Extract Named Entities

Description

Extracts named entities from plain text. You can set the type and language used to identify the named entity.

Named entities are real-world objects identified by their proper names. Named entities refer to a person, location, organization, product, or a moment in time for example.

The results that this command returns might vary according to the selected NLP provider. For more information, see Setting an NLP provider.

Script syntax

IBM RPA's proprietary script language has a syntax similar to other programming languages. The script syntax defines the command's syntax in the script file. You can work with this syntax in IBM RPA Studio's Script mode.

extractNamedEntities --entities(NaturalLanguageEntities) [--culture(String)] --text(String) (List<String>)=values (String)=first (DataTable)=valuesmapping (Boolean)=success

Input parameters

The following table displays the list of input parameters available in this command. In the table, you can see the parameter name when working in IBM RPA Studio's Script mode and its Designer mode equivalent label.

Output parameters

Example

Example 1: The following example uses the Legacy NLP provider to extract the names of famous authors and books from the text.

defVar --name entities --type String
defVar --name entitiesList --type List --innertype String
defVar --name result --type Boolean
defVar --name firstEntity --type String
defVar --name valueMappings --type DataTable
setVar --name "${entities}" --value "My favorite authors are Sir Arthur Conan Doyle, and Agatha Christie. I also like some books from Edgar Allan Poe, such as Eureka. But my favorite book of all time is Don Quixote, from Miguel de Cervantes."
setNlpProvider --provider "Legacy"
extractNamedEntities --entities "Person" --culture "en-US" --text "${entities}" entitiesList=values firstEntity=first valueMappings=valuesmapping result=success
logMessage --message "Named entities list: ${entitiesList}\r\nFirst entity found: ${firstEntity}\r\nMappings: ${valueMappings}\r\nResult: ${result}" --type "Info"
// Output:
// Named entities list: [Arthur Conan Doyle,Agatha Christie,Edgar Allan Poe,Don Quixote,Miguel de Cervantes]
// First entity found: Arthur Conan Doyle
// Mappings: 1, 28, 18, Arthur Conan Doyle, 4
// 2, 52, 15, Agatha Christie, 4
// 3, 97, 15, Edgar Allan Poe, 4
// 4, 166, 11, Don Quixote, 4
// 5, 184, 19, Miguel de Cervantes, 4

Example 2: The following example uses the IBM Watson NLP provider to extract names of locations and units of measurement from the text.

defVar --name entities --type String
defVar --name entitiesList --type List --innertype String
defVar --name result --type Boolean
defVar --name firstEntity --type String
defVar --name valueMappings --type DataTable
defVar --name farenheitValues --type List --innertype String
defVar --name farenheitFirstValue --type String
defVar --name farenheitMappings --type DataTable
setVar --name "${entities}" --value "Mike and Jenny went to New York last season. They said it was freezing cold there, but it couldn\'t be colder than Helsinki. Edward told me that Berlin was below 14 degrees Farenheit, and I couldn\'t believe him."
setNlpProvider --provider "Watson"
extractNamedEntities --entities "Place" --culture "en-US" --text "${entities}" entitiesList=values firstEntity=first valueMappings=valuesmapping result=success
extractNamedEntities --entities "Measure" --culture "en-US" --text "${entities}" farenheitValues=values farenheitFirstValue=first farenheitMappings=valuesmapping
logMessage --message "Named entities list: ${entitiesList}\r\nFirst entity found: ${firstEntity}\r\nMappings: ${valueMappings}\r\nResult: ${result}" --type "Info"

Limitations

Some entities are not supported in some languages by the Legacy provider. See the Legacy provider limitations below:

The following named entities are supported in en-US:

• Person

The following named entities are not supported in pt-BR and pt-PT:

• Event
• Abstract

Related links

• Answer Question
• Boolean Extract
• Classify Text
• Extract Address
• Extract CNPJ
• Extract CPF
• Extract Date
• Extract E-mail Address
• Extract Intent
• Extract Monetary Value
• Extract Numbers
• Extract Phone Number
• Extract Quantity
• Extract Time Span
• Parse Sentences
• Spell Checker
• Summarize Text
• Synonyms