in English))

Our solution is for large companies or Business Process Services, spending too much time and effort browsing through legal documents trying to understand the legal jargon, in order to classify them and extract the right information. We automate the processing of huge volumes of documents, written in natural language, handled manually and repetitively by employees. Our product is capable of converting non-structured data into structured data.

Collaborating Companies or Organisations

Indra's Role

Indra is the Business Champion and will lead the consortium, provide the NLP technological assets to be market-validated and exploit the results to commercialize the final product.

Universities and Technology Centers

Technologies used

Our SaaS product uses Natural language Processing to automatically extract information and detect entities from documents. We use NLP hybrid techniques: Deep learning and Regular Expressions.

Our solution is cloud native and can be deployed in any public or private cloud that uses Docker as a lightweight virtualization system. Our product is implemented following the Micro-Service Arquitectura paradigm.

More information

This project, under reference nº ID-19142, has received funding from the European Institute of Innovation and Technology (EIT). This body of the European Union receives support from the European Union's Horizon 2020 research and innovation programme. /p>