MEET CLOVER AI

Leader in symbolic, and deep learning language processing

We specialize in high granularity named-entity detection, text-based routing based on categorization, and text flow processing. We offer fast, custom solutions for over 40 languages, making us your go-to partner for multilingual language processing needs.

WHAT WE DO

Our Story

Building the world's most comprehensive natural language processing company

Clover.AI was started to bridge the gap between Symbolic Natural Language Processing, which looks at language as something discrete and indeed symbolic, and the emerging Deep Learning solutions, which look at language as something more organic. We achieved a technology breakthrough related to parsing technology when one of our co-founder, Emmanuel Roche, filed the first of a series of patents in 2019.

At Clover.AI, we have continuously put good science first, an approach which puts the nature of language at the core of our inquiries. However, we are also very pragmatic in bringing what technology works best at a given point for a given need.

Learn more
WHAT WE DO

The Clover Programming Language

The CLOVER programming language is the result of decades of research in Language Processing and Finite-State Processing. It is designed for scalability (1 million statements applied 500,000 words/s on a single core of a single CPU), expressive, learnable and scalable. Learn more <LINK to the CLOVER programming language page.

PORTFOLIO

Our Projects

See some of the projects that we are working on.

Natural Language Compiler

A natural language compiler is the process of translating a natural language input into a formal language. This formal statement could be a SQL query, a JSON object, or an API call. This complex problem is best looked at with a combination of formal descriptions for which we use the CLOVER programming language and generative LLMs.

Hybridization

It is possible to reduce the size of LLM, and hence its cost, by one to two orders of magnitude (depending of the type of LLM) by injecting high quality pre-analysis to training and runtime input. This is a process we call hybridization. It leverages the incredible predictive power of LLMs with the ability to interpret part of the input with some symbolic certainty.

Identity and Logic Extraction

Traditional NLP tasks, such as Named Entity Recognition (NER), focus on the extraction of sub-strings, letting the mapping of those substrings to actual identifiable entities to other processes. We believe these two steps need to be combined to become part of the same feedback loop. This leads to actionable output, including actual identifiable persons, objects, and predicate statements on those identifiable entities. Such actions include API calls.

LET’S CHAT

Check collaboration opportunities with Clover.AI

Fill contact form and we’ll reach out to you!

Contact us