To skip the background information and go straight to the lab's steps, go here.
“The service enables developers without a background in machine learning or statistical algorithms to create natural language interfaces for their applications. The service interprets the intent behind text and returns a corresponding classification with associated confidence levels. The return value can then be used to trigger a corresponding action, such as redirecting the request or answering a question.
The Natural Language Classifier is tuned and tailored to short text (1000 characters or less) and can be trained to function in any domain or application.
- Tackle common questions from your users that are typically handled by a live agent.
- Classify SMS texts as personal, work, or promotional
- Classify tweets into a set of classes, such as events, news, or opinions.
- Based on the response from the service, an application can control the outcome to the user. For example, you can start another application, respond with an answer, begin a dialog, or any number of other possible outcomes.
- Text to a pre-trained model
- Watch video
- Check out demo
“The Natural Language Classifier is designed to be trained easily for your use case and data. The service is "well-read" in the content of Wikipedia. That background knowledge means that it can return classes for texts that it has not seen in training.”
“One use of the service is to take some of the load off your support staff. Answer your customer's questions quickly and accurately. Take predictive actions, such as routing a user's question to the correct person in real time.”
Here are some other examples of how you might apply the Natural Language Classifier:
- Twitter, SMS, and other text messages
- Classify tweets into a set of classes, such as events, news, or opinions.
- Analyze text messages into categories, such as Personal, Work, or Promotions.
- Sentiment analysis
- Analyze text from social media or other sources and identify whether it relates positively or negatively to an offering or service.
- Now that you've read through the background information you can run through a lab here