MonkeyLearn

MonkeyLearn icon

MonkeyLearn is a text analysis platform with machine learning that automates business workflows and saves manual data processing time.

Actions

Action

Configuration fields

Data type

Required?

Extract keywords from text - Extract keywords from a text list

Text list - A list of text, separated by semicolons, to extract the keywords from

Example: Juan lives in Mexico; Jane lives in Canada

String

Checkmark icon, required field

Whitelist - Enter a list of preferred keywords to return instead of the default representation

Example: Pricing

String

 

Blacklist - Enter a list of unwanted keywords to discard

Example: Spam

String

 

Maximum keywords - Enter the maximum number of keywords to extract. The default is 10.

Example: 5

String

 

Lowercase - Indicate whether to format the specified text as lowercase. The default is false.

Choice

 

Use IDF - Indicate whether to use a language model for computing the Inverse Document Frequency. The default is true.

Choice

 

Keyword representation - Select how to obtain the canonical representation of a keyword

Choice

 

Keyword transformation - Select how words are transformed into keyword groups

Choice

 

Classify text - Specify a model for classifying text

Classifier - Select the classifier to use

Choice

Checkmark icon, required field

Text list - Enter a comma-separated list of text strings to extract classifying keywords from

Example: Juan lives in Mexico, Jane lives in Canada

String

Checkmark icon, required field

Extract company or organization (English) from text - Extract a company or organization from text in the English language

Text list - Enter a list of text, separated by semicolons, to extract the company or organization names from

Example: ChapStick; Kleenex

String

Checkmark icon, required field

Extract text from HTML - Extract text from an HTML list

HTML list - Enter a list of text formatted as HTML, separated by semicolons, to extract text from

For example: <html><body><p>Hello World</p></body></html>; <html><body><p>Goodnight World</p></body></html>

String

Checkmark icon, required field

Extract email address from text - Extract email addresses from a text list

Text list - Enter a text list, separated by semicolons, to extract email addresses from

Example: Hello from jessedoe@example.com; Goodbye from genedoe@example.com

String

Checkmark icon, required field

Extract location from text - Extract a location from a text list

Text list - Enter a text list, separated by semicolons, to extract the locations from

Example: Juan lives in Mexico; Jane lives in Canada

String

Checkmark icon, required field

Extract person from text - Extract a person from a text list

Text list - Enter a text list, separated by semicolons, to extract the people from

Example: Juan Doe lives in Mexico; Jane Doe lives in Canada

String

Checkmark icon, required field

Extract phone number from text (English) - Extract North American phone numbers from English text and return them with unified formatting

Text list - Enter a text list, separated by semicolons, to extract the phone numbers from

Example: For assistance, call (800)555-0100; For information, call (800)555-0199

String

Checkmark icon, required field

Extract entity from document - Extract an entity (person, organization, or location) from a document

File URL - Enter the URL of the file to extract the entities from

Warning  Extracts plain text from binary documents such as .doc, .docx, .pdf, and .odt

URL

Checkmark icon, required field