Learning natural language processing with NLP Sample
NLP Sample is a reference application that contains a set of ready-to-use tools and example use cases to guide you through natural language processing (NLP) on Pega Platform. After you become comfortable with the examples, you can build your own tools for text analytics and use NLP Sample to analyze news-feeds, emails, and posts on social media.
Install NLP Sample by importing the archive file that contains the application ruleset.
- Download the following archive file that contains the NLP Sample ruleset: NLP Sample 8.1.
- Import the archive file to your application. For more information, see Importing rules and data by using the Import wizard.
- Log in to Pega Platform by entering the following
- User name – [email protected]
- Password – rules
- In Dev Studio, open NLP Sample by clicking .
Understanding natural language processing
Discover natural language processing features in Pega Platform, explore how to use the processing outcome to create a case, and learn how to increase the accuracy of machine-learning models by reviewing the analyzed records and providing feedback.
Exploring NLP features
Learn about natural language processing features in Pega Platform by exploring text categorization, text extraction, and language detection. Use the default examples or provide custom input to classify text into various categories, derive sentiment, extract named entities, and create summaries.
Understanding NLP in the application context
Learn how to use text analysis outcome to create a case and assign it to an operator or a group. After you process input records, you can view a summary report as well as a detailed analysis of individual records.
Updating machine-learning models with feedback
Increase machine-learning models accuracy by updating records that you analyze with your feedback, for example, the correct sentiment value, intent, category, or entity. When you collect the updated records, you can retrain the corresponding model to classify similar records correctly in future analyses.
For more information about tools and features for text analytics, see Building text analyzers.
Previous topic Training data size considerations for building text analytics models Next topic Text Analytics APIs