Using InterSystems Natural Language Processing (NLP)

• Text Analytics (Natural Language Processing)
• Try it
• Read all about it
• Explore more
• Conceptual Overview
• A Simple Use Case
• What is NLP?
• Logical Text Units Identified by NLP
• Smart Indexing
• Smart Matching
• NLP Implementation
• A Note on Program Examples
• A Note on %Persistent Object Methods
• A Note on %iKnow and %SYSTEM.iKnow
• Space Requirements and NLP Globals
• Input Data
• Output Structures
• Constants
• Error Codes
• Domain Architect
• Accessing Architect
• Creating a Domain
• Model Elements
• Save, Compile, and Build
• Domain Explorer
• Introduction
• Domain Explorer Settings
• Listing All Concepts
• Analyzing a Specified Entity
• Limiting the Sources to Analyze
• Indexing Results
• Introduction
• Domain Data
• Manual input Data
• Indexed Sentences
• Concepts and CRCs
• REST Interface
• Swagger
• REST Operations
• Creating an NLP Environment Manually
• NLP Domains
• InterSystems NLP Configurations
• InterSystems NLP User Dictionary
• Loading Text Data Programmatically
• Loader
• Lister
• Listing and Loading Examples
• Updating the Domain Contents
• Loading a Virtual Source
• Copying and Re-indexing Loaded Source Data
• Performance Considerations when Loading Texts
• NLP Queries
• Types of Queries
• Queries Described in this Chapter
• Query Method Parameters
• Counting Sources and Sentences
• Counting Entities
• Listing Top Entities
• CRC Queries
• Listing Similar Entities
• Listing Related Entities
• Counting Paths
• Listing Similar Sources
• Summarizing a Source
• Querying a Subset of the Sources
• Semantic Attributes
• How Attributes Work: Marker Terms and Attribute Expansion
• Access Attribute Data
• Supported Attributes
• Negation
• Time, Duration, and Frequency
• Measurement
• Sentiment
• Certainty
• Generic Attributes
• Stemming
• Configuring Stemming
• Stem Retrieval Methods
• Using Stems
• Skiplists
• Creating a Skiplist
• Queries that Support Skiplists
• Filtering Sources
• Supported Filters
• Filtering by the ID of the Source
• Filtering a Random Selection of Sources
• Filtering by Number of Sentences
• Filtering by Entity Match
• Filtering by Indexing Date Metadata
• Filtering by User-defined Metadata
• Filtering by SQL Query
• Filter Modes
• Using GroupFilter to Combine Multiple Filters
• Text Categorization
• Text Categorization Implementation
• Establishing a Training Set and a Test Set
• Building a Text Classifier Programmatically
• Testing a Text Classifier
• Building a Text Classifier Using the UI
• Using a Text Classifier
• Dominance and Proximity
• Semantic Dominance
• Semantic Proximity
• Custom Metrics
• Implementing Custom Metrics
• Types and Targets
• Copying Metrics
• Smart Matching: Creating a Dictionary
• Introducing Dictionary Structure and Matching
• Creating a Dictionary
• Listing and Copying Dictionaries
• Extending Dictionary Constructs
• Smart Matching: Using a Dictionary
• How Dictionary Matching Works
• Matching A String
• Matching Sources
• Defining a Matching Profile
• User Interfaces
• How to Display NLP User Interfaces
• Abstract Portal
• Abstract Source Viewer
• Loading Wizard
• Domain Explorer
• Basic Portal
• Indexing Results
• Matching Results
• InterSystems IRIS Natural Language Processing (NLP) Tools
• NLP Shell Interface
• NLP Data Upgrade Utility
• iKnow Web Services
• Available Web Services
• Using an NLP Web Service
• Comparison of NLP Web Services with Primary NLP APIs
• See Also
• KPIs and Dashboards
• KPI Terminology
• Defining a KPI That Uses Text Analytics Query
• Available KPI Filters
• Overriding the KPI Properties
• Example
• Creating a Dashboard to Display the KPI
• Providing Access to Dashboards
• See Also
• Customizing NLP
• Custom Lister
• Custom Processor
• Custom Converter
• Language Identification
• Configuring Automatic Language Identification
• Using Automatic Language Identification
• Overriding Automatic Language Identification
• Language-Specific Issues
• Domain Parameters