Extract entities from text

Identify people, organizations, brands, places and other named entities mentioned in the text.

Top Benefits

  • High precision: context-dependent disambiguation enables to identify exactly what entity the text is referring to.
  • Extensive coverage: identify entities included in an extensive ontology and increase recall with custom dictionaries.
  • Enrich your output through complementary semantic information, Wikipedia pages or Linked Data resources related to it.
  • Able to analyze texts in multiple languages: English, Spanish, French, etc.
  • Extract the most meaningful topics appearing in the text, providing its semantic footprint.

Tasks

  • Extract named entities from documents, web pages, social content and contact center interactions.
  • Adapt the extraction to your domain to increase accuracy, using customized dictionaries.
  • Use the returned semantic information to search, relate and recommend content.
  • Obtain the full analysis of the entities detection.

In many situations it is useful to have the semantic footprint of a document or content: to find it more easily, to relate it to others with whom it shares meaning, to recommend similar content, etc.

The extraction of named entities provides a simple and actionable version of this footprint, by unambiguously identifying the people, organizations, brands or places that appear in the text.

This bot receives a text and uses the MeaningCloud Topics Extraction API to return a list with the named entities mentioned in it, unambiguously identified taking into account context and optionally enriched with semantic information about them.

The bot will output the entities, if configured their semantic type and relevance and a JSON with the complete analysis returned by the API.

The bot is useful in situations where there is a need to semantically characterize large amounts of text, for example, the understanding of emails and interactions in the contact center, the monitoring of the brand in social media, the contextualization of web content, or the extraction of data of contracts, insurance claims or other complex documents.

The API relies on MeaningCloud’s built-in ontology to identify hundreds of thousands of predefined named entities in several languages. If the user wants to adapt the operation of the bot to his scenario, so that he can identify his specific people, organizations or brands, it suffices to incorporate these into a user dictionary to extend the ontology, so that the bot will be able to identify them from that moment (thus increasing the precision and recall of the process).

Get Bot

Free

Bot Security Program
Level 1
Applications
Business Process
Category
Downloads
23
Vendor
Automation Type
Bot
Last Updated
January 22, 2020
First Published
January 22, 2020
Enterprise Version
11.x
ReadMe
ReadMe
Support

See the Bot in Action

Entities extraction TaskBot
Example response of the analysis available
JSON response with complete analysis
PREV NEXT
Entities extraction TaskBot
Example response of the analysis available
JSON response with complete analysis

Setup Process

Install

Download the Bot and follow the instructions to install it in your AAE Control Room.

Configure

Open the Bot to configure your username and other settings the Bot will need (see the Installation Guide or ReadMe for details.)

Run

That's it - now the Bot is ready to get going!

Requirements and Inputs

  • Access to MeaningCloud Topics Extraction 2.0 (MeaningCloud account)
  • Input a UTF-8 text