SOLUTIONS

Start your journey to derive value from documents by checking out use-cases

Challenges: Monitor and evaluate company and market information.

Data sources: Website (news, publication), social network (Twitter…) combined with business vocabulary (company, product…).

Impacts: Automation of processes, automatic support for recurrent tasks with even large volumes of document, multilingual scope.

Automated pipeline:

Challenges: Track and evaluate technology trends.

Data sources: Website (news, publication), social network and business vocabulary (technology…).

Impacts: Automation of processes, multilingual scope.

Automated pipeline:

Challenges:  Detect, assess and monitor adverse reactions and associated conditions of pharmaceutical products.

Data sources: Websites (reviews, publications, research, trials, drug approvals, patient forums), journals combined with business vocabulary (drug names, molecules, symptoms…).

Impacts: Automation of processes, Respond to new customer requests easily, Multilingual deployment, Extend volume of content monitored.

Automated pipeline:

Challenges: Detect numerical data figures and other information in contracts: Termination? Effective date? Obligations? Fees?

Data sources: Documents (contracts, statutes…) in research, due diligence or forensic processes.

Impacts: Allow exhaustive analysis, Extend manageable document volumes, New questions? Just reanalyse (prohibitive when done manually).

Automated Pipeline:

Challenges: Identify customer irritants and detect their degree of dissatisfaction.

Data sources: Customer verbatim, speech-to-text recordings.

Impacts: Automation of processes, multilingual scope.

Automated pipeline:

Challenges: Make content more findable, create new products or services, improve editorial processes.

Data sources: Editorial content, newspaper & broadcast (speech to text) and business vocabulary (thesaurus, list of people, organization…).

Impacts: Automation of processes, easy to integrate and ready for large scale deployment.

Automated pipeline:


PLATFORM

A fast, accurate & fun AI-Powered Natural Language Processing Platform for everyone, to build and run AI Assistants at scale

Text annotation & Dataset creation

Upload your documents, annotate and create dataset quickly with our unique suggestion engine.
Achieve high quality dataset using our powerful search, filtering and navigation features.
Text in any format, including audio.

Machine Learning experimentation

Evaluate different state-of-the-art Machine Learning and Deep Learning libraries.
Train your models on dataset, tune and select the most appropriate one.
No coding required.

Annotation pipeline & Knowledge Base

Build your annotation pipeline with your custom models and possibly Knowledge Base especially when it comes to ensure normalization, disambiguation & linking of information.
Any Knowledge Base, including Wikidata, always up-to-date.
Your AI assistant is ready.

Deployment & Monitoring

Deploy your annotation pipeline into your workflow, set up feedback loops to improve models performance and continue feeding your Knowledge Base.
Your AI assistant is up & running.


REFERENCES

Powerful AI and NLP software is vital to accomplish knowledge discovery in an efficient and fast manner for our scientists.

Dr. Karlheinz Spenny – Head of the Scientific Information Center

We just released our new version heavily driven by the Kairntech NLP platform for the semantic aspects with a pretty massive impact.

Hugo Le Houarner – CEO

We are delighted to embark the Kairntech team in phase 2 of the DGA’s Artemis project to boost our capacity for innovation in AI & NLP.

Eric Rous – Senior Manager

To make the most of our content, it is essential to build high-quality AI models simply and quickly and to combine them with knowledge base.

Gaëlle Recource – Head of Content

The handling of the platform was very quick. We use it to accelerate dataset production with significant time savings.

Benjamin Carpano – CEO

Very useful platform and intuitive. The suggestion engine is clearly a monstrous time-saver. It even makes you want to annotate more!

Cédric Lagnier – CTO

We have integrated the Kairntech platform to boost our productivity while being able to offer to our customers the ability to analyse an ever growing number of documents.

Hugo Simon-Chautemps – COO

Our Technology and Innovation Intelligence services are based on semantic language models where Kairntech’s solutions accelerates the building process in a significant way.

Tim Schloen – Founder

With Kairntech, we produced verbatim analysis prototypes in record time. Their AI/NLP platform is essential for our new Customer Experience (CX) platform.

Arnold Haine – CTO

Automate document analysis?

We made it fast, accurate and fun for everyone.

Quickly build and run AI assistants that will power your documents processes, saving you time and effort. Anybody can do it. No programming skills required.

Free TrialVideo

NEWS

Finding new needles in content haystacks: Vocabulary maintenance with AI!

Posted on
Introduction Structured vocabularies (thesauri, taxonomies…) play an important role in many applications where complex, large and volatile information needs to be organized and made accessible. A fine example is the famous MeSH thesaurus that facilitates search and access on Medical topics. Enriching scientific content with MeSH terms allows to guarantee that content on a specific … Continue reading Finding new needles in content haystacks: Vocabulary maintenance with AI!

Fraunhofer SCAI and Kairntech succeed with AI-powered Relation Extraction for Indication-Specific Knowledge Graph assembly

Posted on
A Knowledge Graph for psychiatric disorders SANKT AUGUSTIN.   The Fraunhofer Institute for Algorithms and Scientific Computing SCAI and the software company Kairntech (Grenoble) have created a knowledge graph for psychiatric disorders, especially psychoses. Knowledge graphs allow unstructured texts to be represented in a structured, comparable format. They visualize cause-and-effect models to help medical professionals … Continue reading Fraunhofer SCAI and Kairntech succeed with AI-powered Relation Extraction for Indication-Specific Knowledge Graph assembly

COMPANY

For 20 years, we have been building Text Mining solutions in industry and public organizations contexts.
We created Kairntech in December 2018 to make NLP easy-to-use by domain experts without IT skills.
We leverage NLP with advanced methods including Machine Learning, Deep Learning &
Knowledge Base technologies to extract insights from your documents.

We are a team of seasoned and forward thinking people.

Gilles Pouzenc

Chief Executive Officer

Vincent Nibart

Chief Operation Officer

Stefan Geissler

Chief Scientific Officer

Want to join or send us a message?