Iceberg A.I. Platform

Dynamic Ontology

Iceberg's graph-oriented data representation can fit any data model from document databases to analytic profiles, classification taxonomies or temporal events

Easily evolve & refine your data model as requirements change

Easy data Ingestion

Import/Export structured data from XML, CSV or RDF files or connect to current Databases using the built-in connectors

Import data from Public Sources

Create crawl jobs and parsers to efficiently import data from public sources

Import data from vLex

Re-use and extend vLex global data for your organization's internal projects (subject to content license)

Explore & Search your Data

Explore, search and visualize your data in real-time

Workspace-based collaboration

Workspaces provide zero-cost private copies of data so that your editors and data-scientists can experiment with data transformations without impacting your production users

When changes are ready, a data merge is one-click away

IceNet Classification & Search Ranking Algorithms

IceNet is Iceberg’s own classification and search ranking algorithm designed to benefit from Iceberg’s graph-oriented data-representation and the past behavior of similar users

IceNet content-based recommendations

IceNet also provides content-based recommendations that enable your users to discover content that's relevant to their research

Enrich your data with Rule-based automations & Mass Updates

Rule-based automations and Mass Updates allow domain experts to turn their knowledge into rules and get instant results

Scale-up human data gathering with Workflows

Workflows provide task-oriented interfaces that optimize human data enrichment tasks

Distribute tasks to internal or external teams, review outputs and track progress

Enrich your data with vCite citator

Apply vLex's proprietary vCite algorithms to detect citations to legal documents in 20+ countries

Track engagement metrics

Automatically collect and aggregate user engagement data and use it to feed your machine learning algorithms

Probabilistic data model

Every fact in Iceberg is assigned a Quality Score that describes your editorial judgement of the data quality

Quality Scores can naturally describe the uncertainty associated to ML outputs and enable editors to override the output of automations if necessary

Iceberg Text Engineering

Iceberg Text Engineering provides built-in integration with the General Architecture for Text Engineering (GATE) framework to enable hand-crafted data extraction pipelines from text (vCite, metadata extraction, document segmentation)

This can be used in combination with ML

Plug-and-play API integrations with ML providers

API integrations with best machine-learning-as-a-service providers

Build Applications consuming your Cloud Data Set

Create Apps connecting to Iceberg GraphQL APIs

Professional Services upon request