AzureTextAnalyticsConnector

Connects to Azure Text Analytics Service for natural language processing on text.

Typical Uses

Detecting entities, phrases, language or sentiment.

How does it work?

The AzureTextAnalyticsConnector uses your Azure Cognitive Services account credentials to access the natural language processing service.

Text is submitted to the service, and one or more features are output with attributes added according to the requested Detection Type.

Available services are:

Detection Type	Analysis
Entities	Detects linked or categorized entities.
Key Phrases	Extracts key phrases.
Language	Detects the dominant language.
Sentiment	Detects text sentiment.

See Language support for Language features for language availability.

Optional Input Port

This transformer has two modes, depending on whether a connector is attached to the Input port or not:

Input-driven: When input features are connected, the transformer runs once for each feature it receives in the Input port.
Run Once: When no input features are connected, the transformer runs one time.

When the Input port is in use, the Initiator output port is also enabled.

Usage Notes

For better performance, requests to the Azure Text Analytics service are made in parallel, and are returned as soon as they complete. Consequently, detection results will not be returned in the same order as their associated requests.

Configuration

Input Ports

Output Ports

Output

Features with added attributes, as specified in parameters and according to Detection Type.

Detection Type	Output - Input-Driven	Output - Run Once
Entities	Input feature(s), one copy for each entity identified, with details about the entity.	New feature(s), one for each entity identified, with details about the entity .
Key Phrases	Input feature with identified key phrases in a list attribute.	New feature with identified key phrases in a list attribute.
Language	Input feature(s), one copy for each language identified, with details about the language.	New feature(s), one copy for each language identified, with details about the language.
Sentiment	Input feature with sentiment and confidence details.	New feature with sentiment and confidence details.

Parameters

Authentication

To use the AzureTextAnalyticsConnector or the AzureAIVisionConnector you will need a Cognitive Services Account, then generate an endpoint and key to authenticate.

Credential Source

Select the type of credentials to use:

Web Connection (Recommended): Use an Azure Cognitive Services web connection.
Embedded: Embed an endpoint and secret key as parameters in the transformer.

Account

When Credential Source is Web Connection, select or create a Web Connection connecting to an Azure Cognitive ServicesWeb Service.

See Using Web Connections.

Embedded Credentials

When Credential Source is Embedded:

The required endpoint URL and access keys can be found in the Microsoft Azure Portal under Resource Management > Keys and Endpoint, after creating or selecting the appropriate resource based on the Detection Type:

Endpoint	Provide an endpoint URL.
Key	Provide an access key.

Request

Text

Provide the text to submit for analysis.

Detection Type

Select the type of detection to perform:

Entities
Key Phrases
Language
Sentiment

Entity Detection Type

When Detection Type is Entities, select a type:

Categorized Entities	Identifies entities in text by classifying them into predefined types such as Person or Location.
Linked Entities	Identifies entities in text by linking to entries in external knowledge bases such as Wikipedia and Bing.

Detection Type > Entities

Detect Entities Options

Language

Select or provide the language of the Text.

If providing a value, use the language code, as in en for English, or Unknown [unk] for automatic language detection.

See Language support for Language features.

Added Attributes

Output features will receive these attributes:

Categorized Entities

_category	The category of the entity (for example, Person).
_subcategory	The subcategory of the entity.
_entity_text	The text snippet from the analyzed text (for example, if the input is John is an artist, and John is identified as a Person entity, then entity_text would be John.)
_confidence_score	The confidence score (between 0 and 1) of the extracted text.
_text	The text analyzed.

Categorized Entities

_name	The standardized, formal name of the entity from the data source.
_language	The 2-letter ISO 639-1 language code for the language used in the data source (for example, en for English).
_url	The URL to the entity from the data source.
_data_source	The data source used to extract information about the entity (for example, Wikipedia).
_data_source_entity_id	The unique identifier of the entity from the data source.
_bing_entity_search_api_id	The Bing Entity Search unique identifier of the entity from the data source.
_text	The text analyzed.

Detection Type > Key Phrases

Detect Key Phrases Options

Language

Select or provide the language of the Text.

If providing a value, use the language code, as in en for English, or Unknown [unk] for automatic language detection.

See Language support for Language features.

Added Attributes

Output features will receive these attributes:

_key_phrases{}	The important words/phrases in the text. Outputs as a list attribute.
_text	The text analyzed.

Detection Type > Language

Detect Language Options

Language detection has no parameters to configure.

Added Attributes

Output features will receive these attributes:

_language_code	The language code guessed for the text (for example, en).
_language_name	The name of the language (for example, English).
_confidence	The probability (between 0 and 1) that a given prediction is correct.
_text	The text analyzed.

Detection Type > Sentiment

Detect Sentiment Options

Language

Select or provide the language of the Text.

If providing a value, use the language code, as in en for English, or Unknown [unk] for automatic language detection.

See Language support for Language features.

Added Attributes

Output features will receive these attributes:

_sentiment	The sentiment for the text. Possible values are: POSITIVE, NEGATIVE, NEUTRAL
_positive_confidence_score	The confidence score (between 0 and 1) for the positive sentiment.
_neutral_confidence_score	The confidence score (between 0 and 1) for the neutral sentiment.
_negative_confidence_score	The confidence score (between 0 and 1) for the negative sentiment.
_text	The text analyzed.

Editing Transformer Parameters

Transformer parameters can be set by directly entering values, using expressions, or referencing other elements in the workspace such as attribute values or user parameters. Various editors and context menus are available to assist. To see what is available, click beside the applicable parameter.

How to Set Parameter Values

Defining Values

There are several ways to define a value for use in a Transformer. The simplest is to simply type in a value or string, which can include functions of various types such as attribute references, math and string functions, and workspace parameters.

Using the Text Editor

The Text Editor provides a convenient way to construct text strings (including regular expressions) from various data sources, such as attributes, parameters, and constants, where the result is used directly inside a parameter.

Text Editor

Using the Arithmetic Editor

The Arithmetic Editor provides a convenient way to construct math expressions from various data sources, such as attributes, parameters, and feature functions, where the result is used directly inside a parameter.

Arithmetic Editor

Conditional Values

Set values depending on one or more test conditions that either pass or fail.

Parameter Condition Definition Dialog

Content

Expressions and strings can include a number of functions, characters, parameters, and more.

When setting values - whether entered directly in a parameter or constructed using one of the editors - strings and expressions containing String, Math, Date/Time or FME Feature Functions will have those functions evaluated. Therefore, the names of these functions (in the form @<function_name>) should not be used as literal string values.

Content Types

String Functions	These functions manipulate and format strings.
Special Characters	A set of control characters is available in the Text Editor.
Math Functions	Math functions are available in both editors.
Date/Time Functions	Date and time functions are available in the Text Editor.
Math Operators	These operators are available in the Arithmetic Editor.
FME Feature Functions	These return primarily feature-specific values.
FME Parameters	FME and workspace-specific parameters may be used.
Creating and Modifying User Parameters	Create your own editable parameters.

Dialog Options - Tables

Table Tools

Transformers with table-style parameters have additional tools for populating and manipulating values.

Row Reordering

Enabled once you have clicked on a row item. Choices include:

Add a row
Remove a row
Move current row up one
Move current row down one
Move current row to top
Move current row to bottom

Cut, Copy, and Paste

Enabled once you have clicked on a row item. Choices include:

Cut a row - delete and copy to clipboard
Copy a row to the clipboard
Paste a row from the clipboard

Cut, copy, and paste may be used within a transformer, or between transformers.

Filter

Start typing a string, and the matrix will only display rows matching those characters. Searches all columns. This only affects the display of attributes within the transformer - it does not alter which attributes are output.

Import

Import populates the table with a set of new attributes read from a dataset. Specific application varies between transformers.

Reset/Refresh

Generally resets the table to its initial state, and may provide additional options to remove invalid entries. Behavior varies between transformers.

Note: Not all tools are available in all transformers.

For more information, see Transformer Parameter Menu Options.

Reference

Processing Behavior	Feature-Based
Feature Holding	No
Dependencies	Azure Cognitive Services Account
Aliases
History	Released FME 2019.2

FME Online Resources

The FME Community and Support Center Knowledge Base have a wealth of information, including active forums with 35,000+ members and thousands of articles.

Search for all results about the AzureTextAnalyticsConnector on the FME Community.

Examples may contain information licensed under the Open Government Licence – Vancouver, Open Government Licence - British Columbia, and/or Open Government Licence – Canada.