Aiimi Insight Engine Disco
User GuidesAiimi
  • Introducing Aiimi Insight Engine
  • Architecture
    • Overview and Key Concepts
    • Hosting Options
    • Architecture and How It Works
      • Agent Servers
        • Security Agent
        • Source Agent
        • Content Agent
        • Enrichment Agent
        • Job Agent
        • OCR Agent
        • Migration Agent
        • Tika Agent
      • Repository
        • Data Node
        • Proxy Node
        • Kibana Node
      • Gateway and User Interface
      • Document and Data Sources
    • Deployment Options
      • Development Environments
      • Testing and QA Environments
      • Production Environments
      • Disaster Recovery Environments
    • Security
      • Source Systems
      • Firewalling
      • Agent Servers
        • Security Agent
        • Source Agent
        • Content Agent
        • Enrichment Agent
        • Job Agent
        • OCR Agent
        • Migration Agent
        • Tika Agent
      • Repository
      • Gateway (Web Server)
      • Tools & Utilities
  • Installation
    • Elasticsearch Installation (Windows)
    • Aiimi Insight Engine Installation (Windows)
    • Python REST Service Install and Configuration
      • Installation and Setup
        • Offline Huggingface Set-up
        • Configuration of Logging
        • Running as a Service (Windows)
        • Using SSL
        • Performance and Concurrency
        • Security
      • Communicating with the Python REST Service
      • Step Configuration
        • Classify
        • Entity Mapper
        • Huggingface NER
        • Language Detection
        • Phrases and Topics
        • Summary
        • Spacyner
    • HTML Cleaner Service
  • security
    • Users
      • User Authentication
      • Code of Conduct
      • App Access and Role-Based Access
    • Data & Documents
      • Document and Data Access Control Lists
      • Progressive Access and Privileged Access
        • Progressive Access
        • Privileged Access
      • Source Scope and Visibility within Apps
      • Classification
      • Advanced Security Controls - Security Classifications
      • Risk Ratings
      • Redaction and Anonymisation
      • Banned Words
      • Mark as Sensitive
      • Audit Controls
  • Control Hub
    • Configurations
      • Managing Configurations
        • Edit and Delete
        • Find a Configuration
        • Monitoring Stats
        • Stop a Configuration
        • Refreshing
      • Security Configurations
        • Configuring Security
        • Active Directory
        • Azure Active Directory
        • BuiltinSecurity
        • Security Sync
        • Security Agents
        • Security Scheduling
      • Source Configurations
        • General
        • Source
          • Azure Blob Storage
          • BBC Monitoring
          • Big Query Cataloguer
          • BIM360
          • CSV Data Loader
          • Confluence
          • Content Server
          • Data File Cataloguer
          • Document Store
          • Dropbox
          • Exchange 365
          • Filesystem
          • Google Bucket
          • JSON Data Loader
          • ODBC Data Loader
          • PowerBi Cataloguer
          • Reuters Connect
          • ShareFile
          • SharePoint
          • SharePoint Legacy
          • SQL Server Cataloguer
          • Websites
          • XML Data Loader
        • Crawl
        • Source Agents
        • Source Scheduling
        • Advanced
      • Enrichment Configurations
        • Creating a Pipeline
          • General
          • Steps
            • Tika Text Extraction
            • External Links
            • Delete
            • Copy
            • Text Cleaner
            • Data Rule Processor
            • Checksum
            • OcrRest
            • AccessMiner
            • CAD Extractor
            • Trie Entity Extractor
            • PCI Extractor
            • Email Extractor
            • Geotag
            • Google Vision Extractor
            • Google NLP Extractor
            • Metrics Calculation
            • Microsoft Vision Extractor
            • Entity Rule Processor
            • Anonymiser
            • Set Document Risk
            • Content Retrieval
            • REST
          • Filters
          • Agents
          • Schedule
          • Advanced
      • OCR Engine
      • Job Configurations
        • General
        • Job
          • AutomatedSearchJob
          • Command Job
          • ElasticJob
          • Extended Metrics Job
          • GoogleVaultSAR
          • Nightly Events Processor Job
          • Notifications Processor Job
          • Portal Sync Job
          • Purge Job
          • Text Content Merge Job
        • Output
        • Agents
        • Scheduling
      • Migration Configuration
        • General
        • Filter
        • Metadata Mappings
        • Agents
        • Scheduling
        • Advanced
      • Content Server
    • Credentials
      • Create a Credential
      • Find a Credential
      • Edit a Credential
      • Delete a Credential
    • Entities
      • Create a Group
      • Create an Entity
      • Managing Entities
      • Import or Export Entities
    • Models
      • Create a New Model
      • Find a Model
      • Enable or Disable a Model
    • Featured Links
    • Global Settings
      • General
        • Thumbnails
        • Windows Authentication
        • SAML2 Authentication
        • ADFS
        • Stackdriver
        • Document Recommendations
        • Searchable PDF Storage
        • Versioning
        • Results
        • Marking Useful Results
        • Folder Browsing
        • Cascading Search
        • Search Suggestions
        • Delve Settings
        • Collections
        • Miscellaneous
      • Application Access
      • Search Relevancy
        • Core Settings
        • Makers Algorithm
        • Filename Boost Layer
        • Minimum Matching Terms Filter
        • Field Boost
        • Modified Date Boosting
        • Hit Highlighting
        • Why My Search Matched
        • Data Search Strategy
      • Search Performance
        • Accurate Totals for Pagination
        • Source cards
        • Facets
      • Filtering
      • Presets
        • File Groups
        • Security Groups
      • Code of Conduct
      • Metrics
      • Viewer
      • SAR
        • Importing Data For A SAR
        • Getting SAR data from Google Vault
        • Redacting Information
        • SAR Access
      • Privacy Portal
        • Activate the Privacy Portal
        • Disclosure
        • Submit SARs From The Privacy Portal
        • Email Delivery Settings
          • Delivery Settings
          • Brand Settings
          • Customise Emails
        • SMS Delivery Settings
        • Requestor Message Limit
        • Attachment Configuration
        • Password Configuration
        • File Scanner Configurator
      • Visualisations
        • Related Result Connections Diagram
        • Event Timeline
        • Create and Modified Date Activity Chart
        • Relationship Map
      • Notifications
      • Map View
      • App
      • Theming
        • Details
        • Logo
        • Background Images
        • Colours
      • Related Results
      • OData API
      • Bulk Search
        • Managing a Bulk Search
    • User Settings
    • Stats
  • API Guides
    • Insight API Guide
      • Swagger Documentation
      • Trying Some Endpoints
      • Search Filter
      • Hits / Items
      • Inspecting REST Calls
    • Data Science API Guide
      • REST Interface
        • Login
        • Datasets
        • Fields
        • Field Statistics
        • Search
        • Scroll
        • Update
      • Python Wrapper
        • Login
        • Datasets
        • Fields
        • Field Statistics
        • Search
        • Query Builders
        • Scroll
        • Scroll Search
        • Update Single Document
        • Bulk Update
    • Creating a Native Enrichment Step
      • Creating an Enrichment Step
        • Creating the Core Classes
        • Extending our Enrichment Step
        • Adding a Configuration Template
        • Adding the Enrichment Step
        • Creating an Enrichment Pipeline
      • Other Tasks
        • Entities, Metadata and Data
        • Accessing the Repository
      • Example Code
      • Troubleshooting
    • Creating a Python Enrichment Step
      • Creating an Enrichment Step
        • Running the Example from Command Line
        • Running the Example
      • Creating Your Own Step
      • Adding or Changing Entities, Metadata
  • whitepapers and explainers
    • Methods for Text Summarization
      • Application
      • Technology Methods
      • Commercial Tools
      • Key Research Centres
      • Productionisation
      • Related Areas of Text Analytics
      • Conclusion
      • References
Powered by GitBook
On this page
  1. whitepapers and explainers

Methods for Text Summarization

Automatic summarization refers to the algorithmic shortening of a communication. The result should effectively convey the important points in a shorter form, be complete, readable and follow the vocabulary of the original. This allows a user to consume critical information as efficiently as possible. Summarization appears in virtually every form of consumable media, for example:

  • Abstracts of research papers

  • Synopses of books and films

  • Headlines of articles

  • Minutes of a meeting

  • Sound bites of politicians and correspondents for news media.

Text summarization is of particular interest because of its relative simplicity to approach computationally, compared to the large potential gain in productivity. For this reason, vendors such as Google have heavily invested in research in this area and now feature summaries that many of us use every day: answering a user’s query directly on the search page without the need to ever click through to a source.

Text summarization can be broadly categorized into two approaches:

  1. Extractive, wherein the key phrases are identified and presented verbatim, with no additional content generated by the algorithm.

  2. Abstractive, where the whole text is interpreted, and a summarized output is generated using language that may not have been present in the original.

Extractive techniques have the advantage of being far easier to implement due to their method of scoring and concatenating existing phrases rather than creating new ones. For this reason, more research is in this area and there are more available toolsets for extractive summarization. The drawback of this approach is mostly in the inconsistent fluency of the summary.

Abstractive techniques are more complex and generally require more adventurous algorithms and computing power. They are usually highly domain-specific, with little transferability to other types of text. However, for their intended domain, they can provide highly accurate and readable summaries.

This whitepaper will discuss the most popular approaches to automatic text summarization; their implementations, practicality and relative strengths and weaknesses. The topic of text summarization will be considered in its wider business and historical context, and an overview of the leading institutions in this field will be provided. An overview of the available commercial and open-source options will be provided, along with a summary of related fields in Natural Language Processing.

PreviousAdding or Changing Entities, MetadataNextApplication