Anzo Unstructured

Anzo Unstructured

Capitalize Upon Unstructured Data for Advanced Analytics and Smart Data Management

Anzo® Unstructured is an add-on module to Anzo Enterprise that delivers a wide range of out of the box crawling, annotating, and processing capabilities.to analyze, link and unify a wide variety of internal and external unstructured data sources, for advanced analytics and smart data management. With Anzo, unstructured data can be easily blended with structured data from internal and external sources to allow users to conduct a wide variety of analytics and data management on the integrated data.

See the charts below to learn more about what capabilities are delivered either right out of the box, or by selecting additional plugins from our 3rd party technology partners.

 

ANZO UNSTRUCTURED HIGHLIGHTS

Cambridge Semantics offers a robust approach to unlocking the hidden wealth of information contained within unstructured data, so that organizations process unstructured data with the same quality and reproducibility as structured data to provide reliable analytics and data management.

Anzo Unstructured Highlights

Base

Premium Plugins

Advanced Text Analytics

 

 

Autotags Entities, Relationships, Concepts, Categories and Sentiment

 

 

Autocombines Structured and Unstructured Information

 

 

Conceptual Mapping of Enterprise Documents

 

 

Multilingual Support

 

 

Granular Access Controls

 

 

Integrated Curation Support

 

 

Parallelized Document Analysis Pipelining

 

 

Seamless Integration with Best-of-Breed Applications

 

 

UNSTRUCTURED DATA PROCESSING FRAMEWORK

With Anzo Unstructured we offer a full stack of plug and play, best of breed text analytics and NLP capabilities that are easily updated, maintained and deployed to address multiple use cases. Powered by the Anzo Smart Data Platform, Anzo Unstructured scales with your data volume while providing real time analytic capabilities.

Anzo Unstructured Framework

Base

Premium Plugins

Support of Pushed and Pulled Documents, Pages, and Posts

 

 

Document Rich Text, Thumbnail and Metadata Extraction

 

 

Semantic Correspondence Linker

 

 

Entity Linking and Disambiguation

 

 

Document Canonicalization

 

 

Annotation Filtering

 

 

Generalized Annotation Web Service

 

 

Annotation Harmonization

 

 

Annotation Restructuring

 

 

Annotation Combination

 

 

Enterprise-Specific Concept-Based Relationships

 

 

Semantic Query Enrichment

 

 

Relationship Compounding

 

 

Learns Schema from Data

 

 

Automatic Ontology Mapping

 

 

Automatic Schema Growth

 

 

Visualize and Navigate Annotations in Context

 

 

Document Formatting

 

 

Assisted Reading Support

 

 

Curation Workflow Support

 

 

Accuracy Reporting Support

 

 

Flexible NLP Output Routing

 

 

Powerful SDK and API's

 

 

SEARCH

Traditional search is no longer good enough to help organizations leverage their data for optimal business value. Rather than just finding information, wouldn’t it be better if search delivered meaning and context to your data, so you can understand what it means? Cambridge Semantics delivers search capabilities that create conceptual links between structured and unstructured data to help deliver real value for your content analytics needs.

Search

Base

Premium Plugins

Full Semantic Search

 

 

Concept-Based Full Text Search

 

 

Search Documents by Implicit Entity or Relationship Attributes

 

 

Mix Structured and Unstructured Filters

 

 

Supports both Federated and Centralized Search

 

 

Similar Documents Search

 

 

External Search Index Federation

 

 

Cognitive Computing Search Interface

 

 

Natural Language Query Understanding

 

 

Automated Question Answering

 

 

Optional Support for GSA Integration and Enrichment

 

 

AUTOMATED DOCUMENT ANNOTATION

The proper tagging, categorization and indexing of data is a crucial element to leveraging unstructured data to uncover data patterns and relationships that can be conceptually linked and mapped to your business terminology, ontology and data models. Cambridge Semantics offers a best of breed capability for combining annotations of different types to deliver unparalleled value for your data.

Automated Document Annotation

Base

Premium Plugins

Taxonomy and Thesauri Annotator

 

 

Knowledgebase Annotator

 

 

Common Entity Extractor

 

 

Custom Relationship Annotator

 

 

Significant Phrase Annotator

 

 

Fuzzy Rule Network Annotator

 

 

Pattern and Regular Expression Annotator

 

 

Autotaggers

 

 

Document Classifier

 

 

Document Clusterer

 

 

Document Section Annotator

 

 

JAPE Annotator

 

 

Hierarchical Web Scraper Annotator

 

 

External Data Enricher

 

 

UIMA and GATE Annotation Framework Acceleration 

 

 

Lexalytics Salience

 

 

Basis Technology Rosette Integration

 

 

ChemAxon Integration

 

 

Linguamatics I2E Integration

 

 

SciBite Termite Integration

 

 

ExpertSystem Cogito Integration

 

 

CliniThink Clix Integration

 

 

AlchemyAPI Integration

 

 

Semantria Integration

 

 

NIH MetaMap Integration

 

 

OpenCalais Integration

 

 

OpenAmplify Integration

 

 

Additional Annotators via SDK

 

 

DOCUMENT INTAKE

Anzo Unstructured easily automates the intake of internal and external documents, and web resources in numerous file formats, from a large and diverse data pipeline.

Document Intake

Base

Premium Plugins

Web Crawler

 

 

Filesystem Crawler

 

 

RSS Feed Crawler

 

 

News Crawler

 

 

DataSift Crawler and Listener

 

 

Twitter Sampling Listener

 

 

Enterprise CMS Crawlers

 

 

IMAP Server Crawler

 

 

Windows Share Crawler

 

 

RDF Dataset Crawler

 

 

Enterprise DAMS Crawler

 

 

PubGet Journal Service Integration 

 

 

Google Search Appliance Integration 

 

 

Document Listener Web Service

 

 

Additional Crawlers via SDK

 

 

AUTOMATED DOCUMENT TRANSFORMATION

Anzo Unstructured automates the ability to mine, convert and repurpose text from multiple document types. No need to worry about multiple languages, data duplication, etc.…..we’ve got you covered.

Automated Document Transformation

Base

Premium Plugins

Document Preview Generators

 

 

Thumbnail Generators

 

 

Google Translate Integration

 

 

Near Duplicate Document Detector

 

 

Google Language Identifier

 

 

Basis Technology Language Identifier

 

 

Standard Language Identifier

 

 

Klout Integration

 

 

Article Content Recognizer

 

 

Diffbot Content Recognizer Integration

 

 

Office Format Converters

 

 

PDF Format Converters

 

 

Web Format Converters

 

 

XML Format Converters

 

 

Additional Transformers via SDK

 

 

UNSTRUCTURED OUTPUT METHODS

A key promise of working with unstructured data, is getting the right information, to the right people at the right time. Anzo Unstructured data is built for bi-directional input and output, delivered in a fast and flexible manner that integrates with numerous reporting tools, dashboards, and a variety of content distribution methods.

Unstructured Output Methods

Base

Premium Plugins

Anzo on the Web Dashboards for Mashups and Semantic Search

 

 

Assisted Reading View

 

 

Dashboards for structured data facets

 

 

Semantic Document Overlays

 

 

Web Services, Database Feeds, CSV's

 

 

Semantic Document Overlays