Accesses the Amazon AI Comprehend Service for natural language processing on text.
Typical Uses
Submit text to the Amazon AWS Comprehend service to
- detect dominant language
- get sentiment information
- extract key phrases
- get entities
How does it work?
The ComprehendConnector uses your Amazon AWS account credentials (either via a previously defined FME web connection, or by setting up a new FME web connection right from the transformer) to access the natural language processing service.
It will submit text to the service, and return features with attributes about that text. Each input feature may result in several output features.
Usage Notes
- For better performance, requests to the Comprehend 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.
- All confidence scores are returned between 0 and 1. For more information about accuracy, see the Amazon Comprehend FAQs: https://aws.amazon.com/comprehend/faqs/
Configuration
Input Ports
Input
This transformer accepts any feature.
Output Ports
Output
Output will depend on the analysis chosen.
Language Detection
Detects the dominant language for text. The service may return multiple language guesses for an individual request.
Attributes
| _language_code | The language code guessed for the text. A list of available languages is available at: https://docs.aws.amazon.com/comprehend/latest/dg/supported-languages.html |
| _confidence | The probability that a given prediction is correct. |
| _text | The text analyzed. |
Sentiment Detection
Detects the sentiment for text.
Attributes
| _sentiment | The sentiment for the text. Possible values are: POSITIVE, NEGATIVE, NEUTRAL, MIXED |
| _sentiment_postive | The confidence score for positive sentiment. |
| _sentiment_negative | The confidence score for negative sentiment. |
| _sentiment_neutral | The confidence score for neutral sentiment. |
| _sentiment_mixed | The confidence score for mixed sentiment. |
| _text | The text analyzed. |
Key Phrase Detection
Detects the key phrases in text.
Attributes
| _key_phrases{}.text | The key phrases from the text. |
| _key_phrases{}.confidence | A number between 0 and 1 that indicates the confidence score for the key phrase. |
| _key_phrases{}.begin_offset | The key phrase beginning offset in the text. |
| _key_phrases{}.end_offset | The key phrase ending offset in the text. |
| _text | The original text. |
Entity Detection
Detects the entities in text. The service can return multiple entities in a given text.
Attributes
| _entities{}.text | The entity from the text. |
| _entities{}.confidence | A number between 0 and 1 that indicates the confidence score for the entity. |
| _entities{}.begin_offset | The entity beginning offset in the text. |
| _entities{}.end_offset | The entity ending offset in the text. |
| _entities{}.type | The type of the detected entity. Types can be found here: https://docs.aws.amazon.com/comprehend/latest/dg/how-entities.html |
Initiator
The incoming feature is output through this port.
<Rejected>
Features that cause the operation to fail are output through this port. An fme_rejection_code attribute, having the value ERROR_DURING_PROCESSING, will be added, along with a more descriptive fme_rejection_message attribute which contains more specific details as to the reason for the failure.
Note: If a feature comes in to the ComprehendConnector already having a value for fme_rejection_code, this value will be removed.
Rejected Feature Handling: can be set to either terminate the translation or continue running when it encounters a rejected feature. This setting is available both as a default FME option and as a workspace parameter.
Parameters
Authentication
| Credential Source |
The ComprehendConnector can use credentials from different sources. Using a web connection integrates best with FME, but in some cases, you may wish to use one of the other sources.
|
| Account |
Available when the credential source is Web Connection. To create a Comprehend connection, click the 'Account' drop-down box and select 'Add Web Connection...'. The connection can then be managed via Tools -> FME Options... -> Web Connections. |
| Region | The AWS Region through which to access Comprehend. To optimize latency, it is best practice to specify the correct region. |
| Access Key and Secret Access Key | Available when the credential source is Embedded. An access key ID and secret access key can be specified directly in the transformer instead of in a web connection. |
Request
| Text | The text where the chosen detection will be performed. |
| Action |
The type of operation to perform. Choices are:
|
Entity, Key Phrase, and Sentiment Detection Options
|
Language |
This parameter is available when the Action parameter is Entity Detection, Key Phrase Detection, or Sentiment Detection. This parameter specifies the language of the text. All text must be in the same language per transformer. |
Editing Transformer Parameters
Using a set of menu options, transformer parameters can be assigned by referencing other elements in the workspace. More advanced functions, such as an advanced editor and an arithmetic editor, are also available in some transformers. To access a menu of these options, click 
beside the applicable parameter. For more information, see Transformer Parameter Menu Options.
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. There are a number of tools and shortcuts that can assist in constructing values, generally available from the drop-down context menu adjacent to the value field.
How to Set Parameter Values
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.
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.
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
| These functions manipulate and format strings. | |
|
Special Characters |
A set of control characters is available in the Text Editor. |
| Math functions are available in both editors. | |
| Date/Time Functions | Date and time functions are available in the Text Editor. |
| These operators are available in the Arithmetic Editor. | |
| These return primarily feature-specific values. | |
| FME and workspace-specific parameters may be used. | |
| Creating and Modifying User Parameters | Create your own editable parameters. |
Reference
|
Processing Behavior |
|
|
Feature Holding |
No |
| Dependencies | Amazon AWS Account with Comprehend access |
| FME Licensing Level | FME Base Edition and above |
| Aliases | AmazonAWSComprehendConnector |
| History | Released FME 2019.2 |
| Categories |
FME Community
The FME Community is the place for demos, how-tos, articles, FAQs, and more. Get answers to your questions, learn from other users, and suggest, vote, and comment on new features.
Search for all results about the ComprehendConnector on the FME Community.
Examples may contain information licensed under the Open Government Licence – Vancouver