Intelligo
Intelligo develops Italian-language natural language processing technology built on a proprietary lexicon of 4.5 million inflected forms. Its italica-X engine powers italica, a grammatical analysis app for learners, and ADA, an on-premises document anonymization solution for public administration, healthcare, and legal publishing that processes documents in under half a second each.
- Enterprise Software
- Education Technology
- Artificial Intelligence
- Government Technology
- Software Only
- Applications
Funding
Founders
Founder details are not available yet.
Product
Problem
Organizations and individuals working with Italian-language texts lack specialized NLP tools that accurately handle the language's grammatical complexity and linguistic nuances. Generic multilingual solutions often fail to deliver precise text classification, entity extraction, and grammatical analysis for Italian, limiting automation and efficiency in document-heavy workflows.
Solution
intelligo provides a suite of NLP solutions built around italica-X, a proprietary engine that uses custom algorithms and a vocabulary of 4.5 million inflected forms generated from 115,924 lemmas to perform text analysis and classification specifically for the Italian language. The engine powers italica, a mobile application for grammatical analysis that identifies parts of speech with an interface inspired by instant messaging systems, and ADA Suite, an on-premises document management solution for public administration, healthcare, and justice that automatically classifies documents, extracts 21 classes of entities, and supports anonymization. These tools enable organizations to automate key processes, improve operational efficiency, and enhance data protection while working with Italian-language content, with all processing performed locally and no outbound connections required.
Target Audience
Primary customers include public administration organizations, healthcare and justice sectors needing automated document classification and anonymization, as well as legal publishers, databases, and newsrooms that publish rulings and documents containing personal data. The italica app serves learners and teachers of Italian seeking grammatical analysis tools.
Features
- Proprietary NLP engine with custom Italian vocabulary and algorithms for text analysis and classification, processing a sentence in approximately 2 milliseconds
- POS-tagging and tokenization for accurate grammatical processing of Italian text, disambiguating words based on context (e.g., "la porta è chiusa" vs. "porta la borsa")
- Named entity recognition (NER) covering 21 entity classes including persons, minors, addresses, identity documents, personal codes, health data, judicial data, and economic information
- Validated code detection for tax codes (including omocodici), IBANs, number plates, postcodes, ID cards, IP and MAC addresses, verified against formal format rules
- Deterministic, auditable processing with explicit rules that produce consistent results across entire archives, with multi-tenant management, user roles, case files, logs, and sharing capabilities
- italica mobile app available on web, iOS, and Android with an interface available in seven languages for learners and teachers
- ADA anonymization engine that processes documents on-premises at 0.46 seconds per document, with separate layers for uploaded, tokenized, annotated, and anonymized stages
- On-premises appliance model available as physical server or virtual machine, requiring only CPU (no GPU), Linux-based, with no outbound network connections
- Sentiment analysis identifying positive, neutral, or negative polarity, plus linguistic register detection (formal, bureaucratic, colloquial)