Watson Natural Language Understanding
The Qlik Watson Natural Language Understanding connector uses the Natural Language Understanding API to interpret and analyze the semantic features of content using Watson.
Supported offerings
- Qlik Sense Business
- Qlik Sense Enterprise SaaS
Ways to access your data
To be able to use Watson Natural Language Understanding, you need to authenticate the connector with your Watson account credentials. After you create a connection and select Watson Natural Language Understanding as your data source, you are requested to log in with your credentials.
Creating a data source connection
Loading data from tables
After you authenticate the connector with your account credentials, use the available tables to fetch data. The table below outlines some of the use cases for some of the available tables:
| Table | Description |
|---|---|
| Keywords | Use this to identify keywords in the content and to make a sentiment and emotion analysis of the keywords. |
| Sentiment | Use this to analyze the sentiment of the content or target phrases. |
| Entities | Use this to identify entities referenced in the content and to make a sentiment and emotion analysis of the detected entities. |
To select and load data from a table, enter the required table parameters and click Preview data. Required parameters are marked with an asterisk (*) in the dialog. The table fields are displayed under the Data preview tab. You can select fields individually by selecting the box beside each field name. Select Insert script after you have made your selection.
Creating a connection and selecting data
Working with the Natural Language Understanding API quota limits
The Qlik Web Connectors use the Natural Language Understanding API to extract data from Watson and load it into your Qlik Sense app. While reloading your Watson-based app, you might receive an error message that the connector has reached the Natural Language Understanding API rate limit and that all subsequent API calls will fail until the connector falls back under the throttling limit. If you receive this error message, then you have exceeded one of the API rate limits.
Reference - Natural Language Understanding API documentation
You can refer to the Natural Language Understanding API documentation to learn more about the requirements and restrictions imposed by the Natural Language Understanding API.
Natural Language Understanding API
Troubleshooting
You receive an error message that you have reached the API rate limit
Possible cause
You have exceeded the API limits that are imposed by the Natural Language Understanding API.
Proposed action
To reduce the impact of reaching API rate limits, develop your app with the following in mind:
- Extract only the data you need.
- Reload one Watson-based application at a time.
- Ensure that loops in your script that make API calls do not result in infinite loops.