Search / connect / combine / analyze your (or any) data and documents by MEANING.
In natural language, in different languages.
Forget keywords and limited bots.
Let's turn data into value.

Discover our solutions

LEXISTEMS' solutions apply directly to any business and/or public documents and data assets. As 100% configurable APIs, they integrate seamlessly into your web, mobile, AR/VR or appliance applications.

The® API

The API is LEXISTEMS' all-inclusive solution for accessing and processing data and documents by MEANING. It combines all LEXISTEMS's APIs in an easy-to-install package. is designed for a wide spectrum of business use cases, like the creation of 24/7 digital experts delivering high-value insights and analyses from multiple sources of heterogeneous data.

This example comments a demo of on an open dataset (Wikidata). Feel free to compare with your favorite search engine or digital assistant...

The LEXISTEMS API used by the app queries data by meaning. Here is an example of a tricky question - and a perfect answer returned. Each answer element has a clickable title which links to the relevant data in the source knowledge base (Wikidata here).

Sliding the answer of the previous screenshot... Note the "Idea" zone in the demo app that offers buttons with 1-click questions (for digging deeper on the current topic, on other topics or just for fun). The questions relate to Donald Trump, not his children. That's because...

...The 1-click questions provided by are in fact relevant to context. In this screenshot, we clicked on "place of birth", and got the corresponding answer. In addition to being very handy, this shows that the API uses context intelligently to return results.

Sliding the answer of the previous screenshot...

This screenshot shows a simple question with an answer containing a full text and an image, both extracted by meaning from the source knowledge base. Note the "street" phrasing.

Scrolling down the previous screenshot, we see more contextual 1-click questions. These are related to the topic of the question (Bob Marley) rather than to the topic of the answer (Reggae). This adaptive process by the API can be configured easily. Let's click on "place of birth"...

Clicking on "place of birth" in the previous screenshot returned a compound answer (text + image). The context-related buttons return the same results as if the question had been asked "completely". If data is available in the source knowledge base, it will be aggregated according to API or user settings.

Another example of the power of The question might sound silly but, although simple, it is very interesting from a data science standpoint as it is conceptual, poorly phrased and has misleading keywords. NB: also offers links to more websites related to the topic (the star is for Donald Trump's official website).

Another example of answer returned from an 1-click contextual question, with the aggregated elements and more context buttons.

The API accepts colloquial entity names, even foreign.

Of course, can return simple, factual answers to simple, factual questions. Three examples of data types here: one encyclopedic, one mathematic (we used a simple example), one geographic.

Using the 1-click context questions is an efficient way to dig deeper into something. Ok, most people know that – regardless of the phrasing - Shakespeare wrote Hamlet but...

Clicking on "characters" gives you the dramatis personae of the play in 1 click...

As well as the narrative location...

As well as more information about the Tragedy genre - and the list goes on... Is there any quicker and more transverse way to browse a topic?

Another example of a composite, listed answer on a simple question that most assistants and search engines won't answer directly.

Sliding the answer of the previous screenshot...

The API is permissive regarding questions phrasing. Note also that there are several famous people named "Bach". Here, is configured to return only the most consulted result, but many other conditions or statistical scorings are applicable (recency, update, length, additional elements...).

Since always include its "sources" in the results it returns, adding a verification or a sources consulting scheme right into powered applications (Web, mobile, AR/VR or appliance) is very easy.

The API adds MEANING-based search to your applications, on business and/or public data. Because it is not limited to keywords, outperforms today's most famous search engines by several orders of magnitude. It also allows you to query data available in a language different than that of the question.

The API lets you build intelligent digital assistants capable of answering complex questions in natural language on a wide range of business or general domains. Compared to today's bots APIs, is not limited to simple intentions and named entities, and includes SensibleSearch's MEANING-based search functionalities.

Meaning in your apps ?

It's as easy as 1-2-3.

LEXISTEMS' solutions make giving the power of meaning
 to your apps a no-brainer.

With a few lines of code, you can tap your (or any)
 data and documents with a zillion times more sense
 than through keywords.

This JavaScript example adds an API® interface into any web, mobile, AR/VR or appliance app. It also features an optional conversation widget for questions + answers. In both cases, dozens of settings are available to adapt everything
 to your exact needs.

No disruption anywhere.

Your teams will love the ease. Your users will love the results.

LEXISTEMS APIs integration example

You're in control of everything.

100 % securely.

LEXISTEMS APIs customers have their own private administration console on their own servers.
 End-to-end HTTP2 access (the fast, unbreakable HTTP)
 and Docker containers with NO ports opened
 means absolute security and scalability.

The console manages and monitors everything API-wise: settings, queries, results, users, accesses... even usage of the console itself. It also serves as an interactive front-end
 to add / edit custom data to be used by the API.

Different API administration tasks can be delegated and monitored in an extensible role-based management model.

All the data used or produced by the console can be directly exported in JSON, XML, CSV, TXT, SQL or MS-Excel format
 for reuse or analysis.


LEXISTEMS* delivers solutions
for querying, connecting and creating information
by meaning, in different languages.

Based on disruptive technologies,
these solutions instantly turn *your* data assets
into competitive advantages and profitable applications.

Intelligent interaction between man and data is the next development of our digital civilization. With the support of its institutional and business partners, LEXISTEMS makes it happen today.

A major innovation - LEXISTEMS' solutions let you search, query and process data and documents by MEANING, using natural language, in different languages. Which is way more powerful and pertinent than with keywords. For organizations, employees and customers, this means measurable improvements in ease of use, empowerment and performance on a daily basis.
Name your use case - At our customers, LEXISTEMS' solutions cover a wide range of needs and assignments. They generate expert insights from complex questions. They gather and connect heterogeneous data (whatever their source, format and structure) to return added-value information automatically. They industrialize knowledge mining and analysis in general or business contexts: finance, legal, industrial, medical...
Customer + ROI first - LEXISTEMS' solutions are customer centric. They deliver meaningful, actionable results, helping you create substantial value from business and public data of any type (textual, numeric, mathematic, geographic...). You will benchmark them easily, install them in a matter of days, consume them à la carte and appreciate their state-of-the-art security.

LEXISTEMS - Governance

Coming from major French universities (Centrale Paris, EM Lyon, ENS Lyon, Paris IV - Sorbonne, Paris V - René Descartes) and the HPC (High-Performance Computing) ecosystem, we bring unbounding energy and passion to work everyday. We're independent and inquisitive, open to new ideas and we love to talk...

  • Marie GRANIER
    Co-founder & CEO
    MBA and engineer in Applied mathematics.
    Specialized in Startup management and Corporate problem solving.
  • Frédéric MILLIOT
    Co-founder & CTO
    PhD. MA. Software architect.
    Specialized in High Performance Computing and semantic Web applications.
    Serial entrepreneur.
    Head of Research
    Software architect
    (Ecole Normale Supérieure Lyon, Télécom ParisTech).
    Ex research/engineering intern at Google Corp., ENS Cachan and INRIA.
  • Eddy CARON
    Scientific Advisor*
    PhD. MCF. Associate Professor at LIP (Parallel Computing Laboratory) / ENS Lyon.
    * in accordance with the LEXISTEMS - ENS Lyon partnership.

They support us

LEXISTEMS APIs: monetize your data today!

Your data is your capital

When your customers, your teams, your digital processes

access and process your data by MEANING on any device...

you monetize it to the fullest.